WO2014017434A1 - 画像処理装置 - Google Patents
画像処理装置 Download PDFInfo
- Publication number
- WO2014017434A1 WO2014017434A1 PCT/JP2013/069785 JP2013069785W WO2014017434A1 WO 2014017434 A1 WO2014017434 A1 WO 2014017434A1 JP 2013069785 W JP2013069785 W JP 2013069785W WO 2014017434 A1 WO2014017434 A1 WO 2014017434A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- unit
- image
- detection
- sun
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/51—Housings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Definitions
- the present invention relates to an image processing apparatus.
- Patent Document 1 discloses a vehicle image processing apparatus that can estimate the luminance change of the sun or a headlight by luminance change estimation means.
- the image processing apparatus calculates an image acquisition unit that acquires a captured image output by the camera shooting outside the vehicle, and calculates the position of the sun including at least the altitude of the sun. Based on the image information of the first image area of the captured image, a sun determination unit that determines that the altitude of the camera is less than a predetermined altitude, a cloudiness detection unit that detects that the lens surface of the camera is clouded, A vehicle detection unit that detects another vehicle different from the vehicle, and a sun determination unit that the altitude of the sun is equal to or lower than a predetermined altitude when at least the first image area is clouded is detected by the cloudiness detection unit.
- the vehicle detection unit has a predetermined threshold related to the detection sensitivity of the other vehicle, and the control unit is configured to detect the position of the sun on the lens surface.
- the sun determination unit calculates the position of the sun based on the date and time, the latitude and longitude where the vehicle is located, and the direction of the vehicle.
- the sun determination unit calculates the position of the sun by performing image processing on the captured image.
- the camera captures at least a road surface outside the vehicle, and the sun determination unit extracts a high-luminance region due to road surface reflection from the captured image. It is preferable to calculate the position of the sun based on the position of the center of gravity of the high-luminance region.
- the control unit corresponds to the image range in the lens surface based on the luminance gradient of the image range centered on the position of the sun. It is preferable to detect that the range is cloudy.
- a cloudiness detection region is set in the photographed image, and the cloudiness detection unit calculates an edge intensity histogram for the cloudiness detection region. Based on the average value of the edge intensity calculated using the histogram, a region where the camera lens is clouded is detected.
- the camera captures at least a road surface outside the vehicle, and a plurality of cloudiness detection areas are provided in the vicinity of the vanishing point of the white line provided on the road surface.
- the white turbidity detection unit calculates a histogram of edge intensity for each of the white turbidity detection areas, and the camera lens is white turbid based on the average value of the edge intensity calculated using each of the histograms. Detect areas.
- the camera captures at least a road surface outside the vehicle, and the cloudiness detection region is in the vicinity of the vanishing point of the white line provided on the road surface.
- the cloudiness detection unit detects the area where the camera lens is clouded using the first cloudiness detection area during the daytime, and the camera lens is clouded using the second cloudiness detection area during the nighttime. Detect the area.
- the predetermined notification unit is notified that the control unit has suppressed the detection of the other vehicle by the vehicle detection unit. It is preferable to further include a notification control unit.
- the cloudiness detection unit causes the camera lens surface to become cloudy when the cloudiness degree of the camera lens surface exceeds the first cloudiness degree.
- the vehicle detection unit sets the threshold to the first threshold when the lens surface of the camera is not cloudy, and sets the threshold to the first threshold.
- a third threshold value is set to a second threshold value that is larger than the first threshold value and the threshold value is set to a third threshold value that is smaller than either the first threshold value or the second threshold value when the degree of cloudiness is exceeded. Is preferably provided between the second cloudiness degree and the first cloudiness degree.
- the accuracy of the image recognition process does not deteriorate even when sunlight enters the photographed image.
- FIG. 1 It is a block diagram which shows the structure of the vehicle-mounted vehicle recognition apparatus by the 1st Embodiment of this invention. It is a figure which shows the imaging
- FIG. 1 is a block diagram showing a configuration of an in-vehicle vehicle recognition device 100 according to the first embodiment of the present invention.
- An in-vehicle vehicle recognition device 100 shown in FIG. 1 is used by being mounted on a vehicle, and includes a camera 1, a control unit 2, an alarm output unit 3, and an operation state notification unit to which a light shielding plate 1a is attached. 4, an external device control unit 5, and a storage unit 6.
- the camera 1 is installed toward the rear of the vehicle, and takes images in a shooting area including the road surface behind the vehicle at predetermined time intervals.
- an image sensor such as a CCD or a CMOS is used.
- a captured image acquired by the camera 1 is output from the camera 1 to the control unit 2.
- FIG. 2 is a diagram showing a shooting area and a light shielding area of the camera 1, and shows a state in which the camera 1 is viewed from the lateral direction.
- the upper part of the photographing area of the camera 1 is masked by the light shielding plate 1a to form a light shielding area.
- the camera 1 captures an image including a road surface behind the vehicle in an imaging region other than the light shielding region.
- the shooting area (view angle) of the camera 1 is set to be relatively wide so that the road surface behind the vehicle can be shot in a sufficiently wide range in the left-right direction. Unnecessary light is also incident on the camera 1. Therefore, in order to block such unwanted incident light on the camera 1, a light shielding region is provided by the light shielding plate 1a.
- FIG. 3 is a diagram showing an example of the attachment position of the camera 1.
- a number plate 21 is installed on the vehicle body 20 at the rear portion of the host vehicle.
- the camera 1 is mounted obliquely downward at a position directly above the number plate 21, and a light shielding plate 1a is installed thereon.
- the attachment position shown here is an example to the last, you may attach the camera 1 to another position. As long as the road surface behind the vehicle can be photographed within an appropriate range, the mounting position of the camera 1 may be determined in any way.
- the control unit 2 executes a program stored in the storage unit 6 to perform predetermined image processing using a photographed image from the camera 1, and performs various controls according to the processing result.
- a program stored in the storage unit 6 to perform predetermined image processing using a photographed image from the camera 1, and performs various controls according to the processing result.
- LDW Li Departure Warning
- BSW Blind Spot Warning
- MOD Motion Object Detection
- PED Pedestrian Detection
- RSR Raad Sign
- Various functions called Recognition and IMD Image Diagnosis
- the LDW is a function that outputs a warning when the host vehicle is likely to deviate from the traveling lane by detecting a white line (lane boundary line, vehicle outer line, etc.) on the road surface from the photographed image.
- MOD is a function that informs the driver of the presence of a moving object around the host vehicle when moving backward by detecting the moving object from a captured image.
- PED is a function that informs the driver of the presence of a pedestrian on the path of the vehicle by detecting the shape of a person from a captured image.
- the RSR is a function for recognizing a traffic sign on a road from a photographed image and, for example, warning a driver when the speed exceeds a speed limit sign.
- the IMD is a function for diagnosing whether a captured image is correctly captured by the camera 1.
- the BSW is a function that warns the driver of the presence of a vehicle that may collide with the host vehicle when the lane is changed by detecting another vehicle traveling on the road from the captured image.
- the alarm output unit 3 is a part for outputting an alarm by an alarm lamp or an alarm buzzer to the vehicle driver.
- the warning lamps are installed on both sides of the front pillar of the vehicle.
- the operation of the alarm output unit 3 is controlled by the control unit 2. For example, when it is determined in the aforementioned LDW that the host vehicle is about to depart from the lane in which the vehicle is traveling, or when a vehicle that may collide with the host vehicle is detected in the BSW, according to the control of the control unit 2 An alarm is output from the alarm output unit 3.
- the operation state notification unit 4 is a part for notifying the driver of the vehicle of the operation state of the vehicle-mounted vehicle recognition device 100. For example, when the in-vehicle vehicle recognition device 100 is in a non-operating state without satisfying a predetermined operating condition, a lamp installed near the driver's seat of the vehicle as the operating state notifying unit 4 under the control of the control unit 2 Lights up. This notifies the driver that the vehicle-mounted vehicle recognition device 100 is in a non-operating state.
- the external device control unit 5 controls the external device according to the control from the control unit 2.
- the BSW control performed by the control unit 2 in the vehicle-mounted vehicle recognition device 100 will be described.
- a strong light source such as the sun
- the contrast is lowered near the position of the light source in the shot image.
- dirt is attached to the photographing lens of the camera 1 and it is clouded
- the contrast of the entire photographed image further decreases.
- the control unit 2 controls the operation of the BSW based on the position and degree of cloudiness on the lens surface of the photographing lens of the camera 1 when the sun is present in the photographing region.
- FIG. 4 is a control block diagram of the control unit 2 related to BSW. As illustrated in FIG. 4, the control unit 2 includes an image acquisition unit 31, a BSW unit 32, a cloudiness detection unit 33, a sun determination unit 34, and a BSW control unit 35.
- Image acquisition unit 31 acquires image information of a captured image from the camera 1 every predetermined time. Image information of the captured image acquired by the image acquisition unit 31 is output to at least the BSW unit 32 and the cloudiness detection unit 33. In FIG. 4, the image acquisition unit 31 also outputs image information of the captured image to the BSW control unit 35.
- the BSW unit 32 includes a vehicle detection unit 41 and a notification control unit 42.
- the vehicle detection unit 41 includes a viewpoint conversion unit 411, an alignment unit 412, and a three-dimensional object detection unit 413.
- the viewpoint conversion unit 411 converts the viewpoint of the image information of the captured image acquired by the image acquisition unit 31 into bird's-eye image data in a bird's-eye view state.
- the state viewed from the bird's-eye view is a state viewed from the viewpoint of the virtual camera looking down from above, for example, vertically downward.
- This viewpoint conversion can be executed as described in, for example, Japanese Patent Application Laid-Open No. 2008-219063.
- the viewpoint conversion of captured image data to bird's-eye view image data is based on the principle that a vertical edge peculiar to a three-dimensional object is converted into a group of straight lines passing through a specific fixed point by viewpoint conversion to bird's-eye view image data. This is because a planar object and a three-dimensional object can be distinguished if used.
- the alignment unit 412 sequentially receives the bird's-eye image data obtained by the viewpoint conversion of the viewpoint conversion unit 411, and aligns the positions of the inputted bird's-eye image data at different times.
- 5A and 5B are diagrams for explaining the outline of the processing of the alignment unit 412.
- FIG. 5A is a plan view showing the moving state of the host vehicle V
- FIG. 5B is an outline of the alignment. It is an image.
- the host vehicle V at the current time is located at V1, and the host vehicle V one hour before is located at V2.
- the other vehicle VX is positioned in the rear direction of the host vehicle V and is in parallel with the host vehicle V, the other vehicle VX at the current time is positioned at V3, and the other vehicle VX one hour before is positioned at V4.
- the host vehicle V has moved a distance d at one time.
- “one hour ago” may be a past time for a predetermined time (for example, one control cycle) from the current time, or may be a past time for an arbitrary time.
- the bird's-eye image PB t at the current time is as shown in Figure 5 (b).
- the bird's-eye image PB t becomes a rectangular shape for the white line drawn on the road surface, but a relatively accurate is a plan view state, tilting occurs about the position of another vehicle VX at position V3.
- the white line drawn on the road surface is rectangular and is in a state of being relatively accurately viewed in plan, but the other vehicle VX at the position V4 is Falls down.
- the alignment unit 412 performs alignment of the bird's-eye images PB t and PB t ⁇ 1 as described above on the data. At this time, the alignment unit 412 offsets the bird's-eye view image PB t-1 at the previous time and matches the position with the bird's-eye view image PB t at the current time.
- the image on the left side and the center image in FIG. 5B show a state that is offset by the movement distance d ′.
- This offset amount d ′ is the amount of movement on the bird's-eye view image data corresponding to the actual movement distance d of the host vehicle V shown in FIG. 5A, and the signal from the vehicle speed sensor and the current time from one hour before. It is determined based on the time until.
- the alignment unit 412 takes the difference between the bird's-eye images PB t and PB t ⁇ 1 and generates data of the difference image PD t .
- the pixel value of the difference image PD t may be an absolute value of the difference between the pixel values of the bird's-eye images PB t and PB t ⁇ 1 , and the absolute value is predetermined in order to cope with a change in the illuminance environment. It may be set to “1” when the threshold value p is exceeded and “0” when the threshold value p is not exceeded.
- a difference image PD t Right side of the image in FIG. 5 (b), a difference image PD t. This threshold value p may be set in advance.
- Three-dimensional object detection unit 413 of FIG. 4 detects three-dimensional object on the basis of the data of the difference image PD t shown in Figure 5 (b).
- the three-dimensional object detected by the three-dimensional object detection unit 413 includes other vehicles that may come into contact when the host vehicle V changes lanes.
- the three-dimensional object detection unit 413 also calculates the movement distance of the three-dimensional object in real space.
- the three-dimensional object detection unit 413 uses the movement distance of the three-dimensional object per time for calculating the movement speed of the three-dimensional object. Then, the three-dimensional object detection unit 413 uses the moving speed of the three-dimensional object to determine whether or not the three-dimensional object is a vehicle.
- the three-dimensional object detection unit 413 first generates a differential waveform. In generating the difference waveform, the three-dimensional object detection unit 413 sets a detection region in the difference image PD t .
- FIG. 6 is a diagram illustrating an example of the detection area. In FIG. 6, rectangular detection areas A1 and A2 are illustrated on the left and right sides behind the host vehicle V. In the detection areas A1 and A2 in FIG. 6, the other vehicle is detected as a three-dimensional object traveling in the lane adjacent to the lane in which the host vehicle V is traveling.
