WO2011086807A1 - 車両周辺監視装置 - Google Patents
車両周辺監視装置 Download PDFInfo
- Publication number
- WO2011086807A1 WO2011086807A1 PCT/JP2010/072647 JP2010072647W WO2011086807A1 WO 2011086807 A1 WO2011086807 A1 WO 2011086807A1 JP 2010072647 W JP2010072647 W JP 2010072647W WO 2011086807 A1 WO2011086807 A1 WO 2011086807A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- vehicle
- image portion
- monitoring device
- periphery monitoring
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/20—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/22—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles for viewing an area outside the vehicle, e.g. the exterior of the vehicle
- B60R1/23—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles for viewing an area outside the vehicle, e.g. the exterior of the vehicle with a predetermined field of view
- B60R1/24—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles for viewing an area outside the vehicle, e.g. the exterior of the vehicle with a predetermined field of view in front of the vehicle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/20—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/30—Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles providing vision in the non-visible spectrum, e.g. night or infrared vision
-
- 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
- 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
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/103—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using camera systems provided with artificial illumination device, e.g. IR light source
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/107—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using stereoscopic cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/20—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of display used
- B60R2300/205—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of display used using a head-up display
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
- B60R2300/301—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing combining image information with other obstacle sensor information, e.g. using RADAR/LIDAR/SONAR sensors for estimating risk of collision
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
- B60R2300/302—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing combining image information with GPS information or vehicle data, e.g. vehicle speed, gyro, steering angle data
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
- B60R2300/307—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing virtually distinguishing relevant parts of a scene from the background of the scene
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
Definitions
- the present invention relates to a vehicle periphery monitoring device that recognizes a monitoring object around a vehicle from an image captured by a camera attached to the vehicle.
- a vehicle periphery monitoring device in which a monitoring object such as a pedestrian that may come into contact with the host vehicle is detected from an image around the host vehicle captured by a camera and is notified to the driver.
- a monitoring object such as a pedestrian that may come into contact with the host vehicle is detected from an image around the host vehicle captured by a camera and is notified to the driver.
- the distance from the own vehicle is the same in order to identify and extract the image portion of the pedestrian and the image portion of the other vehicle since the image is captured by the infrared camera. Therefore, an image area including a pair of image portions whose infrared rays amount is equal to or less than a predetermined value and is present at a symmetrical position is recognized as an image area of another vehicle.
- an object of the present invention is to provide a vehicle periphery monitoring device that can accurately recognize an image of another vehicle without using distance information between the host vehicle and a monitoring object.
- the present invention has been made to achieve the above-described object, and relates to a vehicle periphery monitoring device that recognizes a monitoring object around the host vehicle based on an image captured by an in-vehicle camera.
- a lamp image part extraction unit that extracts a first image part having a feature quantity of a vehicle lamp from the captured image, and a predetermined size including the first image part.
- An extension area setting unit that sets an area as a first extension area, and whether or not the first extension area has horizontal symmetry in the horizontal direction with the first image portion as a midpoint; When it has, it has the object classification recognition part which recognizes the image containing the said lamp body image part as a vehicle, It is characterized by the above-mentioned.
- the shape of the left and right sides of the vehicle lamp (headlight, taillight) is designed to be symmetrical. Therefore, for the first extended region including the first image portion having the feature amount of the lamp extracted by the lamp image portion extraction unit, the first image portion is set as a midpoint by the object type recognition unit. By determining whether there is left-right symmetry in the horizontal direction, it is possible to accurately recognize whether or not the monitoring target is a vehicle.
- a symmetric image portion extraction unit that extracts a first image portion and a second image portion that exist in a line-symmetrical position in the horizontal direction from the captured image, and the first image.
- An extended area setting unit that sets an area of a predetermined size including a portion as a first extended area, and an extended search that sets a range wider than the size of the first extended area including the second image portion as an extended search range
- a search is made for a second extension area in which the degree of correlation between the range setting unit and the first extension area or the mirror inverted image of the first extension area is equal to or higher than a predetermined level within the extension search range, and the second extension area
- an object type recognizing unit that recognizes an image including the first image portion and the second image portion as a vehicle when detected.
- the object type recognizing unit causes the second extension area having a correlation level with a mirror inverted image of the first extension area or the first extension area to be equal to or higher than a predetermined level. Whether or not the image including the first image portion and the second image portion is an other vehicle is recognized depending on whether or not it exists within the range. In this case, in addition to the symmetry between the first image portion and the second image portion, the form of the image around the first image portion and the second image portion (shape, size, brightness, etc.) If the first image portion and the second image portion are image portions of the same vehicle, the correlation degree is high. Therefore, it is possible to accurately recognize whether or not the monitoring target is another vehicle without using information on the distance between the host vehicle and the monitoring target.
- the extension area setting unit connects the first extension area, the first image portion and the second image portion, and a straight line orthogonal to the line segment and the midpoint of the line segment.
- the extended search range setting unit sets a horizontal range of the extended search range from the midpoint to the second image portion. It is characterized in that it is set so as to include this range.
- the extension region setting unit uses the first extension region to connect the first image portion and the second image portion as a boundary with a line segment and a straight line orthogonal to the midpoint of the line segment as a boundary.
- the extended search range setting unit includes a range in the horizontal direction of the extended search range so as to include a range from the midpoint to the second image portion, By setting, the second extended area can be searched efficiently.
- the extension area setting unit sets the first extension area on the condition that the height from the road surface at the position in the corresponding real space is equal to or higher than a predetermined height. It is characterized by.
- the present invention it is possible to prevent an image of a single component (muffler or the like) provided in the lower part of another vehicle from being included in only one of the first surrounding area and the second surrounding area. Thus, it is possible to suppress the correlation degree from being lowered.
- the object includes a feature portion search unit that searches for a third image portion having a predetermined feature portion of a vehicle in a region around the first image portion and the second image portion.
- the type recognizing unit is configured such that when the degree of correlation between the first extended region and the second extended region is equal to or higher than a predetermined level and the third image portion is detected by the feature portion searching unit, An image including an image portion and the second image portion is recognized as an image of another vehicle.
- the present invention it is possible to increase the recognition accuracy of other vehicles by the object type recognizing unit by using the presence of the third image portion as a condition.
- the vehicle-mounted camera has a single camera, and the distance from the own vehicle to the monitoring object is determined between the captured images of the camera at different times.
- a distance calculation unit that calculates based on a rate of change in the size of the image of the monitoring object is provided.
- the distance calculation unit calculates the distance between the host vehicle and the monitoring target object from the image captured by a single camera, the accuracy of the distance may be reduced.
- the other vehicle can be recognized by the object type recognition unit without using information.
- the vehicle-mounted camera has a single camera, and the distance from the own vehicle to the monitoring object is determined by the first image portion and the second image portion in the captured image of the camera. It is characterized by comprising a distance calculation unit for calculating based on the horizontal interval.
- the distance between the first image portion and the second image portion corresponds to the width of the vehicle (approximately 150 cm to 200 cm). Become. Then, as the distance from the host vehicle becomes longer, the interval between the first image portion and the second image portion becomes shorter. Therefore, for example, by preparing in advance the data of the correspondence between the horizontal width of the vehicle image on the captured image and the real space distance when it is assumed that the width of the vehicle is 170 cm. The distance to the vehicle can be calculated from the interval between the image portion and the second image portion.
- the distance calculation unit calculates a distance from the own vehicle to the monitoring object based on a rate of change in the size of the image of the monitoring object between the captured images of the camera at different times, and the target
- the object type recognizing unit calculates a distance based on a horizontal interval between the first image portion and the second image portion, which is calculated by the distance calculating unit for the same monitoring object, and a size of the image of the monitoring object.
- the difference from the distance based on the change rate of the height is a predetermined value or more, the monitoring object is recognized as a moving object.
- the object type recognizing unit calculates the distance based on the distance between the first image portion and the second image portion calculated by the distance calculating unit for the same monitoring object and the image of the monitoring object.
- the difference from the distance based on the rate of change in size is greater than or equal to a predetermined value, the monitoring object can be recognized as a moving object.
- the monitoring object when the monitoring object is recognized as a moving object, a distance with a large error is used by prohibiting the calculation of the distance based on the rate of change in the size of the image of the monitoring object. You can avoid that.
- the monitoring target when the monitoring target is a moving object, it is certain that the object is not a pedestrian that is regarded as a stationary object, and therefore can be excluded from the target of contact determination for pedestrians, for example.
- the block diagram of the vehicle periphery monitoring apparatus of this invention Explanatory drawing of the attachment aspect to the vehicle of the vehicle periphery monitoring apparatus shown in FIG. 2 is a flowchart of a series of processing by the image processing unit shown in FIG. The flowchart of a symmetrical image partial extraction process. Explanatory drawing of a symmetrical image partial extraction process. The flowchart of a symmetrical reliability determination process. The flowchart of a symmetrical reliability determination process. Explanatory drawing of a shape reliability determination process.