- the detection areas A1 and A2 are provided in the left and right lanes adjacent to the lane in which the host vehicle V travels.
- the three-dimensional object detection unit 413 may set the detection areas A1 and A2 based on the relative position with respect to the host vehicle V, or may set the white line position using the existing white line recognition technology or the like as a reference. Good.
- the three-dimensional object detection unit 413 recognizes the sides (sides along the traveling direction) of the set detection areas A1 and A2 on the own vehicle V side as the ground lines L1 and L2.
- the ground line means a line in which a three-dimensional object contacts the ground, but in the present embodiment, it is set as described above, not a line in contact with the ground. Even in this case, from experience, the difference between the ground line according to the present embodiment and the ground line obtained from the position of the other vehicle VX is not too large, and there is no problem in practical use.
- FIG. 7 is a schematic diagram showing how a three-dimensional object detection unit 413 generates a differential waveform.
- the three-dimensional object detection unit 413 calculates the difference from the portion corresponding to the detection areas A1 and A2 in the difference image PDt (for example, the right diagram in FIG. 5B) calculated by the alignment unit 412.
- a waveform DWt is generated.
- the three-dimensional object detection unit 413 generates a differential waveform DWt along the direction in which the three-dimensional object falls due to viewpoint conversion.
- the detection area A1 is described for convenience, but the difference waveform DWt is generated for the detection area A2 in the same procedure.
- the three-dimensional object detection unit 413 defines a line La in the direction in which the three-dimensional object falls on the data of the difference image DWt. Then, the three-dimensional object detection unit 413 counts the number of difference pixels DP indicating a predetermined difference on the line La.
- the difference pixel DP indicating a predetermined difference is a pixel that exceeds a predetermined threshold when the pixel value of the difference image DWt is an absolute value of the difference between the pixel values of the bird's-eye images PB t and PB t ⁇ 1.
- the pixel value of the difference image DWt is expressed by “0” and “1”, it is a pixel indicating “1”.
- the three-dimensional object detection unit 413 calculates the intersection CP between the line La and the ground line (for example, the ground line L1) after counting the number of difference pixels DP. Then, the three-dimensional object detection unit 413 associates the intersection CP with the count number, determines the horizontal axis position based on the position of the intersection CP, that is, the position on the vertical axis in the right diagram of FIG. The axis position, that is, the position on the left-right axis in the right diagram of FIG. 7 is determined and plotted as the count number at the intersection CP.
- the three-dimensional object detection unit 413 defines lines Lb, Lc... In the direction in which the three-dimensional object falls, counts the number of difference pixels DP, and determines the horizontal axis position based on the position of each intersection CP. Then, the vertical axis position is determined from the count number (number of difference pixels DP) and plotted.
- the three-dimensional object detection unit 413 generates the differential waveform DWt as shown in the right diagram of FIG.
- the distance La and the line Lb in the direction in which the three-dimensional object falls are different from each other in the overlapping distance with the detection area A1. For this reason, if the detection area A1 is filled with the difference pixels DP, the number of difference pixels DP is greater on the line La than on the line Lb. For this reason, when the three-dimensional object detection unit 413 determines the vertical axis position based on the count number of the difference pixels DP, the three-dimensional object detection unit 413 is normalized based on the distances where the lines La and Lb in the direction in which the three-dimensional object falls and the detection area A1 overlap. Turn into. Specifically, in the left diagram of FIG.
- the three-dimensional object detection unit 413 normalizes the count number by dividing it by the overlap distance.
- the difference waveform DW t the line La on the direction the three-dimensional object collapses, the value of the differential waveform DW t corresponding to Lb is substantially the same.
- the three-dimensional object detection unit 413 calculates the movement distance by comparison with the differential waveform DW t ⁇ 1 one time before. That is, the three-dimensional object detection unit 413 calculates the movement distance from the time change of the differential waveforms DW t and DW t ⁇ 1 .
- the three-dimensional object detection unit 413 first divides the differential waveform DW t into a plurality of small areas DW t1 to DW tn (n is an arbitrary integer equal to or greater than 2).
- FIG. 8 is a diagram illustrating small areas DW t1 to DW tn divided by the three-dimensional object detection unit 413.
- the small areas DW t1 to DW tn are divided so as to overlap each other, for example, as shown in FIG. In FIG. 8, the small area DW t1 and the small area DW t2 overlap, and the small area DW t2 and the small area DW t3 overlap.
- the three-dimensional object detection unit 413 calculates an offset amount for each of the small areas DW t1 to DW tn .
- the offset amount is the amount of movement in the horizontal axis direction (vertical direction in FIG. 8) of the differential waveform, and the difference (horizontal axis direction) between the differential waveform DW t ⁇ 1 at the previous time and the differential waveform DW t at the current time. Calculated based on the distance.
- the three-dimensional object detection unit 413 calculates an offset amount for each of the small areas DW t1 to DW tn by the following process.
- the three-dimensional object detection unit 413 moves the differential waveform DW t ⁇ 1 at the previous time in the horizontal axis direction for each of the small areas DW t1 to DW tn to minimize the error from the differential waveform DW t at the current time.
- the position (position in the horizontal axis direction) is searched.
- the three-dimensional object detection unit 413 calculates, for each of the small areas DW t1 to DW tn , the amount of movement in the horizontal axis direction between the position where the error is minimum and the original position of the differential waveform DW t ⁇ 1. The amount of movement is taken as the offset amount.
- the three-dimensional object detection unit 413 generates a histogram of the offset amount calculated for each of the small areas DW t1 to DW tn, and calculates the moving distance of the three-dimensional object from the histogram.
- FIG. 9 is a diagram illustrating an example of an offset amount histogram. As shown in FIG. 9, since the offset amount varies somewhat, the three-dimensional object detection unit 413 forms a histogram of the offset amount including the variation, and calculates the moving distance of the three-dimensional object from the histogram.
- the three-dimensional object detection unit 413 calculates the moving distance of the three-dimensional object based on the maximum value of the offset amount histogram. For example, in the example of FIG. 9, the maximum value of the histogram is the movement distance ⁇ * .
- the three-dimensional object detection unit 413 calculates the absolute movement distance of the three-dimensional object based on the movement distance ⁇ * and the signal from the vehicle speed sensor provided in the host vehicle V.
- the three-dimensional object detection unit 413 weights each of the plurality of small areas DW t1 to DW tn and counts the offset amount obtained for each of the small areas DW t1 to DW tn according to the weights to form a histogram. May be.
- FIG. 10 is a diagram illustrating weighting by the three-dimensional object detection unit 413.
- the small area DW m (m is an integer of 1 to n ⁇ 1) is flat.
- the three-dimensional object detection unit 413 reduces the weight for such a small region DW m . This is because the flat small area DW m has no characteristics and is likely to have a large error in calculating the offset amount.
- the small region DW m + k (k is an integer equal to or less than nm) is rich in undulations.
- Three-dimensional object detection unit 413 increases the weight for such small area DW m. This is because the small region DW m + k rich in undulations is characteristic and there is a high possibility that the offset amount can be accurately calculated. By weighting in this way, the calculation accuracy of the moving distance of the three-dimensional object can be improved.
- FIGS. 11 and 12 are flowcharts relating to the processing of the vehicle detection unit 41 executed by the control unit 2.
- the viewpoint conversion unit 411 generates bird's-eye image data based on the image information of the captured image acquired by the image acquisition unit 31.
- the alignment unit 412 aligns the bird's-eye view image PB t and the bird's-eye view image PB t-1 one hour before.
- the three-dimensional object detection unit 413 generates a difference image PD t.
- step S130 the three-dimensional object detection unit 413 and the data of the difference image PD t, and a one unit time before the difference image PD t-1 of the data, generates a difference waveform DW t.
- step S140 the three-dimensional object detection unit 413 determines whether or not the peak of the differential waveform DW t is greater than or equal to the first threshold value ⁇ .
- the first threshold value ⁇ is set under the control of the BSW control unit 35 described later.
- the process of the vehicle detection unit 41 proceeds to step S150 in FIG. 12 when step S140 is affirmed, and proceeds to step S230 in FIG. 12 when step S140 is negative.
- step S150 of FIG. 12 the three-dimensional object detection unit 413 divides the differential waveform DW t into a plurality of small regions DW t1 to DW tn .
- step S160 as described with reference to FIG. 9, the three-dimensional object detection unit 413 performs weighting for each of the small areas DW t1 to DW tn .
- step S170 the three-dimensional object detection unit 413 calculates an offset amount for each of the small areas DW t1 to DW tn .
- step S180 the three-dimensional object detection unit 413 generates a histogram of offset amounts for each of the small areas DW t1 to DW tn .
- step S190 the three-dimensional object detection unit 413 calculates a relative movement distance that is a movement distance of the three-dimensional object with respect to the host vehicle V based on the histogram generated in step S180.
- step S200 the three-dimensional object detection unit 413 calculates the absolute movement speed of the three-dimensional object from the relative movement distance calculated in step S190.
- the three-dimensional object detection unit 413 calculates the relative movement speed by differentiating the relative movement distance with respect to time, and calculates the absolute movement speed by adding the own vehicle speed detected by the vehicle speed sensor or the like of the own vehicle.
- step S210 the three-dimensional object detection unit 413 determines whether the absolute movement speed of the three-dimensional object is ⁇ km / h or more and the relative movement speed of the three-dimensional object is ⁇ 1 km / h or more and ⁇ 2 km / h or less. judge. For example, the three-dimensional object detection unit 413 determines whether or not the absolute movement speed of the three-dimensional object is 20 km / h or more and the relative movement speed of the three-dimensional object with respect to the host vehicle V is ⁇ 20 km / h or more and +40 km / h or less. To do.
- the process of the vehicle detection unit 41 proceeds to step S220 when the affirmative determination is made in step S210, and proceeds to step S230 when the negative determination is made in step S210.
- step S220 the three-dimensional object detection unit 413 determines that the three-dimensional object is the other vehicle VX.
- step S230 the three-dimensional object detection unit 413 determines that there is no other vehicle. And the control part 2 complete
- the cloudiness detection unit 33 sets a cloudiness detection region for the photographed image of the camera 1 and generates a histogram of edge intensity for each cloudiness detection region. Then, when the average value of the histogram is equal to or less than a predetermined value, the cloudiness detection unit 33 determines that the photographing lens of the camera 1 is cloudy.
- FIG. 13 is a diagram illustrating a cloudiness detection region.
- FIG. 13 illustrates white turbidity detection areas 51, 52, and 53.
- the cloudiness detection areas 51, 52, and 53 are set in the vicinity of the vanishing point 56 where the white line 54 and the white line 55 intersect in the captured image 50.
- the cloudiness detection areas 52 and 53 have a symmetrical shape with respect to each other, and are set at symmetrical positions.
- the cloudiness detection areas 52 and 53 correspond to the detection areas A1 and A2 set by the three-dimensional object detection unit 413, respectively, and are used to detect that the lens surface corresponding to the detection areas A1 and A2 is cloudy. It is done.
- the cloudiness detection areas 52 and 53 are set at positions that sandwich the cloudiness detection area 51.
- the white turbidity detection areas 52 and 53 extend below the white turbidity detection area 51 and can detect an edge in the vicinity of the host vehicle V, so that it is detected at night that the lens surface is cloudy. Is suitable.
- the cloudiness detection area 51 has a symmetrical shape, and is set above the center of the captured image and below the light shielding portion 57.
- the white turbidity detection region 51 has a region overlapping with the white turbidity detection region 52 and a region overlapping with the white turbidity detection region 53.
- the cloudiness detection area 51 is used to detect that the lens surface corresponding to the detection area A1 set by the three-dimensional object detection unit 413 or the lens surface corresponding to the detection area A2 is cloudy.
- the image in the white turbidity detection region 51 has relatively little change even when the host vehicle V is traveling, so that the detection accuracy is stable.
- region 51 can detect the edge far from the own vehicle V, it is suitable for detecting that the lens surface is cloudy in the daytime.
- the white turbidity detection unit 33 detects that at least the lens surface of the photographing lens corresponding to the detection regions A1 and A2 set by the three-dimensional object detection unit 413 is cloudy. be able to.
- FIG. 14 is a flowchart regarding the processing of the cloudiness detection unit 33.
- Image information of a captured image acquired by the image acquisition unit 31 is input to the white turbidity detection unit 33.
- image information of the captured image 50 in FIG. 13 is input.
- the control unit 2 generates an edge detection image for the captured image using a well-known edge detection process.
- step S301 the control unit 2 generates, for the region corresponding to the cloudiness detection region 51 in the edge detection image generated in step S300, a histogram H1 related to the edge strength of the edge included in the region.
- step S302 the control unit 2 generates, for the region corresponding to the cloudiness detection region 52 in the edge detection image generated in step S300, a histogram H2 regarding the edge strength of the edge included in the region.
- step S303 the control unit 2 generates a histogram H3 related to the edge strength of the edge included in the region corresponding to the cloudiness detection region 53 in the edge detection image generated in step S300. Note that the order of step S301, step S302, and step S303 may be executed in an arbitrary order.
- step S304 the control unit 2 calculates an average value E1 of the histogram H1, an average value E2 of the histogram H2, and an average value E3 of the histogram H3.