- a vehicle periphery monitoring device includes a single infrared camera 2 capable of detecting far-infrared rays, a yaw rate sensor 3 that detects the yaw rate of the vehicle, and a vehicle speed sensor that detects the traveling speed of the vehicle. 4, a brake sensor 5 that detects the amount of brake operation performed by the driver, and a monitoring object (such as a pedestrian) in front of the vehicle is detected from an image obtained by the infrared camera 2, and the monitoring object and the vehicle come into contact with each other.
- An image processing unit 1 that outputs an alarm when there is a high possibility, a speaker 6 that outputs an alarm by voice, and an image obtained by the infrared camera 2 and a monitoring object that has a high possibility of contact Is provided with a head-up display 7 (hereinafter referred to as HUD 7) for performing a display for the driver to visually recognize.
- HUD 7 head-up display 7
- the infrared camera 2 is disposed at the front portion of the vehicle 10 and has a characteristic that the output level increases (the luminance increases) as the temperature of the imaged object increases. Further, the HUD 7 is provided such that the screen 7 a is displayed at a front position on the driver side of the front window of the vehicle 10.
- the image processing unit 1 converts an analog video signal output from the infrared camera 2 into digital data, loads it into an image memory (not shown), and performs various calculations on the image ahead of the vehicle captured in the image memory. It has a function to perform processing.
- the image processing unit 1 includes a target object extraction unit 20 that extracts a candidate image portion of a monitoring target object from an image ahead of the vehicle captured in an image memory, and a horizontal symmetry among the image candidates.
- a symmetric image part extracting unit 21 that extracts first and second image parts having an extended area setting unit 22 that sets a first extended area including the first image part.
- the image processing unit 1 has an extended search range setting unit 23 that sets an extended search range including the second image portion, and a first level of correlation with the mirror inverted image of the first extended region within the extended search range. 2 By searching the extended area, it is determined whether or not symmetrical reliability exists, and the object type recognizing unit 24 that recognizes an image having symmetrical reliability as an image of another vehicle, and a position in the real space corresponding to the image.
- a real space position calculation unit 25 for calculating, and a contact determination unit 26 for determining the possibility of contact between the monitoring object and the vehicle 10 (own vehicle) are provided.
- the image processing unit 1 is an electronic unit configured by a CPU, a memory, and the like (not shown). By causing the CPU to execute a vehicle periphery monitoring program, the image processing unit 1 includes the object extraction unit 20, It functions as a symmetric image partial extraction unit 21, an extended region setting unit 22, an extended search range setting unit 23, an object type recognition unit 24, a real space position calculation unit 25, and a contact determination unit 26.
- the image processing unit 1 recognizes other vehicles by performing the steps of “preprocessing” (STEP 100-) ⁇ “symmetric image partial extraction” (STEP 200-) ⁇ “symmetric reliability determination” ⁇ “shape reliability determination” To do.
- Pre-processing is executed by the object extraction unit 20.
- the object extraction unit 20 inputs an infrared video signal (analog signal) from the infrared camera 2 and takes in a grayscale image converted into digital gradation (luminance) data into an image memory. Then, for each pixel of the grayscale image, the image processing unit 1 sets a pixel whose luminance is equal to or higher than a predetermined threshold as “1” (white), and sets a pixel whose luminance is lower than the threshold as “0” (black).
- a binary image is acquired by performing binarization processing.
- the image processing unit 1 extracts a candidate image portion of a specific part (for example, a pedestrian's head) of the monitoring target from the binary image. Specifically, the run length data of each white area in the binary image is calculated, and a labeling process is performed to label the areas with overlapping portions in the horizontal direction together, and among the labeled areas, A region having a preset feature amount (circular shape or the like) is extracted as a candidate for an image portion of a specific part of the monitoring target.
- a specific part for example, a pedestrian's head
- FIG. 5A shows a binary image Im including an image 30 of the other vehicle, and the image portions 31 and 32 of the headlight portion of the other vehicle are extracted as candidates for the image portion of the monitoring object. It shows the state that was done. Below, the case where the other vehicle contained in the image Im of Fig.5 (a) is recognized is demonstrated as an example.
- “Symmetric image part extraction” is executed by the symmetric image part extraction unit 21 according to the flowchart shown in FIG.
- the symmetric image portion extraction unit 21, as shown in FIG. 5B includes a first image portion having a width in the horizontal direction dxP and the vertical direction dyP that includes the candidate 31 of the image portion of the monitoring target. Set A1.
- the symmetrical image portion extraction unit 21 reverses the mirror image of the first image portion A1 (the image obtained by inverting the left and right of the first image portion A1 with respect to the vertical line passing through the center of the first image portion A1). A1m is generated.