- step S305 the control unit 2 determines whether the average value E1 is equal to or greater than the predetermined threshold value ⁇ 1, the average value E2 is equal to or greater than the predetermined threshold value ⁇ 2, and the average value E3 is equal to or greater than the predetermined threshold value ⁇ 3. Determine whether. If the determination in step S305 is affirmative, the control unit 2 advances the process in FIG. 11 to step S307. If the determination in step S305 is negative, the control unit 2 advances the process in FIG. 11 to step S306.
- step S304 may be different depending on whether white turbidity detection is performed during the day or when white turbidity detection is performed at night. For example, when white turbidity detection is performed in the daytime, the control unit 2 may determine whether or not the average value E1 is equal to or greater than a predetermined threshold value ⁇ 1. Further, when the cloudiness detection is performed at night, the control unit 2 determines whether the average value E2 is equal to or greater than the predetermined threshold value ⁇ 2 and whether the average value E3 is equal to or greater than the predetermined threshold value ⁇ 3. Good. That is, the cloudiness detection may be performed using the cloudiness detection area 51 during the daytime and the cloudiness detection areas 52 and 53 may be performed during the nighttime.
- step S306 the control unit 2 determines that the taking lens of the camera 1 is not clouded.
- step S307 the control unit 2 determines that at least the lens surface corresponding to the detection region A1 or A2 is clouded among the lens surfaces of the photographing lens of the camera 1.
- the sun determination unit 34 in FIG. 4 calculates the position of the sun and determines whether or not sunlight is incident on the imaging region of the camera 1.
- the position of the sun calculated by the sun determination unit 34 includes at least the altitude of the sun.
- the sun determination unit 34 calculates the altitude of the sun based on, for example, date and time information and the latitude of the vehicle position where the vehicle V is present.
- the sun determination part 34 calculates the azimuth
- the direction of the sun can be calculated based on, for example, date and time information, the latitude and longitude of the vehicle position, and the direction of the vehicle V.
- the sun determination unit 34 sets a predetermined range centered on the calculated altitude and direction of the sun as the solar range.
- FIG. 15 is a diagram illustrating the solar range.
- FIG. 15 illustrates an example of a position 60 corresponding to the altitude and direction of the sun calculated by the sun determination unit 34 and a sun range 61 corresponding to the position 60 on the photographed image 50.
- the sun determination unit 34 determines whether or not a part of the sun range overlaps the shooting area. That is, it is determined whether or not the altitude of the sun is below a predetermined altitude and the direction of the sun is within a predetermined range.
- the predetermined altitude and the predetermined range are set based on, for example, the direction of the vehicle body of the host vehicle V (the optical axis direction of the camera 1), the angle of the camera 1, and the like.
- the sun determination unit 34 determines whether or not a part of the sun range overlaps the imaging region by determining whether or not the altitude of the sun is equal to or less than a predetermined altitude. To do.
- FIG. 16 is a flowchart regarding the processing of the sun determination unit 34.
- the control unit 2 calculates the position of the sun.
- the control unit 2 sets the solar range based on the position of the sun calculated in step S400.
- step S402 the control unit 2 determines whether or not a part of the sun range overlaps the imaging region. That is, it is determined whether or not the altitude of the sun is below a predetermined altitude and the direction of the sun is within a predetermined range. If the determination in step S402 is affirmative, the control unit 2 advances the process in FIG. 16 to step S403. If the determination in step S402 is negative, the control unit 2 advances the process in FIG. 16 to step S404.
- step S403 the sun determination unit 34 determines that sunlight is incident on the imaging region of the camera 1.
- step S ⁇ b> 404 the sun determination unit 34 determines that sunlight does not enter the shooting area of the camera 1.
- FIG. 17 is an example of a set value table related to the first threshold value ⁇ set by the BSW control unit 35.
- the setting value table in FIG. 17 may be stored in the storage unit 6 as a lookup table. In that case, the BSW control unit 35 refers to the lookup table stored in the storage unit 6 based on the detection result of the cloudiness detection unit 33 and the determination result of the sun determination unit 34, and sets the first threshold value ⁇ . Set.
- FIG. 17 shows the presence or absence of road surface reflection as a parameter for setting the first threshold value ⁇ .
- the presence or absence of road surface reflection is determined by the BSW control unit 35 based on the captured image input from the image acquisition unit 31.
- FIG. 18 is a diagram for explaining determination of the presence or absence of road surface reflection.
- FIG. 18 shows a captured image 80 having a high brightness area 81.
- the center of gravity of the high luminance region is between the upper limit line 82 and the lower limit line 83 shown by the broken line in FIG. It determines with a high-intensity area
- the position where sunlight due to road surface reflection appears in the captured image becomes a lower position in FIG. 18 as the solar altitude increases. Then, sunlight due to road surface reflection does not enter the photographing lens of the camera 1 when the altitude of the sun is equal to or higher than the predetermined altitude Q1. Moreover, the sunlight by road surface reflection will become a brightness
- the upper limit line 82 is set by the predetermined altitude Q2 derived by experiments or the like
- the lower limit line 83 is set by the predetermined altitude Q1 derived by an incident or the like.
- a region sandwiched between the upper limit line 82 and the lower limit line 83 is referred to as a reflected sunlight region.
- the first threshold value ⁇ is expressed as a level.
- the actual setting value of the first threshold value ⁇ which is not expressed in level the larger the level, the larger the value set, and the maximum value at the level 10.
- the set value of the first threshold value ⁇ corresponding to each level is determined in advance at the design stage of the in-vehicle vehicle recognition device 100.
- FIG. 17 is merely an example, and the maximum level may not be level 10.
- the determination in step S140 in FIG. 11 is always negative.
- the vehicle detection unit 41 outputs a detection result that no other vehicle exists regardless of the captured image input from the image acquisition unit 31. Therefore, the notification control unit 42 does not notify the driver of the presence of a vehicle that may collide with the host vehicle in the alarm output unit 3 while the first threshold value ⁇ is set to the maximum level.
- the BSW control unit 35 suppresses the function of the BSW by setting the first threshold value ⁇ to the maximum level in this way.
- the BSW control unit 35 is the No. of FIG. 7 and no. In the situation of 8, the first threshold value ⁇ is set to level 10 (maximum level). When sunlight enters the shooting area of the camera 1, the contrast of the entire captured image of the camera 1 is lowered. Further, when the photographing lens of the camera 1 is clouded, the contrast of the entire photographed image of the camera 1 is further lowered. Thereby, there exists a possibility that the detection accuracy of the other vehicles etc. in the BSW part 32 may deteriorate.
- the BSW control unit 35 suppresses notification by the BSW unit 32 in such a situation, thereby suppressing erroneous detection of other vehicles and not reducing the accuracy of the image recognition process.
- the BSW control unit 35 is No. In the situation of No. 3, no. The first threshold value ⁇ is set lower than the first situation. In addition, the BSW control unit 35 is No. In the situation of No. 5, no. The first threshold value ⁇ is set lower than the first situation. Further, the BSW control unit 35 is set to No. In the situation of No. 4, no. The first threshold value ⁇ is set to be lower than the situation 2. In addition, the BSW control unit 35 is No. In the situation of No. 6, no. The first threshold value ⁇ is set to be lower than the situation 2.
- the BSW control unit 35 sets the first threshold value ⁇ to be low so that the other vehicle Is set so that the detection of other vehicles can be performed with high accuracy in response to a decrease in the peak of the differential waveform due to a decrease in contrast.
- FIG. 19 is a flowchart regarding the processing of the BSW control unit 35.
- the control unit 2 acquires the determination result by the sun determination unit 34. That is, information regarding the determination in step S403 or step S404 in FIG. 16 is acquired.
- step S501 the control unit 2 acquires the detection result by the cloudiness detection unit 33. That is, information related to the determination in step S306 or step S307 in FIG.
- step S502 the control unit 2 extracts pixels with high luminance (for example, luminance is 190 or more in 256 gradations) from the captured image input from the image acquisition unit 31.
- step S503 the control unit 2 extracts an image area having a predetermined number of pixels or more from the pixel block (image area) connected with the pixels extracted in step S502.
- step S504 the control unit 2 determines whether or not an image area whose center of gravity is in the reflected sunlight area exists in the image area extracted in step S503.
- the control unit 2 calculates the centroid for each of the image areas extracted in step S502, and then determines whether these centroids are inside the reflected sunlight area. Then, it is determined whether or not there is an image area having a center of gravity inside the reflected sunlight area among the image areas extracted in step S502.
- step S505 the control unit 2 determines whether the information acquired in steps S500 and S501 is the same as the determination result in step S504 continuously for a predetermined time or more. If the determination in step S505 is affirmative, the control unit 2 proceeds to step S506. If the determination in step S505 is negative, the control unit 2 proceeds to step S500.
- step S506 the control unit 2 sets the first threshold value ⁇ of the BSW unit 32 based on the table of FIG. 17, and then advances the processing of FIG. 19 to step S500.
- Notification control unit 42 When the lane change or the like, when the three-dimensional object detection unit 413 determines that the three-dimensional object is the other vehicle VX in step S220 in FIG. 12, the notification control unit 42 controls the alarm output unit 3 to collide with the own vehicle. The driver is notified of the presence of a vehicle that may On the other hand, when the three-dimensional object detection unit 413 determines that there is no other vehicle in step S230 of FIG. 12, the notification control unit 42 does not perform such notification to the driver.
- FIG. 20 is a flowchart regarding the notification control unit 42.
- step S1000 the control unit 2 determines whether or not BSW is suppressed. For example, it is determined whether or not the first threshold value ⁇ is set to level 10. If the determination in step S1000 is affirmative, the control unit 2 proceeds to step S1001. If the determination in step S1000 is negative, the control unit 2 proceeds to step S1002.
- step S1001 the control unit 2 confirms that the BSW is suppressed and that the lighting of the alarm lamp and the output of the alarm sound are suppressed via the operation state notification unit 4 (for example, the meter of the host vehicle V). Inform.
- step S1002 the control unit 2 determines whether or not the other vehicle VX is detected by the three-dimensional object detection unit 413. If the determination at step S1002 is affirmative, the control unit 2 proceeds to step S1003. If the determination at step S1002 is negative, the control unit 2 proceeds to step S1000.
- step S1003 the control unit 2 turns on an alarm lamp installed on the front pillar in the direction in which another vehicle is detected by the three-dimensional object detection unit 413 in the alarm output unit 3.
- step S1004 the control unit 2 determines whether or not the direction indicator of the host vehicle V existing in the direction in which the other vehicle VX is detected by the three-dimensional object detection unit 413 among the direction indicators of the host vehicle V is flashing. Determine. The blinking state of the direction indicator may be acquired using the CAN communication illustrated in FIG. If the determination at step S1004 is affirmative, the control unit 2 proceeds to step S1005. If the determination at step S1004 is negative, the control unit 2 proceeds to step S1000.
- step S1005 the control unit 2 outputs an alarm sound from the alarm buzzer of the alarm output unit 3.
- the control unit 2 of the in-vehicle vehicle recognition device 100 includes an image acquisition unit 31, a sun determination unit 34, a cloudiness detection unit 33, a vehicle detection unit 41, and a BSW control unit 35.
- the image acquisition unit 31 acquires a captured image output by the camera 1 shooting outside the vehicle.
- the sun determination unit 34 calculates the position of the sun including at least the solar altitude (step S400 in FIG. 16), and at least determines whether the solar altitude is equal to or lower than a predetermined altitude (step S402 in FIG. 16). ).
- the cloudiness detection unit 33 detects that at least the lens surfaces corresponding to the exit areas A1 and A2 are clouded among the lens surfaces of the photographing lens of the camera 1 (step S307 in FIG. 14).
- the vehicle detection unit 41 detects another vehicle from the image area of the captured image corresponding to the detection areas A1 and A2 (step S220 in FIG. 12).
- the BSW control unit 35 determines that the sun determination unit 34 determines that the solar altitude is equal to or lower than a predetermined altitude.
- At least the first threshold value ⁇ is adjusted to the maximum level to suppress detection of other vehicles by the vehicle detection unit 41 (step S506 in FIG. 19 and No. 7 and No. 8 in FIG. 17). By doing in this way, in the vehicle-mounted vehicle recognition device 100, the accuracy of the image recognition processing does not decrease even when sunlight enters the captured image.
- FIG. 21 is a block diagram showing a configuration of an in-vehicle vehicle recognition device 200 according to the second embodiment of the present invention.
- the vehicle-mounted vehicle recognition device 200 shown in FIG. 21 is different from the vehicle-mounted vehicle recognition device 100 according to the first embodiment only in that the control unit 2 is changed to the control unit 7.
- the description of the same configuration as the vehicle-mounted vehicle recognition device 100 is omitted.
- control unit 7 executes a program stored in the storage unit 6 to perform predetermined image processing using a photographed image from the camera 1, and performs various processes according to the processing result. Take control.
- various functions called LDW, BSW, MOD, PED, RSR, and IMD are realized in the vehicle-mounted vehicle recognition device 200, for example.
- FIG. 22 is a control block diagram of the control unit 7 related to BSW. As illustrated in FIG. 22, the control unit 7 includes an image acquisition unit 31, a second BSW unit 62, a cloudiness detection unit 33, a second sun determination unit 64, and a second BSW control unit 65. The same components as those in the control block diagram shown in FIG. 4 are denoted by the same reference numerals and description thereof is omitted.