- the symmetric image portion extraction unit 21 sets the right search range ER with the horizontal width dxA and the vertical width dyA on the right side of the first image portion A1, and the first image portion A1.
- a left search range EL having a horizontal width of dxA and a vertical width of dyA is set on the left side.
- the symmetric image partial extraction unit 21 has a correlation degree with the mirror inverted image A1m that is equal to or higher than a predetermined level (high correlation degree with A1m) within the right search range ER and the left search range EL.
- a two-image portion A2 is searched.
- the second image portion A2 including the image portion 32 of the left headlight of the other vehicle is detected.
- the process proceeds from the next STEP 105 to STEP 106, and the symmetric image portion extraction unit 21 has a symmetric image portion (first image portion A1 and second image portion A2).
- the process proceeds to STEP107. In this case, the process proceeds to “symmetric symmetry determination” in FIG.
- the process branches from STEP 105 to STEP 110, and the symmetric image portion extraction unit 21 determines that there is no symmetric image portion and proceeds to STEP 107. In this case, the processes after “symmetric reliability determination” in FIG. 3 are not executed. In addition, if the candidate of the image part of another monitoring target object is extracted by STEP100, the process after STEP200 will be performed again about this candidate.
- “Symmetric reliability determination” is executed by the extended region setting unit 22, the extended search range setting unit 23, and the object type recognition unit 24 in accordance with the flowchart shown in FIG.
- the extended region setting unit 22 determines the width car_w (estimated from the distance between the first image portion A1 and the second image portion A2) of the image 30 of the other vehicle shown in FIG. 5A and the center car_c ( An intermediate point between the first image portion A1 and the second image portion A2) is calculated.
- the expansion area setting unit 22 determines that the difference or ratio between the width car_w of the image 30 and the horizontal width dxP of the first image portion A1 is the difference between the vehicle width and the headlight width in a general vehicle. Or it is judged whether it is in the regulation range set up supposing ratio. If the difference or ratio between car_w and dxP is outside the specified range, the process branches to STEP320.
- STEP 320 is a process performed by the object type recognition unit 24.
- the object type recognition unit 24 has no symmetry reliability between the first image portion A1 and the second image portion A2, and the image 30 is not an image of another vehicle. to decide. In this case, the processing after “shape reliability determination” in STEP 400 of FIG. 3 is not executed. If a candidate for an image portion of another monitoring target has been extracted in the “pre-processing” of STEP 100, the processing after STEP 200 is executed again for this candidate.
- STEP 303 is processes performed by the extended area setting unit 22.
- the extension area setting unit 22 sets the first extension area B1 including the first image portion A1, as shown in FIG.
- the horizontal width dxQ is set to about 1 ⁇ 2 of car_w
- the vertical width dyQ is set to the size of the height dyP + 2 ⁇ ymg of the first image portion A1.
- the extension area setting unit 22 generates a mirror inverted image B1m of the first extension area B1.
- the first extended region B1 includes a line segment 50 connecting the first image portion A1 and the second image portion A2, and a straight line orthogonal to the midpoint Pc of this line segment. It is set on the first image portion A1 side with 51 as a boundary.
- the subsequent STEP 305 is processing by the extended search range setting unit 23.
- the extended search range setting unit 23 starts from the midpoint Pc (car_cx, car_cy) of the line segment 50 connecting the first image portion A1 and the second image portion A2 in the horizontal direction.
- the extended search range setting unit 23 sets the extended search range C from the reference point P2 to a horizontal width dxB of about car_w and a vertical width dyB of about dyP + 2 ⁇ mgp.
- the horizontal range of the extended search range C is set so as to include the range from the midpoint Pc to the second image portion A2.
- the next STEP 306 to STEP 308 are processes by the object type recognition unit 24.
- the object type recognizing unit 24 searches the extended search range C for a second extended area in which the degree of correlation between the first extended area B1 and the mirror inverted image B1m is equal to or higher than a predetermined level. Then, as shown in FIG. 7B, when the second extended region B2 having a correlation degree with the mirror inverted image B1m of a predetermined level or more is detected, the process proceeds from STEP 307 to STEP 308.
- the object type recognition unit 24 determines the symmetry reliability of the image 30.
- the process proceeds to STEP 309, where the “target reliability determination” process is terminated. Then, the process proceeds to “shape reliability determination” in STEP 400 of FIG.
- the process branches from STEP307 to STEP320, and the object type recognition unit 24 has no symmetry reliability of the image 30, It is determined that the image 30 is not an image of another vehicle. In this case, the “shape reliability determination” process of FIG. 3 is not executed. In addition, if the candidate of the image part of another monitoring target object is extracted by STEP100, the process after STEP200 will be performed again about this candidate.
- the “shape reliability determination” in STEP 400 of FIG. 3 is processing by the object type recognition unit 24.
- the object type recognizing unit 24 has vehicle-specific features at the upper or lower portion of the portion where symmetry is recognized (the range between the image portions 31 and 32 of the left and right headlights). Determine if there is a part.
- the object type recognition unit 24 recognizes that the image 30 is an image of another vehicle when there is a portion having a characteristic unique to the vehicle.
- the contact determination unit 26 does not determine the possibility of contact with the own vehicle.
- left and right (horizontal direction) symmetry is determined in STEP 200 and 300 for the image of the monitoring target, and “shape reliability determination” is performed in STEP 400.
- the reliability of other vehicle recognition was improved by this, even if it is a case where "shape reliability determination" is not performed, the effect of the present invention can be acquired.
- the distance calculation part 25 which calculates the distance of the own vehicle and the monitoring target object from the picked-up image by the single camera 6 was shown, it has two cameras (stereo camera), The distance between the host vehicle and the monitoring target may be calculated from the parallax of the two cameras, or the distance between the host vehicle and the monitoring target may be detected by a distance measuring sensor such as a radar.
- the present invention can be applied even when a visible camera is used.
- the second extended area B2 in which the degree of correlation between the first extended area B1 and the mirror inverted image B1m is equal to or higher than a predetermined level is searched.
- the shape of the other vehicle and the setting of the first extended area B1 are searched.
- a search may be made for the second extended region B2 in which the degree of correlation with the first extended region B1 is not less than a predetermined level instead of the mirror inverted image B1m.
- the symmetric image portion (first image portion A1 and second image portion A2) is extracted by the symmetric image portion extraction unit 21, but the first image having the characteristics (circular shape, etc.) of the lamp body.
- a lamp image part extraction unit for extracting the part A1 is provided, a first extension area including the first image part A1 is set by the extension area setting unit 22, and the first extension area is set by the object type recognition unit 24. It may be determined whether or not there is horizontal symmetry in the horizontal direction with the first image portion A1 as the midpoint.
- the first extended region is centered on the first image portion.
- the vehicle has a horizontally symmetrical vehicle as a point, it can be accurately recognized that the image including the first image portion is an image of the vehicle.
- the real space distance calculation unit 25 calculates the distance from the host vehicle to the monitoring object based on the horizontal interval between the first image portion A1 and the second image portion A2 in the captured image of the infrared camera 2. May be.
- the map data corresponding to the width (number of pixels) of the vehicle image in the captured image and the distance from the host vehicle 10 is set assuming that the vehicle width is 170 cm.
- the distance from the host vehicle 10 to the other vehicle can be obtained by storing in the memory in advance and applying the interval (number of pixels) between the first image portion and the second image portion to this correspondence map.
- the object type recognizing unit 24 thus calculates the distance between the host vehicle 10 and the other vehicle calculated based on the interval between the first image portion and the second image portion, and the change in the size of the image described above. It is determined whether or not the difference between the distance between the host vehicle 10 calculated based on the rate and the other vehicle is greater than or equal to a predetermined value. If the difference is greater than or equal to the predetermined value, the other vehicle is recognized as a moving body. It may be.
- the vehicle periphery monitoring device of the present invention it is possible to accurately recognize an image of another vehicle without using the distance information between the own vehicle and the monitoring object, Useful for monitoring.