- the second BSW unit 62 includes a second vehicle detection unit 71 and a notification control unit 42.
- the second vehicle detection unit 71 includes a viewpoint conversion unit 411, a luminance difference calculation unit 712, an edge line detection unit 713, and a second three-dimensional object detection unit 714.
- FIG. 23 (a) and 23 (b) are diagrams illustrating a detection region in which the second BSW unit 62 detects a three-dimensional object.
- FIG. 23A is a plan view
- FIG. 23B is a perspective view in real space on the rear side from the host vehicle V.
- FIG. The detection areas A3 and A4 shown in FIG. 23A are trapezoidal in a plan view (when viewed from a bird's eye view), and the positions, sizes, and shapes of the detection areas A3 and A4 are at distances d1 to d4. To be determined.
- These detection areas A3 and A4 are set by the second three-dimensional object detection unit 714 instead of the detection areas A1 and A2.
- the distance d1 is a distance from the host vehicle V to the ground lines L1 and L2.
- the distance d1 is determined based on the distance d11 from the host vehicle V to the white line W and the distance d12 from the white line W to the position where the other vehicle VX is predicted to travel.
- the distance d1 is the sum of the distance d11 and the distance d12. Since the position on the road on which the other vehicle VX travels and the position on the road on which the host vehicle V travels are roughly determined, the distance d11 and the distance d12 are determined substantially fixedly, and the distance d1 is also determined approximately fixedly. Is done.
- the control unit 7 may recognize the position of the white line W with respect to the host vehicle V by a known technique such as white line recognition, and may determine the distance d11 based on the recognized position of the white line W.
- the distance d2 is a distance extending from the rear end of the host vehicle V in the direction opposite to the vehicle traveling direction.
- the distance d2 is determined so that the detection areas A3 and A4 are at least within the angle of view a of the camera 1.
- the distance d2 is set so as to be in contact with the range divided by the angle of view a.
- the distance d3 is a distance indicating the length of the detection areas A3 and A4 in the vehicle traveling direction. This distance d3 is determined based on the size of the three-dimensional object to be detected. For example, the distance d3 is set to a length including the other vehicle VX.
- the distance d4 is a distance indicating a height set so as to include a tire such as another vehicle VX in the real space.
- the distance d4 has a length as shown in FIG. 13A in the bird's-eye view image.
- the distance d4 may be a length that does not include a lane that is further adjacent to the left and right adjacent lanes in the bird's-eye view image (that is, a lane that is adjacent to two lanes from the lane in which the vehicle V travels).
- the lane adjacent to the two lanes is included from the lane of the own vehicle V, there is another vehicle VX in the adjacent lane on the left and right of the own lane that is the lane in which the own vehicle V is traveling, or the lane adjacent to the two lanes. This is because it becomes impossible to distinguish whether another vehicle VX exists.
- the distances d1 to d4 are determined, and thereby the positions, sizes, and shapes of the detection areas A3 and A4 are determined. More specifically, the position of the upper side b1 of the trapezoidal detection areas A3 and A4 is determined by the distance d1. The starting point position C1 of the upper side b1 is determined by the distance d2. The end point position C2 of the upper side b1 is determined by the distance d3. A side b2 of the detection areas A3 and A4 having a trapezoidal shape is determined by a straight line L3 extending from the camera 1 toward the start position C1.
- the side b3 of the trapezoidal detection areas A3 and A4 is determined by the straight line L4 extending from the camera 1 toward the end point position C2.
- the position of the lower side b4 of the detection areas A3 and A4 forming a trapezoid is determined by the distance d4.
- the areas surrounded by the respective sides b1 to b4 are set as the detection areas A3 and A4.
- the detection areas A3 and A4 are squares (rectangles) in the real space on the rear side from the host vehicle V.
- the luminance difference calculation unit 712 calculates a luminance difference with respect to the bird's-eye view image data subjected to viewpoint conversion by the viewpoint conversion unit 411 in order to detect the edge of the three-dimensional object included in the bird's-eye view image.
- the luminance difference calculation unit 712 calculates a luminance difference between two pixels in the vicinity of each position for each of a plurality of positions along a vertical imaginary line extending in the vertical direction in the real space.
- the luminance difference calculation unit 712 can calculate the luminance difference by either a method of setting only one vertical virtual line extending in the vertical direction in the real space or a method of setting two vertical virtual lines.
- the brightness difference calculation unit 712 performs a first vertical imaginary line corresponding to a line segment extending in the vertical direction in the real space and a vertical direction in the real space different from the first vertical imaginary line, with respect to the bird's-eye view image converted from the viewpoint.
- a second vertical imaginary line corresponding to the extending line segment is set.
- the luminance difference calculation unit 712 continuously obtains the luminance difference between the point on the first vertical imaginary line and the point on the second vertical imaginary line along the first vertical imaginary line and the second vertical imaginary line.
- the operation of the luminance difference calculation unit 712 will be described in detail.
- FIGS. 24A and 24B are diagrams showing examples of the first vertical imaginary line and the second vertical imaginary line.
- the first vertical imaginary line La (hereinafter referred to as attention line La) set by the luminance difference calculation unit 712 and the second vertical imaginary line Lr (hereinafter referred to as reference line Lr) are set. It is shown in the figure.
- the attention line La and the reference line Lr are line segments extending in the vertical direction in the real space and pass through the detection region A3.
- the reference line Lr is set at a position separated from the attention line La by a predetermined distance in the real space.
- the line corresponding to the line segment extending in the vertical direction in the real space is a line that spreads radially from the position Ps of the camera 1 in the bird's-eye view image.
- This radially extending line is a line along the direction in which the three-dimensional object falls when converted to bird's-eye view.
- the luminance difference calculation unit 712 sets the attention point Pa (point on the first vertical imaginary line) on the attention line La.
- the luminance difference calculation unit 712 sets a reference point Pr (a point on the second vertical imaginary line) on the reference line Lr.
- the attention line La, the attention point Pa, the reference line Lr, and the reference point Pr have the relationship shown in FIG.
- the attention line La and the reference line Lr are lines extending in the vertical direction in the real space, and the attention point Pa and the reference point Pr are substantially the same height in the real space. This is the point that is set. Note that the attention point Pa and the reference point Pr do not necessarily have the same height, and an error that allows the attention point Pa and the reference point Pr to be regarded as the same height is allowed.
- the luminance difference calculation unit 712 calculates a luminance difference between the attention point Pa and the reference point Pr. If the luminance difference between the attention point Pa and the reference point Pr is large, it is considered that an edge exists between the attention point Pa and the reference point Pr. Therefore, the edge line detection unit 713 illustrated in FIG. 22 detects the edge line based on the luminance difference between the attention point Pa and the reference point Pr.
- FIG. 25 is a diagram illustrating a detailed operation of the luminance difference calculation unit 712.
- FIG. 25 (a) shows a bird's-eye view image in a bird's-eye view state
- FIG. 25 (b) is shown in FIG. 25 (a). It is the figure which expanded a part B1 of the bird's-eye view image.
- FIGS. 25A and 25B only the detection area A3 is illustrated and described, but the luminance difference is calculated in the same procedure for the detection area A4.
- the luminance difference calculation unit 712 first sets a reference line Lr.
- the reference line Lr is set along the vertical direction at a position away from the attention line La by a predetermined distance in the real space. Specifically, in the camera 1 according to the present embodiment, the reference line Lr is set at a position 10 cm away from the attention line La in real space. Thereby, the reference line Lr is set on the wheel of the tire of the other vehicle VX that is separated from the rubber of the tire of the other vehicle VX by, for example, 10 cm on the bird's-eye view image.
- the luminance difference calculation unit 712 sets a plurality of attention points Pa1 to PaN on the attention line La.
- attention point Pai when an arbitrary point is indicated
- the number of attention points Pa set on the attention line La may be arbitrary.
- the luminance difference calculation unit 712 sets the reference points Pr1 to PrN so as to be the same height as the attention points Pa1 to PaN in the real space. Then, the luminance difference calculation unit 712 calculates the luminance difference between the attention point Pa and the reference point Pr having the same height. Thus, the luminance difference calculation unit 712 calculates the luminance difference between the two pixels for each of a plurality of positions (1 to N) along the vertical imaginary line extending in the vertical direction in the real space. For example, the luminance difference calculation unit 712 calculates a luminance difference between the first point of interest Pa1 and the first reference point Pr1, and the luminance difference between the second point of interest Pa2 and the second reference point Pr2. Will be calculated.
- the luminance difference calculation unit 712 continuously calculates the luminance difference along the attention line La and the reference line Lr. That is, the luminance difference calculation unit 712 sequentially obtains the luminance difference between the third to Nth attention points Pa3 to PaN and the third to Nth reference points Pr3 to PrN.
- the luminance difference calculation unit 712 repeatedly executes the processing such as setting the reference line Lr, setting the attention point Pa and the reference point Pr, and calculating the luminance difference while shifting the attention line La in the detection area A3. That is, the luminance difference calculation unit 712 repeatedly executes the above processing while changing the position of the attention line La and the reference line Lr by the same distance in the extending direction of the ground line L1 in the real space. For example, the luminance difference calculation unit 712 sets the reference line Lr as the reference line Lr in the previous processing, sets the reference line Lr for the attention line La, and sequentially obtains the luminance difference. It will be.
- the edge line detection unit 713 in FIG. 22 detects an edge line from the continuous luminance difference calculated by the luminance difference calculation unit 712. For example, in the case shown in FIG. 25 (b), the first attention point Pa1 and the first reference point Pr1 are located in the same tire portion, so that the luminance difference is small. On the other hand, the second to sixth attention points Pa2 to Pa6 are located in the rubber part of the tire, and the second to sixth reference points Pr2 to Pr6 are located in the wheel part of the tire. Therefore, the luminance difference between the second to sixth attention points Pa2 to Pa6 and the second to sixth reference points Pr2 to Pr6 increases. Therefore, the edge line detection unit 713 may detect that an edge line exists between the second to sixth attention points Pa2 to Pa6 and the second to sixth reference points Pr2 to Pr6 having a large luminance difference. it can.
- the edge line detection unit 713 firstly follows the following equation 1 to determine the i-th attention point Pai (coordinates (xi, yi)) and the i-th reference point Pri (coordinates ( The i-th attention point Pai is attributed based on the luminance difference from xi ′, yi ′)).
- Equation 1 t represents a threshold value
- I (xi, yi) represents the luminance value of the i-th attention point Pai
- I (xi ′, yi ′) represents the luminance value of the i-th reference point Pri.
- the attribute s (xi, yi) of the attention point Pai is “1”.
- the attribute s (xi, yi) of the attention point Pai is “ ⁇ 1”.
- This threshold value t may be a predetermined value set in advance, or may be set by the second BSW control unit 65.
- the edge line detection unit 713 determines whether or not the attention line La is an edge line from the continuity c (xi, yi) of the attribute s along the attention line La based on Equation 2 below.
- the edge line detection unit 713 obtains a sum for the continuity c of all attention points Pa on the attention line La.
- the edge line detection unit 713 normalizes the continuity c by dividing the obtained sum of continuity c by the number N of points of interest Pa.
- the edge line detection unit 713 determines that the attention line La is an edge line when the normalized value exceeds the threshold ⁇ .
- the threshold value ⁇ is a value set in advance by experiments or the like.
- the threshold value ⁇ is set by the second BSW control unit 65.
- the edge line detection unit 713 determines whether or not the attention line La is an edge line based on Equation 3 below. Then, the edge line detection unit 713 determines whether or not all of the attention lines La drawn on the detection area A3 are edge lines. [Equation 3] ⁇ c (xi, yi) / N> ⁇
- the second three-dimensional object detection unit 714 in FIG. 22 detects a three-dimensional object based on the amount of edge lines detected by the edge line detection unit 713.
- the control unit 7 detects an edge line extending in the vertical direction in the real space. The fact that many edge lines extending in the vertical direction are detected means that there is a high possibility that a three-dimensional object exists in the detection areas A3 and A4. For this reason, the second three-dimensional object detection unit 714 detects a three-dimensional object based on the amount of edge lines detected by the edge line detection unit 713.
- the second three-dimensional object detection unit 714 determines whether the edge line detected by the edge line detection unit 713 is correct.
- the second three-dimensional object detection unit 714 determines whether the luminance change along the edge line of the bird's-eye view image on the edge line is larger than a predetermined threshold value. If the brightness change of the bird's-eye view image on the edge line is larger than the threshold value, it is determined that the edge line is detected by erroneous determination. On the other hand, if the luminance change of the bird's-eye view image on the edge line is not larger than the threshold value, it is determined that the edge line is correct.
- This threshold value is a value set in advance by experiments or the like.
- FIG. 26 is a diagram showing the luminance distribution of the edge line
- FIG. 26A shows the edge line and luminance distribution when another vehicle VX as a three-dimensional object is present in the detection area A3, and
- FIG. Indicates an edge line and a luminance distribution when there is no solid object in the detection area A3.
- the attention line La set in the tire rubber part of the other vehicle VX is determined to be an edge line in the bird's-eye view image.
- the luminance change of the bird's-eye view image on the attention line La is gentle. This is because the tire of the other vehicle VX is extended in the bird's-eye view image by converting the image captured by the camera 1 into a bird's-eye view image.