- SYMBOLS 1 ... Image processing unit, 20 ... Object extraction part, 21 ... Symmetric image part extraction part, 22 ... Expansion area setting part, 23 ... Extended search range setting part, 24 ... Object type recognition part, A1 ... 1st image part , A1m ... mirror inverted image of the first image part, A2 ... second image part, B1 ... first extension area, B2 ... second extension area, C ... extension search range.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims (9)
- 車載カメラによる撮像画像に基づいて、自車両周辺の監視対象物を認識する車両周辺監視装置において、
前記撮像画像から、車両の灯体の特徴量を有する第1画像部分を抽出する灯体画像部分抽出部と、
前記第1画像部分を含む所定サイズの領域を、第1拡張領域として設定する拡張領域設定部と、
前記第1拡張領域が前記第1画像部分を中点とした水平方向の左右対称性を有するか否かを判定し、該対称性を有するときは、前記灯体画像部分を含む画像を車両と認識する対象物種別認識部とを備えたことを特徴とする車両周辺監視装置。 - 請求項1記載の車両周辺監視装置において、
前記車載カメラとして単一のカメラを有し、
自車両から監視対象物までの距離を、異なる時刻での前記カメラの撮像画像間における該監視対象物の画像の大きさの変化率に基づいて算出する距離算出部を備えたことを特徴とする車両周辺監視装置。 - 車載カメラによる撮像画像に基づいて、自車両周辺の監視対象物を認識する車両周辺監視装置において、
前記撮像画像から、水平方向で線対称となる位置に存在する第1画像部分及び第2画像部分を抽出する対称画像部分抽出部と、
前記第1画像部分を含む所定サイズの領域を、第1拡張領域として設定する拡張領域設定部と、
前記第2画像部分を含む前記第1拡張領域のサイズよりも広い範囲を、拡張探索範囲として設定する拡張探索範囲設定部と、
前記拡張探索範囲内で前記第1拡張領域又は前記第1拡張領域のミラー反転画像との相関度が所定レベル以上である第2拡張領域を探索し、該第2拡張領域が探知されたときに、前記第1画像部分及び前記第2画像部分を含む画像を車両と認識する対象物種別認識部とを備えたことを特徴とする車両周辺監視装置。 - 請求項3記載の車両周辺監視装置において、
前記拡張領域設定部は、前記第1拡張領域を、前記第1画像部分と前記第2画像部分とを結び線分と該線分の中点で直交する直線を境界とした、該直線の前記第1画像部分側の範囲内に設定し、
前記拡張探索範囲設定部は、前記拡張探索範囲の水平方向の範囲を、前記中点から前記第2画像部分までの範囲を含むようにして、設定することを特徴とする車両周辺監視装置。 - 請求項3記載の車両周辺監視装置において、
前記拡張領域設定部は、対応する実空間上の位置の路面からの高さが所定高さ以上であることを条件として、前記第1拡張領域を設定することを特徴とする車両周辺監視装置。 - 請求項3記載の車両周辺監視装置において、
前記第1画像部分及び前記第2画像部分の周囲領域で、車両の所定の特徴部分を有する第3画像部分を探索する特徴部分探索部を備え、
前記対象物種別認識部は、前記第1拡張領域と前記第2拡張領域との相関度が所定レベル以上であり、且つ、前記特徴部分探索部により前記第3画像部分が探知されたときに、前記第1画像部分及び前記第2画像部分を含む画像を、他車両の画像と認識することを特徴とする車両周辺監視装置。 - 請求項3記載の車両周辺監視装置において、
前記車載カメラとして単一のカメラを有し、
自車両から監視対象物までの距離を、異なる時刻での前記カメラの撮像画像間における該監視対象物の画像の大きさの変化率に基づいて算出する距離算出部を備えたことを特徴とする車両周辺監視装置。 - 請求項3記載の車両周辺監視装置において、
前記車載カメラとして単一のカメラを有し、
自車両から監視対象物までの距離を、前記カメラの撮像画像における前記第1画像部分と前記第2画像部分との水平方向の間隔に基づいて算出する距離算出部を備えたことを特徴とする車両周辺監視装置。 - 請求項8記載の車両周辺監視装置において、
前記距離算出部は、自車両から監視対象物までの距離を、異なる時刻での前記カメラの撮像画像間における該監視対象物の画像の大きさの変化率に基づいて算出し、
前記対象物種別認識部は、同一の監視対象物について前記距離算出部により算出された、前記第1画像部分と前記第2画像部分との水平方向の間隔に基づく距離と該監視対象物の画像の大きさの変化率に基く距離との差が所定値以上であるときに、該監視対象物が移動体であると認識することを特徴とする車両周辺監視装置。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2011549886A JP5480917B2 (ja) | 2010-01-14 | 2010-12-16 | 車両周辺監視装置 |
| CN201080061317.6A CN102713988B (zh) | 2010-01-14 | 2010-12-16 | 车辆周围监测装置 |
| EP10843162.8A EP2482268A4 (en) | 2010-01-14 | 2010-12-16 | DEVICE FOR MONITORING THE VEHICLE ENVIRONMENT |
| US13/515,618 US8994824B2 (en) | 2010-01-14 | 2010-12-16 | Vehicle periphery monitoring device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2010-005905 | 2010-01-14 | ||
| JP2010005905 | 2010-01-14 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2011086807A1 true WO2011086807A1 (ja) | 2011-07-21 |
Family
ID=44304098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2010/072647 Ceased WO2011086807A1 (ja) | 2010-01-14 | 2010-12-16 | 車両周辺監視装置 |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US8994824B2 (ja) |
| EP (1) | EP2482268A4 (ja) |
| JP (1) | JP5480917B2 (ja) |
| CN (1) | CN102713988B (ja) |