- FIG. 26B it is assumed that the attention line La set in the white character portion “50” drawn on the road surface in the bird's-eye view image is erroneously determined as an edge line.
- the brightness change of the bird's-eye view image on the attention line La has a large undulation. This is because, on the edge line, a portion with high luminance in white characters and a portion with low luminance such as a road surface are mixed.
- the second three-dimensional object detection unit 714 determines whether or not the edge line is detected by erroneous determination. When the luminance change along the edge line is larger than a predetermined threshold, the second three-dimensional object detection unit 714 determines that the edge line has been detected by erroneous determination. The edge line is not used for detecting a three-dimensional object. As a result, white characters such as “50” on the road surface, weeds on the road shoulder, and the like are determined as edge lines, and the detection accuracy of the three-dimensional object is prevented from being lowered.
- the second three-dimensional object detection unit 714 calculates the luminance change of the edge line according to any of the following formulas 4 and 5.
- This luminance change of the edge line corresponds to the evaluation value in the vertical direction in the real space.
- Equation 4 evaluates the luminance distribution by the sum of the squares of the differences between the i-th luminance value I (xi, yi) on the attention line La and the adjacent i + 1-th luminance value I (xi + 1, yi + 1).
- Equation 5 evaluates the luminance distribution by the sum of the absolute values of the differences between the i-th luminance value I (xi, yi) on the attention line La and the adjacent i + 1-th luminance value I (xi + 1, yi + 1).
- the threshold value t2 is used to binarize the attribute b of the adjacent luminance value, and the binarized attribute b is summed for all the attention points Pa. Also good.
- Evaluation value in the vertical equivalent direction ⁇ b (xi, yi)
- b (xi, yi) 0
- the attribute b (xi, yi) of the attention point Pa (xi, yi) is “1”. Become. If the relationship is other than that, the attribute b (xi, yi) of the attention point Pai is '0'.
- This threshold value t2 is set in advance by an experiment or the like in order to determine that the attention line La is not on the same three-dimensional object. Then, the second three-dimensional object detection unit 714 sums up the attributes b for all the attention points Pa on the attention line La, obtains an evaluation value in the vertical equivalent direction, and determines whether the edge line is correct.
- (Second vehicle detection unit 71) 27 and 28 are flowcharts related to the second vehicle detection unit 71 executed by the control unit 7. In FIG. 27 and FIG. 28, for convenience, processing for the detection area A3 will be described, but the same processing is executed for the detection area A4.
- Step S600 the viewpoint conversion unit 411 generates bird's-eye image data based on the image information of the captured image acquired by the image acquisition unit 31.
- step S601 the luminance difference calculation unit 712 sets the attention line La on the detection area A3. At this time, the luminance difference calculation unit 712 sets a line corresponding to a line extending in the vertical direction in the real space as the attention line La.
- step S602 the luminance difference calculation unit 712 sets a reference line Lr on the detection area A3. At this time, the luminance difference calculation unit 712 sets a reference line Lr that corresponds to a line segment extending in the vertical direction in the real space and is separated from the attention line La by a predetermined distance in the real space.
- step S603 the luminance difference calculation unit 712 sets a plurality of attention points Pa on the attention line La. At this time, the luminance difference calculation unit 712 sets a number of attention points Pa that are not problematic when the edge line detection unit 713 detects an edge.
- step S604 the luminance difference calculation unit 712 sets the reference point Pr so that the attention point Pa and the reference point Pr are substantially the same height in the real space. Thereby, the attention point Pa and the reference point Pr are arranged in a substantially horizontal direction, and it becomes easy to detect an edge line extending in the vertical direction in the real space.
- step S605 the luminance difference calculation unit 712 calculates the luminance difference between the attention point Pa and the reference point Pr that have the same height in the real space.
- step S606 the edge line detection unit 713 calculates the attribute s of each attention point Pa according to the above mathematical formula 1.
- step S607 the edge line detection unit 713 calculates the continuity c of the attribute s of each point of interest Pa in accordance with Equation 2 above.
- step S608 the edge line detection unit 713 determines whether or not the value obtained by normalizing the total sum of continuity c is greater than the threshold value ⁇ according to the above formula 3.
- the process proceeds to step S609.
- step S609 the edge line detection unit 713 detects the attention line La as an edge line, and the process proceeds to step S610. If the edge line detection unit 713 determines that the normalized value is not greater than the threshold ⁇ (S608: NO), the edge line detection unit 713 advances the process to step S610 without detecting the attention line La as an edge line.
- This threshold value ⁇ can be set by the second BSW control unit 65.
- step S610 the second vehicle detection unit 71 determines whether or not the processing in steps S601 to S609 has been executed for all the attention lines La that can be set on the detection area A3. If the second vehicle detection unit 71 determines that the above process has not been performed for all the attention lines La (S610: NO), the second vehicle detection unit 71 proceeds to the process in step S601, sets a new attention line La, and performs step S610. Repeat the process up to. On the other hand, if the second vehicle detection unit 71 determines that the above process has been performed for all the attention lines La (S610: YES), the process proceeds to step S611 in FIG.
- step S611 in FIG. 28 the brightness along the edge line is detected by the second three-dimensional object detection unit 714 for each edge line detected in step S609 in FIG. Calculate the change.
- the second three-dimensional object detection unit 714 excludes edge lines whose luminance change is larger than a predetermined threshold from the edge lines calculated in step S611. That is, it is determined that an edge line having a large luminance change is not a correct edge line, and the edge line is not used for detecting a three-dimensional object. As described above, this is to prevent characters on the road surface, weeds on the road shoulder, and the like included in the detection area A3 from being detected as edge lines. Therefore, the predetermined threshold value is a value set based on a change in luminance generated by characters on the road surface, weeds on the road shoulder, or the like, which is obtained in advance through experiments or the like.
- the second three-dimensional object detection unit 714 determines whether the amount of the edge line is equal to or greater than the second threshold value ⁇ .
- the second threshold value ⁇ may be determined and set in advance by experiments or the like, or may be set by the second BSW control unit 65. For example, when a four-wheeled vehicle is set as a three-dimensional object to be detected, the second BSW control unit 65 sets the second threshold value based on the number of edge lines of the four-wheeled vehicle that appeared in the detection area A3 in advance through experiments or the like. Set ⁇ . If the second three-dimensional object detection unit 714 determines that the amount of the edge line is greater than or equal to the second threshold value ⁇ (S613: YES), the process proceeds to step S614.
- the second three-dimensional object detection unit 714 determines that the amount of the edge line is not equal to or larger than the second threshold value ⁇ (S613: NO), the second three-dimensional object detection unit 714 determines that there is no three-dimensional object in the detection area A3, and FIG. Terminate the process.
- the second three-dimensional object detection unit 714 detects that a three-dimensional object exists in the detection area A3, and ends the process of FIG.
- the detected three-dimensional object may be determined to be another vehicle VX that travels in the adjacent lane adjacent to the lane in which the host vehicle V travels, or the relative speed of the detected three-dimensional object with respect to the host vehicle V is considered. It may be determined whether the vehicle is another vehicle VX traveling in the adjacent lane.
- (Second sun determination unit 64) Image information of the captured image acquired by the image acquisition unit 31 is input to the second sun determination unit 64 in FIG.
- the second sun determination unit 64 detects a high brightness area by sunlight reflected from the road surface from the photographed image, estimates the position of the sun based on the detection range, and whether the sunlight enters the photograph area. Determine whether or not.
- FIG. 29 is a flowchart regarding the second sun determination unit 64.
- the control unit 7 extracts pixels with high luminance (for example, luminance is 190 or more in 256 gradations) from the captured image input from the image acquisition unit 31.
- the control unit 7 extracts an image region having a predetermined number of pixels or more from the pixel block (image region) in which the pixels extracted in step S700 are connected.
- step S702 the control unit 7 calculates the center of gravity of the image area extracted in step S701.
- step S703 the control unit 7 determines whether at least one of the centroids calculated in step S702 is within the range of the reflected sunlight region. When the determination at step S703 is affirmative, the control unit 7 advances the process to step S704, and when the determination at step S703 is negative, the control unit 7 advances the process to step S705.
- step S704 the control unit 7 calculates the position of the sun based on the position of the center of gravity of the high brightness area where the center of gravity calculated in step S702 was within the range of the reflected sunlight area.
- FIG. 30 shows a captured image 80 including a high luminance area 81.
- an upper limit line 82 and a lower limit line 83 that define the reflected sunlight region are indicated by broken lines.
- the high brightness area 81 in FIG. 30 has its center of gravity 84 inside the reflected sunlight area.
- the control unit 7 calculates the azimuth of the sun based on the direction of the line segment 86 connecting the center of gravity 84 and the lower center 85 of the captured image 80. Further, the altitude of the sun is calculated based on the position of the center of gravity 84 in the vertical direction of the captured image 80.
- step S705 the control unit 7 determines that sunlight is incident on the imaging region of the camera 1. In step S ⁇ b> 706, the control unit 7 determines that sunlight does not enter the imaging region of the camera 1. That is, it is determined that the sun range does not overlap the captured image.
- the second BSW control unit 65 in FIG. 22 sets the threshold ⁇ based on the captured image input from the image acquisition unit 31, the detection result of the cloudiness detection unit 33, and the determination result of the second sun determination unit 64.
- the second BSW unit 62 is controlled by the above.
- FIG. 31 is a flowchart of the second BSW control unit 65.
- the control unit 7 acquires the determination result by the second sun determination unit 64. That is, information regarding the determination in step S705 or step S706 in FIG. 29 is acquired.
- the control unit 7 acquires a detection result by the white turbidity detection unit 33. That is, information related to the determination in step S306 or step S307 in FIG.
- step S802 the control unit 7 determines whether or not the information acquired in step S800 and step S801 is the same for a predetermined time or more. If the determination in step S802 is affirmative, the control unit 7 advances the process in FIG. 31 to step S803. If the determination in step S802 is negative, the control unit 7 advances the process in FIG. 31 to step S800.
- step S803 the control unit 7 sets the threshold value ⁇ of the second BSW unit 62 based on the table of FIG. 32, and then advances the processing of FIG. 31 to step S800.
- FIG. 32 is an example of a setting value table related to the threshold value ⁇ set by the second BSW control unit 65.
- the setting value table of FIG. 32 may be stored in the storage unit 6 as a lookup table.
- the BSW control unit 35 refers to the lookup table stored in the storage unit 6 based on the detection result of the white turbidity detection unit 33 and the determination result of the second sun determination unit 64, and sets the threshold ⁇ . Set.
- the threshold value ⁇ is expressed as a level.
- the actual threshold value ⁇ not represented by the level notation is set to a larger value as the level becomes larger, and becomes maximum at level 10.
- the set value of the threshold value ⁇ corresponding to each level is determined in advance at the design stage of the in-vehicle vehicle recognition device 200.
- FIG. 32 is merely an example, and the maximum level may not be level 10.
- the second BSW control unit 65 is No. in FIG. In the situation of 12, the threshold ⁇ is set to level 10 (maximum level).
- level 10 maximum level
- the second BSW control unit 65 suppresses notification by the second BSW unit 62 in such a situation, thereby suppressing erroneous detection of other vehicles and not reducing the accuracy of the image recognition process.
- the second BSW control unit 65 is No. In the situation of No. 10, no.
- the threshold value ⁇ is set lower than the situation of 9.
- no. No. 11 also.
- the threshold value ⁇ is set lower than the situation of 9.
- the second BSW control unit 65 sets the threshold ⁇ to be low, thereby The detection sensitivity is increased to cope with the decrease in the peak of the differential waveform due to the decrease in contrast, so that other vehicles can be detected with high accuracy.
- the detection areas A3 and A4 set by the second three-dimensional object detection unit 714 are set at substantially the same positions as the detection areas A1 and A2 set by the three-dimensional object detection unit 413 in the first embodiment. Therefore, the white turbidity detection unit 33 detects that the lens surface corresponding to at least the detection region A1 or A2 is clouded and detects that the lens surface corresponding to at least the detection region A3 or A4 is cloudy. Is substantially the same. That is, the white turbidity detection unit 33 can detect that the lens surface corresponding to at least the detection region A3 or A4 is white turbid.
- the notification control unit 42 performs the process shown in the flowchart of FIG. 20 also in the second embodiment.
- the notification control unit 42 in the second embodiment determines whether or not the threshold ⁇ is set to level 10 (maximum value), thereby determining the second BSW control unit. 65 determines whether BSW is suppressed.
- the control unit 7 of the in-vehicle vehicle recognition device 200 includes an image acquisition unit 31, a second sun determination unit 64, a cloudiness detection unit 33, a second vehicle detection unit 71, and a second BSW control unit 65.
- the image acquisition unit 31 acquires a captured image output by the camera 1 shooting outside the vehicle.
- the second sun determination unit 64 calculates at least the altitude of the sun based on the position of the center of gravity of the high brightness area 81 (step S704 in FIG. 29), and the position of the center of gravity 84 of the high brightness area 81 becomes the reflected sunlight area. Determine if it exists.
- the reflected sunlight region is defined by an upper limit line 82 and a lower limit line 83, and when the center of gravity 84 is above the lower limit line 83, the sun altitude is below a predetermined altitude.
- the cloudiness detection unit 33 detects that at least the lens surface corresponding to the detection areas A3 and A4 is clouded among the lens surfaces of the photographing lens of the camera 1 (supplement of the cloudiness detection unit 33).