| WO (1) | WO2011086807A1 (ja) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013186902A (ja) * | 2012-03-07 | 2013-09-19 | Ricoh Co Ltd | 車輌検知方法及び装置 |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9292735B2 (en) * | 2011-09-28 | 2016-03-22 | Honda Motor Co., Ltd. | Living body recognizing device |
| EP2827318A4 (en) * | 2012-03-12 | 2016-01-13 | Honda Motor Co Ltd | DEVICE FOR MONITORING A VEHICLE ENVIRONMENT |
| KR102021152B1 (ko) * | 2013-05-07 | 2019-09-11 | 현대모비스 주식회사 | 원적외선 카메라 기반 야간 보행자 인식 방법 |
| JP5895955B2 (ja) * | 2014-02-07 | 2016-03-30 | トヨタ自動車株式会社 | 車線境界線検出装置 |
| JP6398675B2 (ja) * | 2014-12-09 | 2018-10-03 | 株式会社デンソー | 画像生成装置 |
| US11064226B2 (en) * | 2017-03-16 | 2021-07-13 | Echo-Sense, Inc. | System and method for concurrent data streams from a singular sensor with remotely selectable parameters |
| US10803299B2 (en) | 2017-03-16 | 2020-10-13 | Echo-Sense, Inc. | System to overcome the two-dimensional nature of the captured images when attempting to generate three-dimensional measurement data |
| CN107933461B (zh) * | 2017-11-17 | 2020-07-10 | 重庆长安汽车股份有限公司 | 基于单摄像头的车内识别融合装置及方法 |
| CN111886858B (zh) * | 2018-03-15 | 2022-06-21 | 株式会社小糸制作所 | 车辆用影像系统 |
| JP7073991B2 (ja) * | 2018-09-05 | 2022-05-24 | トヨタ自動車株式会社 | 車両用周辺表示装置 |
| EP3937066B1 (en) * | 2020-07-07 | 2025-10-29 | KNORR-BREMSE Systeme für Nutzfahrzeuge GmbH | Peer vehicle center line determination system and method |
| CN115871599A (zh) * | 2021-09-27 | 2023-03-31 | 本田技研工业株式会社 | 车辆控制装置以及车辆控制方法 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06235635A (ja) * | 1993-02-08 | 1994-08-23 | Daihatsu Motor Co Ltd | 距離検出方法 |
| JPH06333049A (ja) * | 1993-05-27 | 1994-12-02 | Nec Corp | 移動車の環境認識方法および装置 |
| JPH0778258A (ja) * | 1993-09-08 | 1995-03-20 | Sumitomo Electric Ind Ltd | 物体認識装置 |
| JP2002358595A (ja) * | 2001-06-01 | 2002-12-13 | Mitsubishi Electric Corp | 道路交通流計測装置および道路交通流計測方法 |
| JP2005092857A (ja) * | 2003-08-11 | 2005-04-07 | Hitachi Ltd | 画像処理システム及び車両制御システム |
| JP2006285549A (ja) * | 2005-03-31 | 2006-10-19 | Matsushita Electric Ind Co Ltd | 画像処理式車両検出装置及び画像処理式車両検出方法 |
| JP3839329B2 (ja) | 2002-02-04 | 2006-11-01 | 本田技研工業株式会社 | ナイトビジョンシステム |
| JP2009230530A (ja) * | 2008-03-24 | 2009-10-08 | Honda Motor Co Ltd | 車両認識装置、車両、及び車両認識用プログラム |
| JP2009265882A (ja) * | 2008-04-24 | 2009-11-12 | Honda Motor Co Ltd | 車両周辺監視装置 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5638116A (en) | 1993-09-08 | 1997-06-10 | Sumitomo Electric Industries, Ltd. | Object recognition apparatus and method |
| AU2003225228A1 (en) * | 2002-05-03 | 2003-11-17 | Donnelly Corporation | Object detection system for vehicle |
| US7483549B2 (en) * | 2004-11-30 | 2009-01-27 | Honda Motor Co., Ltd. | Vehicle surroundings monitoring apparatus |
| JP4094604B2 (ja) * | 2004-11-30 | 2008-06-04 | 本田技研工業株式会社 | 車両周辺監視装置 |
| CN101450647A (zh) * | 2008-12-29 | 2009-06-10 | 广东铁将军防盗设备有限公司 | 车辆避障告警方法 |
-
2010
- 2010-12-16 EP EP10843162.8A patent/EP2482268A4/en not_active Ceased
- 2010-12-16 CN CN201080061317.6A patent/CN102713988B/zh active Active
- 2010-12-16 WO PCT/JP2010/072647 patent/WO2011086807A1/ja not_active Ceased
- 2010-12-16 US US13/515,618 patent/US8994824B2/en active Active