- the second vehicle detection unit 71 detects another vehicle from the image area of the captured image corresponding to the detection areas A3 and A4 (step S614 in FIG. 28).
- the second BSW control unit 65 determines that the solar altitude is equal to or lower than a predetermined altitude when the white turbidity detection unit 33 detects that the lens surface corresponding to at least the detection areas A3 and A4 is cloudy.
- the determination is made by the unit 64, at least the threshold ⁇ is adjusted to the maximum level to suppress detection of other vehicles by the second vehicle detection unit 71 (step S803 in FIG. 31 and No. 12 in FIG. 32).
- the embodiment described above can be modified and executed as follows.
- (Modification 1) Combination of Embodiments
- the control units 2 and 7 may include both the BSW unit 32 and the second BSW unit 62. In this case, for example, when both the three-dimensional object detection unit 413 and the second three-dimensional object detection unit 714 detect the other vehicle VX, the other vehicle VX may be detected.
- the control unit may include both the BSW control unit 35 and the second BSW control unit 65, or the first BSW control unit 35 and the second BSW control unit 65 may be used to Both the threshold value ⁇ and the threshold value ⁇ may be set.
- the BSW control unit 35 sets the threshold value ⁇
- the setting level of the first threshold value ⁇ in FIG. 17 may be read as the setting level of the threshold value ⁇ .
- the second BSW control unit 65 sets the first threshold value ⁇
- the setting level of the threshold value ⁇ in FIG. 32 may be read as the setting level of the first threshold value ⁇ .
- the control unit 2 may include a second BSW unit 62 instead of the BSW unit 32.
- the control unit 2 includes a second sun determination unit 64 instead of the sun determination unit 34, and the BSW control unit 35 sets a threshold value ⁇ instead of the first threshold value ⁇ .
- the BSW control unit 35 sets the threshold value ⁇
- the setting level of the first threshold value ⁇ in FIG. 17 may be read as the setting level of the threshold value ⁇ .
- the control unit 7 may include a BSW unit 32 instead of the second BSW unit 62.
- the control unit 7 includes the sun determination unit 34 instead of the second sun determination unit 64, and the second BSW control unit 65 sets the first threshold value ⁇ instead of the threshold value ⁇ .
- the second BSW control unit 65 sets the first threshold value ⁇
- the setting level of the threshold value ⁇ in FIG. 32 may be read as the setting level of the first threshold value ⁇ .
- the BSW control unit 35 and the second BSW control unit 65 may set a threshold other than the first threshold ⁇ and the threshold ⁇ .
- the second threshold value ⁇ in step S613 in FIG. 28 may be set.
- the threshold values ⁇ 1, ⁇ 2, and ⁇ 3 of the white turbidity detection unit 33 may be set.
- the BSW control unit 35 sets a threshold other than the first threshold ⁇
- the setting level of the first threshold ⁇ in FIG. 17 may be read as the setting level of the threshold.
- the second BSW control unit 65 sets a threshold other than the threshold ⁇
- the setting level of the threshold ⁇ in FIG. 32 may be read as the setting level of the threshold.
- the control units 2 and 7 may include both the sun determination unit 34 and the second sun determination unit 64.
- the configuration of the first embodiment and the configuration of the second embodiment may be executed in any combination as long as the features of the invention are not impaired.
- the threshold value was changed based on whether the white turbidity detection unit 33 detected white turbidity.
- the threshold value may be changed based on a numerical value representing the degree of cloudiness.
- the cloudiness degree may be calculated based on the average value E1 of the histogram H1, the average value E2 of the histogram H2, and the average value E3 of the histogram H3.
- FIG. 33 is a schematic diagram showing the relationship between the degree of white turbidity and the threshold when the sun determination unit 34 determines that sunlight is incident on the imaging region of the camera 1.
- the vertical axis in FIG. 33 indicates the level of a threshold such as the first threshold ⁇ , and the horizontal axis indicates the degree of cloudiness.
- the degree of cloudiness is C2
- the taking lens of the camera 1 is not clouded.
- the degree of cloudiness is C1 or higher, No.
- the threshold value is set to the maximum level by the BSW control unit 35 or the like.
- the threshold is set lower than when the cloudiness degree is C1 than when the cloudiness degree is C2. Accordingly, it is possible to try to maintain the detection accuracy of the other vehicle VX until the white turbidity detection unit 33 determines that the lens surface corresponding to at least the detection region A1 or A2 is white turbid.
- the BSW control unit 35 may set the threshold to a higher level when the sun range is clouded.
- the second BSW control unit 65 may set the threshold value to a higher level when the sun range is clouded. Whether or not the sun range is clouded may be determined based on the brightness gradient in the sun range. The light passing through the cloudy part of the lens surface of the photographic lens of the camera 1 is diffused by the adhering matter causing the cloudiness, so that the difference in brightness for each pixel corresponding to the cloudy spot is reduced and the brightness gradient is reduced. Get smaller.
- the BSW control unit 35 and the second BSW control unit 65 may determine that the sun range is clouded when the brightness gradient becomes a predetermined value or less.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
Description
本発明の第2の態様によると,第1の態様の 画像処理装置において,車両検出部は,他車両の検出感度に関わる所定の閾値を有し,制御部は,レンズ表面のうち太陽の位置を中心とした画像範囲に対応する範囲が白濁しているとき,レンズ表面の当該範囲が白濁していないときよりも他車両の検出感度を閾値の変更により抑制することが好ましい。
本発明の第3の態様によると,第1の態様の画像処理装置において,太陽判定部は,日時と,車両が位置する緯度および経度と,車両の方向とに基づいて,太陽の位置を演算することが好ましい。
本発明の第4の態様によると,第1の態様の画像処理装置において,太陽判定部は,撮影画像に対して画像処理を行うことにより太陽の位置を演算することが好ましい。
本発明の第5の態様によると,第4の態様の画像処理装置において,カメラは,少なくとも車両外の路面を撮影し,太陽判定部は,路面反射による高輝度領域を撮影画像から抽出して,高輝度領域の重心の位置に基づいて太陽の位置を演算することが好ましい。
本発明の第6の態様によると,制御部は,第2の態様の画像処理装置において,太陽の位置を中心とした画像範囲の輝度勾配に基づいて,レンズ表面のうち当該画像範囲に対応する範囲が白濁していることを検出することが好ましい。
本発明の第7の態様によると,第1の態様の画像処理装置において,撮影画像には白濁検出領域が設定され,白濁検出部は,白濁検出領域に対してエッジ強度のヒストグラムを演算して,ヒストグラムを用いて演算されるエッジ強度の平均値に基づいて,カメラレンズが白濁している領域を検出する。
本発明の第8の態様によると,第7の態様の画像処理装置において,カメラは,少なくとも車両外の路面を撮影し,白濁検出領域は,路面に設けられた白線の消失点の近傍に複数設定され、白濁検出部は,白濁検出領域の各々に対してエッジ強度のヒストグラムを演算して,ヒストグラムの各々を用いて演算されるエッジ強度の平均値に基づいて,カメラレンズが白濁している領域を検出する。
本発明の第9の態様によると,第7の態様の画像処理装置において,カメラは,少なくとも車両外の路面を撮影し,白濁検出領域には,路面に設けられた白線の消失点の近傍であって撮影画像の中央よりも上側の位置に設定される第1の白濁検出領域と,第1の白濁検出領域よりも下方に広がるように消失点の近傍に設定される第2の白濁検出領域とが含まれ,白濁検出部は,昼間は第1の白濁検出領域を用いてカメラレンズが白濁している領域を検出し,夜間は第2の白濁検出領域を用いてカメラレンズが白濁している領域を検出する。
本発明の第10の態様によると,第1から第9のいずれか一態様の画像処理装置において,車両検出部による他車両の検出を制御部が抑制したことを,所定の報知部に報知させる報知制御部をさらに備えることが好ましい。
本発明の第11の態様によると,第2の態様の画像処理装置において,白濁検出部は,カメラのレンズ表面の白濁度合いが第1の白濁度合いを超えたとき,カメラのレンズ表面が白濁していることを検出し,車両検出部は,カメラのレンズ表面が白濁していない第2の白濁度合いのときに閾値を第1の閾値に設定し,カメラのレンズ表面の白濁度合いが第1の白濁度合いを超えたときに閾値を第1の閾値よりも大きい第2の閾値に設定し,閾値を第1の閾値と第2の閾値とのいずれよりも小さい第3の閾値に設定する第3の白濁度合いを第2の白濁度合いと第1の白濁度合いとの間に設けることが好ましい。
図1は,本発明の第1の実施形態による車載用車両認識装置100の構成を示すブロック図である。図1に示す車載用車両認識装置100は,車両に搭載されて使用されるものであり,遮光板1aが取り付けられたカメラ1と,制御部2と,警報出力部3と,動作状態報知部4と,外部装置制御部5と,記憶部6とを備える。
外部装置制御部5は,制御部2からの制御に応じて,外部装置を制御する。
画像取得部31は,所定時間ごとにカメラ1から撮影画像の画像情報を取得する。画像取得部31が取得した撮影画像の画像情報は,少なくともBSW部32と白濁検出部33とに出力される。図4では,画像取得部31は,BSW制御部35にも撮影画像の画像情報を出力している。
BSW部32は,車両検出部41と報知制御部42とを有する。車両検出部41は,視点変換部411と位置合わせ部412と立体物検出部413とを有する。
視点変換部411は,画像取得部31が取得した撮影画像の画像情報を鳥瞰視される状態の鳥瞰画像データに視点変換する。鳥瞰視される状態とは,上空から例えば鉛直下向きに見下ろす仮想カメラの視点から見た状態である。この視点変換は,例えば特開2008-219063号公報に記載されるようにして実行することができる。撮像画像データを鳥瞰視画像データに視点変換するのは,立体物に特有の鉛直エッジは鳥瞰視画像データへの視点変換により特定の定点を通る直線群に変換されるという原理に基づき,これを利用すれば平面物と立体物とを識別できるからである。
位置合わせ部412は,視点変換部411の視点変換により得られた鳥瞰画像データが順次入力され,入力された異なる時刻の鳥瞰画像データの位置を合わせる。図5は,位置合わせ部412の処理の概要を説明するための図であり,図5(a)は自車両Vの移動状態を示す平面図,図5(b)は位置合わせの概要を示す画像である。
図4の立体物検出部413は,図5(b)に示す差分画像PDtのデータに基づいて立体物を検出する。立体物検出部413が検出する立体物の中には,自車両Vが車線変更する際に接触の可能性がある他車両が含まれる。立体物検出部413は,実空間上における立体物の移動距離についても算出する。立体物検出部413は,立体物の時間あたりの移動距離を,立体物の移動速度の算出に用いる。そして,立体物検出部413は,その立体物の移動速度を立体物が車両であるか否かの判断に用いる。
図11および図12は,制御部2が実行する車両検出部41の処理に関するフローチャートである。図11のステップS100では,画像取得部31が取得した撮影画像の画像情報に基づいて,視点変換部411が鳥瞰画像データを生成する。ステップS110では,鳥瞰画像PBtと,一時刻前の鳥瞰画像PBt-1とを,位置合わせ部412が位置合わせする。ステップS120では,立体物検出部413が差分画像PDtを生成する。ステップS130では,立体物検出部413が差分画像PDtのデータと,一時刻前の差分画像PDt-1のデータとから,差分波形DWtを生成する。
図4の白濁検出部33は,カメラ1の撮影レンズの白濁を検出する。白濁検出部33は,カメラ1の撮影画像に対して白濁検出領域を設定して,その白濁検出領域ごとにエッジ強度のヒストグラムを生成する。そして,白濁検出部33は,そのヒストグラムの平均値が所定値以下のとき,カメラ1の撮影レンズが白濁しているものとして判定する。
図4の太陽判定部34は,太陽の位置を演算して,カメラ1の撮影領域に太陽光が入射するか否かを判定する。太陽判定部34が演算する太陽の位置は,少なくとも太陽の高度を含む。太陽判定部34は,太陽の高度を,例えば日時情報と,自車両Vが存在する自車位置の緯度とに基づいて算出する。また,太陽判定部34は,太陽の位置に関する情報として,さらに太陽の方位を算出する。太陽の方位は,例えば日時情報と,自車位置の緯度および経度と、自車両Vの方向とに基づいて算出することができる。
図4のBSW制御部35は,白濁検出部33の検出結果と,太陽判定部34の判定結果と,画像取得部31から入力された撮影画像とに基づいて,第1閾値αを設定することによりBSW部32を制御する。図17は,BSW制御部35が設定する第1閾値αに関する設定値テーブルの一例である。図17の設定値テーブルは,ルックアップテーブルとして記憶部6に記憶しておいてもよい。その場合,BSW制御部35は,白濁検出部33の検出結果と,太陽判定部34の判定結果とに基づいて,記憶部6に記憶されたルックアップテーブルを参照して,第1閾値αを設定する。
報知制御部42は,車線変更時等に,図12のステップS220において立体物が他車両VXであると立体物検出部413が判断したとき,警報出力部3を制御して,自車両と衝突する可能性がある車両の存在を運転者に報知する。一方,報知制御部42は,図12のステップS230において他車両が存在しないと立体物検出部413が判断したとき,運転者に対してそのような報知を行わない。
警報音の出力が抑制された状態であることを動作状態報知部4(例えば,自車両Vのメータ)を介して報知する。
車載用車両認識装置100の制御部2は,画像取得部31と,太陽判定部34と,白濁検出部33と,車両検出部41と,BSW制御部35とを備える。
画像取得部31は,カメラ1が車両外を撮影して出力した撮影画像を取得する。
太陽判定部34は,少なくとも太陽の高度を含む太陽の位置を演算して(図16のステップS400),その太陽の高度が所定高度以下であるか否かを少なくとも判定する(図16のステップS402)。
白濁検出部33は,カメラ1の撮影レンズのレンズ表面のうち,少なくとも出領域A1およびA2に対応するレンズ表面が白濁していることを検出する(図14のステップS307)。
車両検出部41は,検出領域A1およびA2に対応する撮影画像の画像領域から,他車両を検出する(図12のステップS220)。
BSW制御部35は,白濁検出部33により少なくとも検出領域A1およびA2に対応するレンズ表面が白濁していることが検出された場合に,太陽の高度が所定高度以下であると太陽判定部34が判定した場合には少なくとも,第1閾値αを最大レベルに調整することで車両検出部41による他車両の検出を抑制する(図19のステップS506,図17のNo.7およびNo.8)。
このようにすることで,車載用車両認識装置100では,撮影画像に太陽光が入射した場合にも,画像認識処理の精度が低下しない。
本発明の第2の実施の形態について説明する。図21は,本発明の第2の実施形態による車載用車両認識装置200の構成を示すブロック図である。図21に示す車載用車両認識装置200は,第1の実施の形態による車載用車両認識装置100と,制御部2が制御部7に変わっている点のみが異なる。図21に示す車載用車両認識装置200の構成において,車載用車両認識装置100と同一の構成については,その説明を省略する。
輝度差算出部712は,鳥瞰視画像に含まれる立体物のエッジを検出するために,視点変換部411により視点変換された鳥瞰視画像データに対して,輝度差の算出を行う。輝度差算出部712は,実空間における鉛直方向に伸びる鉛直仮想線に沿った複数の位置ごとに,当該各位置の近傍の2つの画素間の輝度差を算出する。輝度差算出部712は,実空間における鉛直方向に伸びる鉛直仮想線を1本だけ設定する手法と,鉛直仮想線を2本設定する手法との何れかによって輝度差を算出することができる。
図22のエッジ線検出部713は,輝度差算出部712により算出された連続的な輝度差から,エッジ線を検出する。例えば,図25(b)に示す場合,第1注目点Pa1と第1参照点Pr1とは,同じタイヤ部分に位置するために,輝度差は,小さい。一方,第2~第6注目点Pa2~Pa6はタイヤのゴム部分に位置し,第2~第6参照点Pr2~Pr6はタイヤのホイール部分に位置する。したがって,第2~第6注目点Pa2~Pa6と第2~第6参照点Pr2~Pr6との輝度差は大きくなる。このため,エッジ線検出部713は,輝度差が大きい第2~第6注目点Pa2~Pa6と第2~第6参照点Pr2~Pr6との間にエッジ線が存在することを検出することができる。
[数1]
I(xi,yi)>I(xi’,yi’)+tのとき
s(xi,yi)=1
I(xi,yi)<I(xi’,yi’)-tのとき
s(xi,yi)=-1
上記以外のとき
s(xi,yi)=0
[数2]
s(xi,yi)=s(xi+1,yi+1)のとき(且つ0=0を除く),
c(xi,yi)=1
上記以外のとき,
c(xi,yi)=0
[数3]
Σc(xi,yi)/N>θ
図22の第2立体物検出部714は,エッジ線検出部713により検出されたエッジ線の量に基づいて立体物を検出する。上述したように,制御部7は,実空間上において鉛直方向に伸びるエッジ線を検出する。鉛直方向に伸びるエッジ線が多く検出されるということは,検出領域A3,A4に立体物が存在する可能性が高いということである。このため,第2立体物検出部714は,エッジ線検出部713により検出されたエッジ線の量に基づいて立体物を検出する。さらに,第2立体物検出部714は,立体物を検出するに先立って,エッジ線検出部713により検出されたエッジ線が正しいものであるか否かを判定する。第2立体物検出部714は,エッジ線上の鳥瞰視画像のエッジ線に沿った輝度変化が所定の閾値よりも大きいか否かを判定する。エッジ線上の鳥瞰視画像の輝度変化が閾値よりも大きい場合には,当該エッジ線が誤判定により検出されたものと判断する。一方,エッジ線上の鳥瞰視画像の輝度変化が閾値よりも大きくない場合には,当該エッジ線が正しいものと判定する。なお,この閾値は,実験等により予め設定された値である。
[数4]
鉛直相当方向の評価値=Σ[{I(xi,yi)-I(xi+1,yi+1)}2]
[数5]
鉛直相当方向の評価値=Σ|I(xi,yi)-I(xi+1,yi+1)|
[数6]
鉛直相当方向の評価値=Σb(xi,yi)
但し,|I(xi,yi)-I(xi+1,yi+1)|>t2のとき,
b(xi,yi)=1
上記以外のとき,
b(xi,yi)=0
図27および図28は,制御部7が実行する第2車両検出部71に関するフローチャートである。なお,図27および図28においては,便宜上,検出領域A3を対象とする処理について説明するが,検出領域A4についても同様の処理が実行される。
図22の第2太陽判定部64には,画像取得部31が取得した撮影画像の画像情報が入力される。第2太陽判定部64は,撮影画像の中から路面反射した太陽光による高輝度領域を検出して,その検出範囲に基づいて太陽の位置を推定し,太陽光が撮影領域内に入射するか否かを判定する。
図22の第2BSW制御部65は,画像取得部31から入力される撮像画像,白濁検出部33の検出結果と,第2太陽判定部64の判定結果とに基づいて,閾値θを設定することにより第2BSW部62を制御する。
第2立体物検出部714が設定する検出領域A3およびA4は,第1の実施の形態における立体物検出部413が設定した検出領域A1およびA2と実質的に同一な位置に設定される。したがって,白濁検出部33が少なくとも検出領域A1またはA2に対応するレンズ表面が白濁していることを検出することと,少なくとも検出領域A3またはA4に対応するレンズ表面が白濁していることを検出することとは実質的に同じである。すなわち,白濁検出部33は,少なくとも検出領域A3またはA4に対応するレンズ表面が白濁していることを検出することを検出することができる。
報知制御部42は,第2の実施の形態においても図20にフローチャートを示す処理を行う。第2の実施の形態における報知制御部42は,図20のステップS1000の処理を行う場合,閾値θがレベル10(最大値)に設定されているか否かを判定することにより,第2BSW制御部65によりBSWが抑制されているかを判定する。
車載用車両認識装置200の制御部7は,画像取得部31と,第2太陽判定部64と,白濁検出部33と,第2車両検出部71と,第2BSW制御部65とを備える。
画像取得部31は,カメラ1が車両外を撮影して出力した撮影画像を取得する。
第2太陽判定部64は,高輝度領域81の重心の位置に基づいて,少なくとも太陽の高度を演算して(図29のステップS704),高輝度領域81の重心84の位置が反射日光領域に存在するか否かを判定する。反射日光領域は上限線82と下限線83により規定され,重心84が下限線83よりも上にあるとき,太陽の高度が所定高度以下であることを表す。
白濁検出部33は,カメラ1の撮影レンズのレンズ表面のうち,少なくとも検出領域A3およびA4に対応するレンズ表面が白濁していることを検出する(白濁検出部33の補足)。
第2車両検出部71は,検出領域A3およびA4に対応する撮影画像の画像領域から,他車両を検出する(図28のステップS614)。
第2BSW制御部65は,白濁検出部33により少なくとも検出領域A3およびA4に対応するレンズ表面が白濁していることが検出された場合に,太陽の高度が所定高度以下であると第2太陽判定部64が判定した場合には少なくとも,閾値θを最大レベルに調整することで第2車両検出部71による他車両の検出を抑制する(図31のステップS803,図32のNo.12)。
このようにすることで,車載用車両認識装置200では,撮影画像に太陽光が入射した場合にも,画像認識処理の精度が低下しない。
(変形例1)実施形態の組み合わせ
制御部2および7には,BSW部32と第2BSW部62の両方を備えることにしてもよい。その場合,例えば立体物検出部413と第2立体物検出部714の両方が他車両VXを検出した場合に,他車両VXが検出されたことにすればよい。また,そのとき,当該制御部には,BSW制御部35と第2BSW制御部65の両方を備えることにしてもよいし,BSW制御部35および第2BSW制御部65のいずれか片方を用いて第1閾値αと閾値θの両方を設定することにしてもよい。BSW制御部35が閾値θを設定する場合は,図17の第1閾値αの設定レベルを閾値θの設定レベルと読み替えればよい。同様に,第2BSW制御部65が第1閾値αを設定する場合は,図32の閾値θの設定レベルを第1閾値αの設定レベルに読み替えればよい。
その他,第1の実施の形態の構成と,第2の実施の形態の構成とは発明の特徴が損なわれない限り任意に組み合わせて実行してもよい。
上記の実施の形態では,白濁検出部33が白濁を検出したか否かに基づいて閾値を変化させたが,カメラ1の撮影レンズの白濁度合いを数値化して,その白濁度合いを表す数値に基づいて閾値を変化させることにしてもよい。例えば,ヒストグラムH1の平均値E1と,ヒストグラムH2の平均値E2と,ヒストグラムH3の平均値E3とに基づいて,白濁度合いを算出することにしてもよい。
BSW制御部35は,太陽範囲が白濁しているとき,閾値をより高レベルに設定することにしてもよい。同様に,第2BSW制御部65は,太陽範囲が白濁しているとき,閾値をより高レベルに設定することにしてもよい。太陽範囲が白濁しているか否かは,太陽範囲内の輝度勾配に基づいて判定すればよい。カメラ1の撮影レンズのレンズ表面のうち白濁している部分を通過する光は白濁の原因となる付着物により拡散するため,白濁箇所に対応する画素ごとの輝度の差は小さくなり,輝度勾配が小さくなる。BSW制御部35および第2BSW制御部65は,輝度勾配が所定値以下となったとき,太陽範囲が白濁していると判定すればよい。
日本国特許出願2012年第167602号(2012年7月27日出願)
2 制御部
3 警報出力部
4 動作状態報知部
5 外部装置制御部
6 記憶部
7 制御部
31 画像取得部
32 BSW部
33 白濁検出部
34 太陽判定部
35 BSW制御部
41 車両検出部
42 報知制御部
51 白濁検出領域
52 白濁検出領域
53 白濁検出領域
61 太陽範囲
62 第2BSW部
64 第2太陽判定部
65 第2BSW制御部
71 第2車両検出部
81 高輝度領域
82 上限線
83 下限線
84 重心
88 太陽範囲
100 車載用車両認識装置
200 車載用車両認識装置
411 視点変換部
412 位置合わせ部
413 立体物検出部
712 輝度差算出部
713 エッジ線検出部
714 第2立体物検出部
Claims (11)
- カメラが車両外を撮影して出力した撮影画像を取得する画像取得部と,
少なくとも太陽の高度を含む太陽の位置を演算して,前記太陽の高度が所定高度以下であることを判定する太陽判定部と,
前記カメラのレンズ表面が白濁していることを検出する白濁検出部と,
前記撮影画像の第1の画像領域の画像情報に基づいて,前記車両とは異なる他車両を検出する車両検出部と,
少なくとも前記第1の画像領域が白濁していることが前記白濁検出部により検出された場合に,前記太陽の高度が前記所定高度以下であると前記太陽判定部が判定したとき,前記車両検出部による前記他車両の検出を抑制する制御部と,
を備える画像処理装置。 - 請求項1に記載の画像処理装置において,
前記車両検出部は,前記他車両の検出感度に関わる所定の閾値を有し,
前記制御部は,前記レンズ表面のうち前記太陽の位置を中心とした画像範囲に対応する範囲が白濁しているとき,前記レンズ表面の当該範囲が白濁していないときよりも前記他車両の検出感度を前記閾値の変更により抑制する画像処理装置。 - 請求項1に記載の画像処理装置において,
前記太陽判定部は,日時と,前記車両が位置する緯度および経度と,前記車両の方向とに基づいて,前記太陽の位置を演算する画像処理装置。 - 請求項1に記載の画像処理装置において,
前記太陽判定部は,前記撮影画像に対して画像処理を行うことにより前記太陽の位置を演算する画像処理装置。 - 請求項4に記載の画像処理装置において,
前記カメラは,少なくとも前記車両外の路面を撮影し,
前記太陽判定部は,路面反射による高輝度領域を前記撮影画像から抽出して,前記高輝度領域の重心の位置に基づいて前記太陽の位置を演算する画像処理装置。 - 請求項2に記載の画像処理装置において,
前記制御部は,前記太陽の位置を中心とした画像範囲の輝度勾配に基づいて,前記レンズ表面のうち当該画像範囲に対応する範囲が白濁していることを検出する画像処理装置。 - 請求項1に記載の画像処理装置において,
前記撮影画像には白濁検出領域が設定され,
前記白濁検出部は,前記白濁検出領域に対してエッジ強度のヒストグラムを演算して,前記ヒストグラムを用いて演算される前記エッジ強度の平均値に基づいて,前記カメラレンズが白濁している領域を検出する画像処理装置。 - 請求項7に記載の画像処理装置において,
前記カメラは,少なくとも前記車両外の路面を撮影し,
前記白濁検出領域は,前記路面に設けられた白線の消失点の近傍に複数設定され、
前記白濁検出部は,前記白濁検出領域の各々に対してエッジ強度のヒストグラムを演算して,前記ヒストグラムの各々を用いて演算される前記エッジ強度の平均値に基づいて,前記カメラレンズが白濁している領域を検出する画像処理装置。 - 請求項7に記載の画像処理装置において,
前記カメラは,少なくとも前記車両外の路面を撮影し,
前記白濁検出領域には,前記路面に設けられた白線の消失点の近傍であって前記撮影画像の中央よりも上側の位置に設定される第1の白濁検出領域と,前記第1の白濁検出領域よりも下方に広がるように前記消失点の近傍に設定される第2の白濁検出領域とが含まれ,
前記白濁検出部は,昼間は前記第1の白濁検出領域を用いて前記カメラレンズが白濁している領域を検出し,夜間は前記第2の白濁検出領域を用いて前記カメラレンズが白濁している領域を検出する画像処理装置。 - 請求項1から9のいずれか一項に記載の画像処理装置において,
前記車両検出部による前記他車両の検出を前記制御部が抑制したことを,所定の報知部に報知させる報知制御部をさらに備える画像処理装置。 - 請求項2に記載の画像処理装置において,
前記白濁検出部は,前記カメラのレンズ表面の白濁度合いが第1の白濁度合いを超えたとき,前記カメラのレンズ表面が白濁していることを検出し,
前記車両検出部は,
前記カメラのレンズ表面が白濁していない第2の白濁度合いのときに前記閾値を第1の閾値に設定し,
前記カメラのレンズ表面の白濁度合いが前記第1の白濁度合いを超えたときに前記閾値を前記第1の閾値よりも大きい第2の閾値に設定し,
前記閾値を前記第1の閾値と前記第2の閾値とのいずれよりも小さい第3の閾値に設定する第3の白濁度合いを前記第2の白濁度合いと前記第1の白濁度合いとの間に設ける画像処理装置。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP13822724.4A EP2879111A4 (en) | 2012-07-27 | 2013-07-22 | IMAGING DEVICE |
| JP2014526910A JP6254084B2 (ja) | 2012-07-27 | 2013-07-22 | 画像処理装置 |
| US14/417,650 US9721169B2 (en) | 2012-07-27 | 2013-07-22 | Image processing device for detecting vehicle in consideration of sun position |
| CN201380039597.4A CN104508723B (zh) | 2012-07-27 | 2013-07-22 | 图像处理装置 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2012-167602 | 2012-07-27 | ||
| JP2012167602 | 2012-07-27 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2014017434A1 true WO2014017434A1 (ja) | 2014-01-30 |
Family
ID=49997245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2013/069785 Ceased WO2014017434A1 (ja) | 2012-07-27 | 2013-07-22 | 画像処理装置 |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US9721169B2 (ja) |
| EP (1) | EP2879111A4 (ja) |
| JP (1) | JP6254084B2 (ja) |
| CN (1) | CN104508723B (ja) |
| WO (1) | WO2014017434A1 (ja) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106489174A (zh) * | 2014-06-27 | 2017-03-08 | 康诺特电子有限公司 | 用于通过机动车辆的相机系统跟踪接近机动车辆的目标车辆的方法、相机系统以及机动车辆 |
| JP2021056760A (ja) * | 2019-09-30 | 2021-04-08 | アイシン・エィ・ダブリュ株式会社 | 運転支援システムおよび運転支援プログラム |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5747482B2 (ja) * | 2010-03-26 | 2015-07-15 | 日産自動車株式会社 | 車両用環境認識装置 |
| JP6174975B2 (ja) * | 2013-11-14 | 2017-08-02 | クラリオン株式会社 | 周囲環境認識装置 |
| KR20150106719A (ko) * | 2014-03-12 | 2015-09-22 | 삼성전자주식회사 | 전자 장치의 촬영 위치 안내 방법 및 이를 이용한 전자 장치 |
| US9718405B1 (en) | 2015-03-23 | 2017-08-01 | Rosco, Inc. | Collision avoidance and/or pedestrian detection system |
| US9904146B2 (en) * | 2015-10-29 | 2018-02-27 | GM Global Technology Operations LLC | Camera with positionable light shade |
| JP6658054B2 (ja) * | 2016-02-16 | 2020-03-04 | トヨタ車体株式会社 | 車体部品の施工部位判定システム及び施工部位判定方法 |
| US10462380B2 (en) * | 2016-06-13 | 2019-10-29 | Aptiv Technologies Limited | Camera system with light-shield |
| JP6938903B2 (ja) * | 2016-12-14 | 2021-09-22 | 株式会社デンソー | 車両における衝突回避装置および衝突回避方法 |
| WO2018158994A1 (ja) * | 2017-02-28 | 2018-09-07 | パナソニックIpマネジメント株式会社 | 変位計測装置および変位計測方法 |
| JP6922297B2 (ja) * | 2017-03-21 | 2021-08-18 | 三菱自動車工業株式会社 | 運転支援システム |
| JP6686988B2 (ja) * | 2017-08-28 | 2020-04-22 | 株式会社Soken | 映像出力装置及び映像生成プログラム |
| US11257375B2 (en) * | 2018-12-31 | 2022-02-22 | Ficosa Adas, S.L.U. | Method and system for detecting objects in a vehicle blind spot |
| JP7528438B2 (ja) * | 2019-12-26 | 2024-08-06 | 日本電気株式会社 | データ圧縮装置、モデル生成装置、データ圧縮方法、モデル生成方法及びコンピュータプログラム |
| US12115916B2 (en) | 2021-02-01 | 2024-10-15 | Rosco, Inc. | Downlighting signal and illumination mirror head for vehicle |
| JP2022142510A (ja) * | 2021-03-16 | 2022-09-30 | パナソニックIpマネジメント株式会社 | 車両用周辺警戒装置および車両用周辺警戒方法 |
| JP2022155838A (ja) * | 2021-03-31 | 2022-10-14 | 本田技研工業株式会社 | 車両制御装置、経路生成装置、車両制御方法、経路生成方法、およびプログラム |
| EP4099100B1 (fr) | 2021-06-02 | 2025-03-12 | The Swatch Group Research and Development Ltd | Mouvement horloger muni d'un oscillateur comprenant un spiral piezoelectrique |
| CN113726983B (zh) * | 2021-07-12 | 2022-07-12 | 北京邮电大学 | 一种基于时间,定位,镜头角度,入射光强和色温的太阳光眩光抑制的方法和装置 |
| EP4130890B1 (fr) | 2021-08-04 | 2024-03-27 | The Swatch Group Research and Development Ltd | Mouvement horloger muni d'un oscillateur comprenant un spiral piézoélectrique |
| US12397712B2 (en) * | 2023-01-19 | 2025-08-26 | Panasonic Automotive Systems Co., Ltd. | Vehicular camera |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003255430A (ja) * | 2002-02-28 | 2003-09-10 | Toshiba Corp | 映像診断装置、車載型映像監視装置の映像診断システム |
| JP2005073296A (ja) * | 2004-10-27 | 2005-03-17 | Mitsubishi Electric Corp | 車両用カメラの露光制御装置 |
| JP2008219063A (ja) | 2007-02-28 | 2008-09-18 | Sanyo Electric Co Ltd | 車両周辺監視装置及び方法 |
| JP2010086266A (ja) | 2008-09-30 | 2010-04-15 | Mazda Motor Corp | 車両用画像処理装置 |
| JP2012003662A (ja) * | 2010-06-21 | 2012-01-05 | Nissan Motor Co Ltd | 移動距離検出装置及び移動距離検出方法 |
| WO2013018673A1 (ja) * | 2011-08-02 | 2013-02-07 | 日産自動車株式会社 | 立体物検出装置及び立体物検出方法 |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004075105A2 (en) * | 2003-02-20 | 2004-09-02 | Intelligent Mechatronic Systems Inc. | Adaptive visual occupant detection and classification system |
| JP5035284B2 (ja) * | 2009-03-25 | 2012-09-26 | 株式会社日本自動車部品総合研究所 | 車両周辺表示装置 |
| US8564502B2 (en) * | 2009-04-02 | 2013-10-22 | GM Global Technology Operations LLC | Distortion and perspective correction of vector projection display |
| US8704653B2 (en) | 2009-04-02 | 2014-04-22 | GM Global Technology Operations LLC | Enhanced road vision on full windshield head-up display |
| US8212874B2 (en) * | 2009-10-23 | 2012-07-03 | GM Global Technology Operations LLC | Automatic camera calibration using GPS and solar tracking |
| CN102036016B (zh) * | 2010-12-03 | 2012-10-10 | 杭州海康威视系统技术有限公司 | 视频检测方法及其系统 |
| JP2012118929A (ja) | 2010-12-03 | 2012-06-21 | Fujitsu Ten Ltd | 外部環境判定装置及び外部環境判定プログラム |
| JP5310760B2 (ja) * | 2011-03-04 | 2013-10-09 | トヨタ自動車株式会社 | 接近車両検出装置 |
| JP5892876B2 (ja) * | 2011-07-28 | 2016-03-23 | クラリオン株式会社 | 車載用環境認識装置 |
-
2013
- 2013-07-22 JP JP2014526910A patent/JP6254084B2/ja active Active
- 2013-07-22 CN CN201380039597.4A patent/CN104508723B/zh active Active
- 2013-07-22 WO PCT/JP2013/069785 patent/WO2014017434A1/ja not_active Ceased
- 2013-07-22 US US14/417,650 patent/US9721169B2/en active Active
- 2013-07-22 EP EP13822724.4A patent/EP2879111A4/en not_active Ceased
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003255430A (ja) * | 2002-02-28 | 2003-09-10 | Toshiba Corp | 映像診断装置、車載型映像監視装置の映像診断システム |
| JP2005073296A (ja) * | 2004-10-27 | 2005-03-17 | Mitsubishi Electric Corp | 車両用カメラの露光制御装置 |
| JP2008219063A (ja) | 2007-02-28 | 2008-09-18 | Sanyo Electric Co Ltd | 車両周辺監視装置及び方法 |
| JP2010086266A (ja) | 2008-09-30 | 2010-04-15 | Mazda Motor Corp | 車両用画像処理装置 |
| JP2012003662A (ja) * | 2010-06-21 | 2012-01-05 | Nissan Motor Co Ltd | 移動距離検出装置及び移動距離検出方法 |
| WO2013018673A1 (ja) * | 2011-08-02 | 2013-02-07 | 日産自動車株式会社 | 立体物検出装置及び立体物検出方法 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP2879111A4 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106489174A (zh) * | 2014-06-27 | 2017-03-08 | 康诺特电子有限公司 | 用于通过机动车辆的相机系统跟踪接近机动车辆的目标车辆的方法、相机系统以及机动车辆 |
| CN106489174B (zh) * | 2014-06-27 | 2019-07-12 | 康诺特电子有限公司 | 通过相机系统跟踪车辆的方法、相机系统以及机动车辆 |
| JP2021056760A (ja) * | 2019-09-30 | 2021-04-08 | アイシン・エィ・ダブリュ株式会社 | 運転支援システムおよび運転支援プログラム |
| JP7371419B2 (ja) | 2019-09-30 | 2023-10-31 | 株式会社アイシン | 運転支援システムおよび運転支援プログラム |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104508723A (zh) | 2015-04-08 |
| JPWO2014017434A1 (ja) | 2016-07-11 |
| EP2879111A1 (en) | 2015-06-03 |
| CN104508723B (zh) | 2016-10-12 |
| US9721169B2 (en) | 2017-08-01 |
| US20150220793A1 (en) | 2015-08-06 |
| EP2879111A4 (en) | 2016-10-19 |
| JP6254084B2 (ja) | 2017-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6254084B2 (ja) | 画像処理装置 | |
| CN104508727B (zh) | 三维物体检测装置和三维物体检测方法 | |
| CN104509101B (zh) | 三维物体检测装置和三维物体检测方法 | |
| CN104509090B (zh) | 车载用图像识别装置 | |
| CN104509102B (zh) | 三维物体检测装置和异物检测装置 | |
| RU2636120C2 (ru) | Устройство обнаружения трехмерных объектов | |
| CN104012081B (zh) | 三维物体检测装置 | |
| JP5804180B2 (ja) | 立体物検出装置 | |
| CN104509100B (zh) | 三维物体检测装置以及三维物体检测方法 | |
| JP4980970B2 (ja) | 撮像手段の調整装置および物体検出装置 | |
| CN104508728B (zh) | 三维物体检测装置 | |
| WO2016125377A1 (ja) | 画像処理装置、および車両システム | |
| JP5943077B2 (ja) | 立体物検出装置および立体物検出方法 | |
| JP5682735B2 (ja) | 立体物検出装置 | |
| CN104685866A (zh) | 三维物体检测装置以及三维物体检测方法 | |
| JP5743020B2 (ja) | 立体物検出装置 | |
| JP5835459B2 (ja) | 立体物検出装置 | |
| JP5668891B2 (ja) | 立体物検出装置 | |
| WO2014017603A1 (ja) | 立体物検出装置および立体物検出方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13822724 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2014526910 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 14417650 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2013822724 Country of ref document: EP |