- 2010-12-16 JP JP2011549886A patent/JP5480917B2/ja not_active Expired - Fee Related
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06235635A (ja) * | 1993-02-08 | 1994-08-23 | Daihatsu Motor Co Ltd | 距離検出方法 |
| JPH06333049A (ja) * | 1993-05-27 | 1994-12-02 | Nec Corp | 移動車の環境認識方法および装置 |
| JPH0778258A (ja) * | 1993-09-08 | 1995-03-20 | Sumitomo Electric Ind Ltd | 物体認識装置 |
| JP2002358595A (ja) * | 2001-06-01 | 2002-12-13 | Mitsubishi Electric Corp | 道路交通流計測装置および道路交通流計測方法 |
| JP3839329B2 (ja) | 2002-02-04 | 2006-11-01 | 本田技研工業株式会社 | ナイトビジョンシステム |
| JP2005092857A (ja) * | 2003-08-11 | 2005-04-07 | Hitachi Ltd | 画像処理システム及び車両制御システム |
| JP2006285549A (ja) * | 2005-03-31 | 2006-10-19 | Matsushita Electric Ind Co Ltd | 画像処理式車両検出装置及び画像処理式車両検出方法 |
| JP2009230530A (ja) * | 2008-03-24 | 2009-10-08 | Honda Motor Co Ltd | 車両認識装置、車両、及び車両認識用プログラム |
| JP2009265882A (ja) * | 2008-04-24 | 2009-11-12 | Honda Motor Co Ltd | 車両周辺監視装置 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP2482268A4 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013186902A (ja) * | 2012-03-07 | 2013-09-19 | Ricoh Co Ltd | 車輌検知方法及び装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| US8994824B2 (en) | 2015-03-31 |
| CN102713988B (zh) | 2015-02-25 |
| EP2482268A1 (en) | 2012-08-01 |
| EP2482268A4 (en) | 2013-09-04 |
| US20120300076A1 (en) | 2012-11-29 |
| JP5480917B2 (ja) | 2014-04-23 |
| CN102713988A (zh) | 2012-10-03 |
| JPWO2011086807A1 (ja) | 2013-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5480917B2 (ja) | 車両周辺監視装置 | |
| JP6197291B2 (ja) | 複眼カメラ装置、及びそれを備えた車両 | |
| CN107392103B (zh) | 路面车道线的检测方法及装置、电子设备 | |
| JP5529910B2 (ja) | 車両周辺監視装置 | |
| US8005266B2 (en) | Vehicle surroundings monitoring apparatus | |
| CN104251993B (zh) | 车辆周围监测装置 | |
| JP5774770B2 (ja) | 車両周辺監視装置 | |
| JP4815488B2 (ja) | 車両周辺監視装置 | |
| JP4733756B2 (ja) | 車両周辺監視装置 | |
| US9965690B2 (en) | On-vehicle control device | |
| JP2017505946A (ja) | 車両検出システムおよびその方法 | |
| JP2007193445A (ja) | 車両の周辺監視装置 | |
| US20180075749A1 (en) | Forward collision warning system and method | |
| JP4887537B2 (ja) | 車両周辺監視装置 | |
| JP2014146267A (ja) | 歩行者検出装置、運転支援装置 | |
| JP5083164B2 (ja) | 画像処理装置及び画像処理方法 | |
| JP4864953B2 (ja) | 車両周辺監視装置 | |
| JP2007323578A (ja) | 車両周辺監視装置 | |
| JP4627305B2 (ja) | 車両周辺監視装置、車両周辺監視方法、及び車両周辺監視用プログラム | |
| JP6087240B2 (ja) | 車両周辺監視装置 | |
| JP2004348645A (ja) | 赤外線画像認識装置、及び赤外線画像認識装置を用いた警報装置 | |
| JP2013092863A (ja) | 車両周辺監視装置 | |
| JP5399887B2 (ja) | 車両周辺監視装置 | |
| JP4975776B2 (ja) | 車両周辺監視装置 | |
| WO2019013253A1 (ja) | 検出装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WWE | Wipo information: entry into national phase |
Ref document number: 201080061317.6 Country of ref document: CN |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10843162 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2011549886 Country of ref document: JP |
|
| REEP | Request for entry into the european phase |
Ref document number: 2010843162 Country of ref document: EP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2010843162 Country of ref document: EP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 13515618 Country of ref document: US |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |