WO2019171565A1 - 線検出装置、線検出方法、プログラム、及び記憶媒体 - Google Patents
線検出装置、線検出方法、プログラム、及び記憶媒体 Download PDFInfo
- Publication number
- WO2019171565A1 WO2019171565A1 PCT/JP2018/009162 JP2018009162W WO2019171565A1 WO 2019171565 A1 WO2019171565 A1 WO 2019171565A1 JP 2018009162 W JP2018009162 W JP 2018009162W WO 2019171565 A1 WO2019171565 A1 WO 2019171565A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- line
- image
- color
- line detection
- unit
- 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Definitions
- the present invention relates to a line detection device, a line detection method, a program, and a storage medium for detecting a line drawn on a traveling road.
- An example of a problem to be solved by the present invention is to accurately detect a line of a specific color from an image including a travel path.
- a pixel whose color is located in a predetermined range is extracted from an image including a traveling path on which the moving body travels, and the distribution of the extracted pixel in the image is used to extract the pixel.
- a first processing unit for detecting a first color line included in the image After the first processing unit executes the process, the pixels whose luminance is located in a predetermined luminance range are extracted from the image, and are included in the image using the distribution of the extracted pixels in the image.
- a second processing unit that identifies a second color line that is different from the first color; Is a line detection apparatus.
- the invention according to claim 7 is a computer, By processing an image including a travel path on which the mobile object travels, a first color line included in the image is detected, After performing the first color line detection process, the pixel is extracted from the image, the luminance is located in a predetermined luminance range, and the extracted pixel distribution in the image is used to extract the image. Is a line detection method for specifying a second color line different from the first color.
- the invention according to claim 8 is provided in a computer.
- the invention according to claim 9 is a storage medium storing a computer-executable program, The program is stored in a computer.
- FIG. 1 is a diagram illustrating a functional configuration of the line detection apparatus 10 according to the first embodiment.
- FIG. 2 is a diagram illustrating the moving body 40 on which the line detection device 10 is mounted.
- the line detection device 10 is a device that detects a line drawn on a travel path on which the moving body 40 travels, and includes a dividing unit 120, an estimated information generation unit 160, and a specific processing unit 180 (first specific processing unit). ing.
- the dividing unit 120 divides an image including a travel path on which the mobile body travels (hereinafter referred to as a processed image) along a first direction including a component in a direction in which the travel path extends, thereby obtaining a plurality of first images. One divided image is generated.
- the estimation information generation unit 160 performs a process of selecting the first candidate pixel for each of the plurality of first divided images.
- the first candidate pixel is a pixel estimated to be a part of the first line drawn on the travel path.
- the identification processing unit 180 identifies the first line included in the processed image based on the positions of the plurality of first candidate pixels in the processed image.
- the 1st detection part 100 outputs the information (1st line information) which shows the specified 1st line.
- the line detection apparatus 10 includes a distribution information generation unit 140.
- the line detection apparatus 10 can also be regarded as including a distribution information generation unit 140, an estimation information generation unit 160, and a specific processing unit 180.
- the distribution information generation unit 140 generates first distribution information indicating the distribution of pixels that satisfy the criterion from the processed image.
- the estimation information generation unit 160 selects the first candidate pixel using the first distribution information.
- the identification processing unit 180 identifies the first line included in the processed image based on the position of the first candidate pixel in the image.
- the moving body 40 is a vehicle such as an automobile or a motorcycle.
- an example of the travel path is a road, and the first line and the second line described later are lines that define a lane.
- the moving body 40 may be an airplane.
- the runway is a runway.
- the moving body 40 includes an imaging device 20 and a control device 30.
- the imaging device 20 captures the front of the moving body 40 to generate a moving image including the travel path.
- a plurality of frame images constituting this moving image are output to the line detection device 10.
- the line detection device 10 detects a first line included in the travel path for each frame image, and generates first line information indicating the detected first line.
- the first line information includes the position of the first line and the color of the first line.
- the process of generating the first line information is performed for each of the plurality of frame images. However, the process of generating the first line information may be performed only for a part of the frame images constituting the moving image.
- the first line information is output to the control device 30.
- the control device 30 is a device that controls the movement of the moving body 40.
- the control device 30 is a control device for automatic driving.
- the level of automatic operation performed by the control device 30 is, for example, level 3 or higher, but is not limited thereto.
- the control device 30 uses the first line information when controlling the movement of the moving body 40. Note that the control device 30 may generate information necessary for controlling the movement of the moving body 40 instead of directly controlling the movement of the moving body 40. Even in this case, the control device 30 generates necessary information using the first line information.
- the information generated here is, for example, information for notifying (for example, displaying) whether or not the lane can be changed, information for notifying (for example, displaying) the necessity of suspension.
- This information is displayed on, for example, a display device (for example, a display of a navigation device in the vehicle) that can be viewed by the operator of the moving body 40.
- the line detection apparatus 10 includes a dividing unit 120, a distribution information generating unit 140, an estimated information generating unit 160, and a specific processing unit 180. Details of processing performed by these will be described later with reference to flowcharts.
- the line detection device 10 is mounted on the moving body 40.
- the line detection device 10 may be located outside the moving body 40.
- the line detection device 10 is connected to the imaging device 20 and the control device 30 via a wireless communication line.
- the control device 30 may be located outside the moving body 40 or may be detachably attached to the moving body 40.
- the moving body is obtained by acquiring a moving image from the imaging device 20 and analyzing a frame image constituting the moving image. It is also possible to specify a line (for example, a division line) drawn on the travel path on which 40 has traveled and update the map information using information for specifying the specified line. In this case, map information can be easily prepared.
- FIG. 3 is a diagram illustrating an example of a hardware configuration of the line detection device 10.
- the main configuration of the line detection apparatus 10 is realized using an integrated circuit.
- This integrated circuit includes a bus 402, a processor 404, a memory 406, a storage device 408, an input / output interface 410, and a network interface 412.
- the bus 402 is a data transmission path through which the processor 404, the memory 406, the storage device 408, the input / output interface 410, and the network interface 412 transmit / receive data to / from each other.
- the method of connecting the processors 404 and the like is not limited to bus connection.
- the processor 404 is an arithmetic processing unit realized using a microprocessor or the like.
- the memory 406 is a memory realized using a RAM (Random Access Memory) or the like.
- the storage device 408 is a storage device realized by using a ROM (Read Only Memory), a flash memory, or the like.
- the input / output interface 410 is an interface for connecting the line detection apparatus 10 to a peripheral device.
- the imaging device 20 and the control device 30 are connected to the input / output interface 410.
- the network interface 412 is an interface for connecting the line detection device 10 to a communication network.
- This communication network is, for example, a CAN (Controller Area Network) communication network.
- a method of connecting the network interface 412 to the communication network may be a wireless connection or a wired connection.
- the storage device 408 stores a program module for realizing each functional element of the line detection apparatus 10.
- the processor 404 implements each function of the line detection device 10 by reading this program module into the memory 406 and executing it.
- the hardware configuration of the integrated circuit described above is not limited to the configuration shown in the figure.
- the program module may be stored in the memory 406.
- the integrated circuit may not include the storage device 408.
- FIG. 4 is a flowchart showing processing performed by the line detection apparatus 10. 5 to 7 are diagrams for explaining the processing shown in FIG. First, when the imaging device 20 generates a frame image that forms a moving image, the line detection device 10 acquires the frame image as a processed image 50. The line detection apparatus 10 performs the process shown in FIG. 4 every time a frame image is acquired.
- the dividing unit 120 of the line detection device 10 generates a plurality of divided images 52 (first divided images) by dividing the processed image 50 along the first direction ( Step S20 in FIG.
- the number of divided images 52 generated from one processed image 50 is, for example, 10 or more and 30 or less, but is not limited thereto.
- the imaging device 20 is photographing the front of the moving body 40
- the y-axis direction includes a component in the direction in which the travel path (for example, a road) extends.
- the dividing unit 120 generates the divided image 52 by dividing the processed image 50 in the y-axis direction. In this case, the load necessary for the process of generating the divided image 52 is reduced.
- the distribution information generation unit 140 performs processing for generating first distribution information indicating the distribution of pixels satisfying the criterion for each of the divided images 52 (step S40 in FIG. 4).
- the standard used here is, for example, having a color belonging to a predetermined range in the color space.
- the above-mentioned “predetermined range” is a range recognized as yellow.
- the distribution information generation unit 140 converts pixels belonging to a predetermined range to 1 and other pixels to 0 (binarization processing).
- the first distribution information is information indicating the pixel distribution in the second direction intersecting with the first direction. For example, as shown in FIG.
- the first distribution information is information indicating the distribution of the number of pixels satisfying the criterion in the second direction, as shown in FIGS. 6A and 6B, for example.
- the estimated information generation unit 160 uses the first distribution information generated by the distribution information generation unit 140 to estimate a pixel (hereinafter referred to as a first line) estimated as a part of the first line drawn on the travel path.
- a process of selecting a pixel is described (step S60 in FIG. 4). This process is performed for each of the divided images 52. For example, when the distribution information indicates a distribution of the number of pixels satisfying the criterion in the second direction as illustrated in FIG. 6, the estimation information generation unit 160 calculates at least one of the standard deviation and the variance in the first distribution information. To select the first image.
- the estimation information generation unit 160 selects all the first candidate pixels as the first pixels. In this case, the estimated information generation unit 160 determines that the first line is included in the divided image 52. For example, in the case shown in FIG. 6A, since the standard deviation and variance are small, all of the first candidate pixels are selected as the first pixels. On the other hand, when the standard deviation and variance are large as shown in FIG. 6B, the first pixel is not selected from the first candidate pixels.
- the estimation information generation unit 160 may select a part of the first candidate pixel as the first pixel. In this case, as illustrated in FIG. 6A, the estimation information generation unit 160 selects, for example, a pixel included in an area where the number of pixels is equal to or greater than a reference value in the first distribution information as the first pixel.
- the specific processing unit 180 uses the position of the first pixel selected by the estimation information generation unit 160 in the processed image 50 (or the position in the divided image 52) of the first line included in the processed image 50.
- the position is estimated (step S80 in FIG. 4).
- the specific processing unit 180 estimates the average value of the positions of the first pixels in the first direction as the position of the first line in the divided image 52.
- the first line included in the processed image 50 is estimated by connecting the positions of the first lines in the plurality of divided images 52 or performing regression analysis.
- the mode value or the median value may be used instead of the average value of the positions of the first pixels in the first direction.
- FIG. 7 is an example of step S80 of FIG. 4 and is a diagram for explaining a case where the specific processing unit 180 estimates the first line using regression analysis.
- a regression line is used.
- FIG. 7A is a diagram in which the estimated position of the first line is plotted. And the specific process part 180 produces
- FIG. 7B is an example in which the first line estimated in the processed image 50 is applied. In this case, for example, the estimated first line is present in the lower part of the processed image 50 (where the plot in FIG. 7A exists) and extends to the upper end of the upper part of the processed image 50. It shows that.
- the specific processing unit 180 selects a pixel that overlaps the regression line among the first pixels, and a pixel that is continuous with the pixel as a pixel that forms the first line. You may specify. In other words, the specification processing unit 180 may specify, in each of the divided images 52, a block that overlaps the regression line among the blocks of the first pixel as a pixel constituting the first line.
- the distribution information generation unit 140 can select pixels that satisfy a predetermined luminance standard and generate distribution information (hereinafter referred to as second distribution information) of the selected pixels.
- This criterion may be, for example, not less than the lower limit value, less than the upper limit value, or not less than the lower limit value and not more than the upper limit value.
- the line detection device 10 can detect a white line.
- the processing performed by the dividing unit 120, the estimated information generating unit 160, and the specific processing unit 180 does not include edge detection processing. For this reason, the amount of calculation required when specifying the first line is reduced. Therefore, an arithmetic device having a high calculation speed is not required, and as a result, the manufacturing cost of the line detection device 10 is reduced.
- the distribution information generation unit 140 of the line detection device 10 generates first distribution information.
- the estimation information generation unit 160 selects a first pixel (that is, a pixel estimated to constitute the first line) using the first distribution information. For this reason, the amount of calculation performed by the estimated information generation unit 160, that is, the amount of calculation when selecting a pixel estimated to form the first line is reduced.
- the line detection apparatus 10 is the same as the line detection apparatus 10 shown in the first embodiment except for the processing performed by the dividing unit 120.
- FIG. 8 is a diagram for explaining processing performed by the dividing unit 120 in the present embodiment.
- the line detection apparatus 10 does not set the entire processed image 50 as a generation target of the divided image 52, but sets only a part 54 of the processed image 50 as a generation target of the divided image 52.
- the line detection apparatus 10 extracts a part 54 of the processed image 50 and divides the part 54 to generate a divided image 52.
- the amount of calculation performed by the line detection device 10 is Even less.
- the position of the part 54 in the processed image 50 is set in advance. For example, when the imaging device 20 is mounted on the moving body 40, there is a high possibility that the road is reflected below the processed image 50. For this reason, it is preferable that the part 54 is set below the moving body 40.
- FIG. 9 is a diagram illustrating a functional configuration of the line detection apparatus 10 according to the third embodiment.
- the line detection apparatus 10 according to the present embodiment has the same configuration as the line detection apparatus 10 according to the first or second embodiment, except that the data conversion unit 110 is provided.
- the processed image 50 generated by the imaging device 20 is an image represented in an RGB color space.
- the data conversion unit 110 converts the processed image 50 into an image shown in a color space defined by indices of hue, brightness (luminance), and saturation, for example, an image shown in the HLS color space (post-conversion image). Convert. Note that an HSV color space or a Lab color space may be used instead of the HLS color space.
- the dividing unit 120, the distribution information generating unit 140, the estimated information generating unit 160, and the specific processing unit 180 perform processing using the processed image 50 after the conversion.
- the distribution information generation unit 140 may be easy to process (easily perform binarization processing).
- the line detection apparatus 10 can detect the first line with higher accuracy than in the case of directly processing the processed image 50 shown in the RGB color space. . This tendency becomes remarkable when the first line is a yellow line.
- the data conversion unit 110 may perform the above-described data conversion process on the divided image 52 instead of the processed image 50.
- FIG. 11 is a diagram illustrating a configuration of the line detection apparatus 10 according to the fourth embodiment.
- the line detection apparatus 10 according to the present embodiment is the same as any of the line detection apparatuses 10 according to the first to third embodiments, except that the line setting apparatus 130 includes an area setting unit 130.
- FIG. 11 shows a case similar to that of the third embodiment.
- the area setting unit 130 processes a frame image (hereinafter referred to as a second frame image) processed after (for example, the next) after the first frame image.
- a frame image the region to be processed by the distribution information generation unit 140 is narrowed.
- the region setting unit 130 determines the distribution information generation unit 140 based on the position of the first line detected in the first frame image in the second direction (for example, the position in the x-axis direction in FIG. 7). Narrow the area to be processed.
- the region setting unit 130 causes the position of the first line in the second direction in the first frame image to be the center of the region to be processed.
- the region setting unit 130 narrows the width of the region to be processed.
- the area setting unit 130 performs the above-described processing on the divided image 52, for example.
- FIG. 12 is a diagram for schematically explaining the processing performed by the region setting unit 130.
- FIG. 12A when the specific processing unit 180 specifies the first line L1 in the first frame image (processed image 50a), the area setting unit 130 indicates information indicating the position of the line L1. (For example, information indicating a line obtained by regression analysis) is acquired from the specific processing unit 180. Then, as illustrated in FIG. 12B, the region setting unit 130 sets a region 56 to be processed by the distribution information generation unit 140 for the second frame image (processed image 50b).
- the identification processing unit 180 can identify the first line L1 also for the second frame image (processed image 50b), the third frame after the second frame image (processed image 50b).
- the area 56 in the image (processed image 50c) is made narrower than the area 56 in the second frame image (processed image 50b).
- the region 56 gradually becomes narrower, but this size (for example, width) has a lower limit. That is, the region setting unit 130 prevents the size (for example, width) of the region 56 from falling below the lower limit.
- the lower limit used here is preferably set to be larger than the width corresponding to the standard value of the standard deviation as a criterion for determining whether or not the divided image 52 includes a part of the line.
- the area setting unit 130 sets the area 56 in the subsequent (for example, the next) frame image. Widen or cancel the setting of the area 56.
- the region setting unit 130 performs the setting of the region 56 described above on the processed image 50 before the dividing unit 120 processes (the processed image 50 after the data converting unit 110 returns). Alternatively, the first distribution information generated by the distribution information generation unit 140 may be performed.
- the region setting unit 130 narrows the region 56 to be processed by the distribution information generation unit 140. At this time, the region setting unit 130 sets the region 56 based on the position of the first line L1 in the processed frame image. For this reason, the calculation amount of the line detection device 10 can be reduced while maintaining the detection accuracy of the line L1. Note that by narrowing the region 56 as a processing target of the distribution information generation unit 140, it is possible to suppress the influence of noise that is unnecessary for the detection of the line L1. For example, examples of noise include characters drawn with a yellow line on a road different from the line L1, display objects drawn with a yellow line, and the like.
- FIG. 13 is a diagram illustrating a functional configuration of the line detection apparatus 10 according to the fifth embodiment.
- the line detection apparatus 10 according to the present embodiment includes a second detection unit 200 in addition to the first detection unit 100.
- the first detection unit 100 is the same as any one of the above-described embodiments.
- the second detection unit 200 detects a line drawn on the travel path using the luminance of the pixels constituting the processed image 50. Specifically, the second detection unit 200 selects a pixel whose luminance satisfies a criterion from the processed image 50, and detects a line (second line) using the selected pixel.
- a line second line
- An example of this process is a binarization process.
- the second detection unit 200 may detect the first line detected by the first detection unit 100 together with other lines. For example, when the first detection unit 100 is intended to detect a yellow line and the second detection unit 200 is intended to detect a white line, the second detection unit 200 can detect the yellow line as well as the white line. There is sex. Therefore, in the present embodiment, the second detection unit 200 sets a luminance reference using the luminance of the pixels constituting the first line detected by the first detection unit 100.
- the above-described luminance reference is a lower limit value. That is, the second detection unit 200 selects a pixel having a luminance equal to or higher than the reference value. Conversely, the second detection unit 200 may select a pixel having a luminance equal to or lower than the reference value. In this case, the second detection unit 200 can indirectly detect the target line by selecting a pixel that forms a region other than the target line. Then, the second detection unit 200 sets the above lower limit value based on a value obtained by statistically processing the luminance of the pixels constituting the first line detected by the first detection unit 100.
- the statistically processed values include an average value and a mode value.
- the second detection unit 200 sets, for example, a value obtained by adding a constant to the statistically processed value as the lower limit value.
- the second detection unit 200 excludes the pixels constituting the first line specified by the first detection unit 100 from the processed image 50, and selects a pixel whose luminance is higher than the reference value from the excluded image. Thus, a white line may be detected.
- the lower limit value in this case is, for example, a fixed value, and a value higher than a general road surface luminance value is used.
- FIG. 14 is a diagram illustrating an example of a functional configuration of the second detection unit 200.
- the second detection unit 200 includes a dividing unit 220, a distribution information generation unit 240, an estimation information generation unit 260, and a specific processing unit 280 (second specific processing unit, third specific processing unit, or white line).
- the processing performed by the dividing unit 220 is the same as the processing performed by the dividing unit 120, and the processing performed by the distribution information generating unit 240, the estimated information generating unit 260, and the specifying processing unit 280 is the pixel selection criterion being luminance.
- the processing is the same as the processing performed by the distribution information generation unit 140, the estimation information generation unit 160, and the specific processing unit 280, respectively.
- the 1st detection part 100 can also serve as the function of the 2nd detection part 200.
- the second detection unit 200 may have a data conversion unit 110 before the division unit 220.
- the distribution information generation unit 240 selects a pixel whose luminance satisfies a predetermined criterion, and generates distribution information (second distribution information) of the selected pixel. As described above, the distribution information generation unit 240 sets the reference used in this processing using the luminance of the pixels forming the first line detected by the first detection unit 100.
- the distribution information generation unit 240 may exclude the pixels detected by the first detection unit 100 from the divided image 52 and generate the second distribution information using the divided image 52 after the exclusion.
- FIG. 15 is a flowchart illustrating an example of processing performed by the line detection apparatus 10 according to the present embodiment.
- the line detection apparatus 10 performs the process shown in this figure for each of the plurality of frame images.
- the first detection unit 100 performs a first line (first color line) detection process.
- the second detection unit 200 receives the luminance information of the first line from the first detection unit 100, and then performs the detection process of the second line (second color line).
- the luminance of the first line is lower than the luminance of the second line.
- the second detection unit 200 When the second detection unit 200 performs the process before the first detection unit 100 performs the process, that is, when the second line is detected before the first line, the second detection unit 200 performs the second process. There is a possibility that the first line is detected together with the second line because the luminance standard used when detecting the second line is too low. On the other hand, in the present embodiment, the second detection unit 200 performs the processing after the first detection unit 100 performs the processing. For this reason, the possibility of detecting the first line together with the second line is reduced. For example, as described above, when the second detection unit 200 performs processing, by excluding pixels that form the first line (yellow line) detected by the first detection unit 100, the second detection unit 200 Only the white line can be detected.
- the details of the first line detection process are as described in any of the above embodiments.
- the details of the second line detection process are as described above.
- the distribution information generation unit 240 of the second detection unit 200 performs a second distribution information generation process using a predetermined luminance reference.
- the second detection unit 200 may perform the second line detection process on the entire processed image 50, or perform the second line detection process only on a part of the processed image 50. May be. In the latter case, the second detection unit 200 may determine a region where the second line detection process is performed based on the position of the first line. In this way, the amount of calculation processing performed by the second detection unit 200 is reduced.
- FIG. 16 is a diagram for explaining an example of a region to be processed by the second detection unit 200.
- a second line L2 for example, a white line
- the first line L1 for example, a yellow line
- the second detection unit 200 determines a range to be processed on the basis of the first line L1 in the direction intersecting the first line L1, and detects the second line L2 located in the range. To do.
- the second detection unit 200 takes the first width W1 in the + direction as the center of the first line L1, and sets the second width W2 in the ⁇ direction. Take.
- This range is set as a region 58.
- the first width W1 and the second width W2 may be equal to each other or different from each other.
- the width of the region 58 may be changed along the direction in which the line L1 extends. For example, when the width of the region included in the processed image 50 becomes narrower as it goes to the upper side of the processed image 50, the width of the region 58 may become narrower as it goes to the upper side of the processed image 50.
- the first line can be detected with high accuracy
- the second line can also be detected with high accuracy
- FIG. 17 is a diagram illustrating a functional configuration of the line detection apparatus 10 according to the sixth embodiment.
- the line detection apparatus 10 according to the present embodiment has the same configuration as that of the line detection apparatus 10 according to the fifth embodiment, except that the determination unit 300 is provided.
- the first detection unit 100 detects the first line included in the processed image 50
- the second detection unit 200 detects the second line included in the processed image 50.
- the processed image 50 is each of the frame images constituting the moving image.
- the determination unit 300 calculates the detection cycle of the first line using the processing result of the first detection unit 100 for each of the frame images, and determines whether or not the first line is a dotted line. The determination unit 300 performs the same process for the second line.
- the determination unit 300 identifies the first line included in the frame image each time the first detection unit 100 processes the frame image (processed image 50). Then, the determination unit 300 determines the detection cycle of the first line by processing the transition between the frame images of the specific result.
- the determination unit 300 calculates the number of divided images 52 that are determined to include the first line. Then, the determination unit 300 determines whether or not the first line is a dotted line using the transition of the number of the divided images 52, as shown in each drawing of FIG. Specifically, the determination unit 300 determines that the first line is a dotted line when the increase / decrease in the number of the divided images 52 is repeated at a constant cycle.
- the determination unit 300 determines that the number of calculated divided images 52 is equal to or greater than a reference number (for example, 70% or more of the number of divided images 52 included in one frame image). In the case where the first line continues, it is determined that the first line is a continuous line. In addition, when the increase / decrease in the number of the divided images 52 is irregularly repeated, the determination unit 300 determines that the first line is a continuous line but is partially lost (or blurred).
- a reference number for example, 70% or more of the number of divided images 52 included in one frame image.
- FIG. 18A shows the result of plotting the number of the divided images 52 for each frame image
- FIG. 18B shows the number of the divided images 52 in a plurality of continuous ( For example, the result of plotting the transition of the average value in five frame images is shown.
- the increase / decrease in the number of the divided images 52 is repeated at a constant cycle, it can be a target of processing by the determination unit 300.
- FIG. 18B also shows that the average value of the above-described divided image 52 falls within a certain range.
- the line detection device 10 may acquire information for specifying the speed of the moving body 40 when the imaging device 20 generates the processed image 50.
- the line detection apparatus 10 acquires information indicating the time when the processed image 50 is generated for each processed image 50 and also acquires information indicating the speed of the moving body 40 by time.
- the determination unit 300 can also determine whether or not the first line is a dotted line using this speed.
- the determination unit 300 calculates the length of the first line using the above-described detection period of the first line and the speed of the moving body 40. For example, consider a case where a part 54 is set in the processed image 50 as shown in FIG. The determination unit 300 starts from a frame image in which the number of divided images 52 determined to include the first line is equal to or greater than the reference number to a frame image in which the number of divided images 52 is equal to or less than the reference number. The length of the first line is calculated by multiplying this number by the frame rate and the speed of the moving body 40.
- the determination unit 300 determines a frame in which the number of the divided images 52 is equal to or greater than the reference number from the frame images in which the number of the divided images 52 determined to include the first line is equal to or less than the reference number. The number of images up to the image is counted, and the interval between the first lines is calculated by multiplying this number by the frame rate and the speed of the moving body 40. Then, the determination unit 300 determines that the first line is a dotted line when the calculated variation in the length of the first line and the variation in the interval between the first lines are equal to or less than a certain value. On the other hand, if the calculated variation in the length of the first line is equal to or greater than a certain value, it is determined that the first line is a continuous line but is partially missing (or blurred).
- the determination unit 300 may acquire type information for specifying the type of travel path, and may determine the above-described reference length using the type information.
- This type information is information for specifying, for example, whether the travel route is a general road, a toll road, or a highway. In the case of an expressway, the reference length is longer than that of a general road.
- the above-described type information may be information that directly specifies the road described above, information that indicates the position of the moving body 40 (for example, information that indicates latitude and longitude such as GPS information), and map information. Good.
- the determination result by the determination unit 300 is output to the control device 30 of the moving body 40.
- the control device 30 uses the information indicating whether the determination result, that is, the first line (or the second line) is a continuous line or a dotted line, for example, the movement of the moving body 40 (for example, the change of the travel line). Control).
- a specific example of this determination is determined based on traffic rules, for example.
- the determination unit 300 can accurately determine whether or not the first line and the second line are dotted lines. And since the control apparatus 30 of the moving body 40 controls the movement of the moving body 40 using this determination result, the automatic operation of the moving body 40 can be advanced.
- line detection apparatus 10 may also include the determination unit 300 described above.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
前記第1処理部が処理を実行した後、前記画像から、輝度が予め定められた輝度範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて、前記画像に含まれていて前記第1色とは異なる第2色の線を特定する第2処理部と、
を備える線検出装置である。
移動体が走行する走行路を含む画像を処理することにより、当該画像に含まれる第1色の線を検出し、
前記第1色の線の検出処理を実行した後、前記画像から、輝度が予め定められた輝度範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて、前記画像に含まれていて前記第1色とは異なる第2色の線を特定する、線検出方法である。
移動体が走行する走行路を含む画像を処理することにより、当該画像に含まれる第1色の線を検出する処理と、
前記第1色の線の検出処理を実行した後、前記画像から、輝度が予め定められた輝度範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて、前記画像に含まれていて前記第1色とは異なる第2色の線を特定する処理と、
を実行させるプログラムである。
前記プログラムは、コンピュータに、
移動体が走行する走行路を含む画像を処理することにより、当該画像に含まれる第1色の線を検出する処理と、
前記第1色の線の検出処理を実行した後、前記画像から、輝度が予め定められた輝度範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて、前記画像に含まれていて前記第1色とは異なる第2色の線を特定する処理と、
を実行させる記憶媒体である。
図1は、第1の実施形態に係る線検出装置10の機能構成を示す図である。図2は、線検出装置10が搭載された移動体40を示す図である。線検出装置10は移動体40が走行する走行路に描かれている線を検出する装置であり、分割部120、推定情報生成部160、及び特定処理部180(第1特定処理部)を備えている。分割部120は、移動体が走行する走行路を含む画像(以下、処理画像と記載)を、走行路が延在する方向の成分を含む第1方向に沿って分割することにより、複数の第1の分割画像を生成する。推定情報生成部160は、第1の候補画素を選択する処理を、複数の第1の分割画像のそれぞれに対して実行する。第1の候補画素は、走行路に描かれている第1の線の一部と推定される画素である。特定処理部180は、処理画像における複数の第1の候補画素の位置に基づいて、処理画像に含まれる第1の線を特定する。そして第1検出部100は、特定した第1の線を示す情報(第1の線情報)を出力する。
本実施形態に係る線検出装置10は、分割部120が行う処理を除いて、第1の実施形態に示した線検出装置10と同様である。
図9は、第3の実施形態に係る線検出装置10の機能構成を示す図である。本実施形態に係る線検出装置10は、データ変換部110を備えている点を除いて、第1又は第2の実施形態に係る線検出装置10と同様の構成である。
図11は、第4の実施形態に係る線検出装置10の構成を示す図である。本実施形態に係る線検出装置10は、領域設定部130を有している点を除いて、第1~第3の実施形態に係る線検出装置10のいずれかと同様である。図11は、第3の実施形態と同様の場合を示している。
図13は、第5の実施形態に係る線検出装置10の機能構成を示す図である。本実施形態に係る線検出装置10は、第1検出部100の他に第2検出部200を備えている。第1検出部100は、上記したいずれかの実施形態と同様である。
図17は、第6の実施形態に係る線検出装置10の機能構成を示す図である。本実施形態に係る線検出装置10は、判断部300を備えている点を除いて、第5の実施形態に係る線検出装置10と同様の構成である。
Claims (9)
- 移動体が走行する走行路を含む画像から、色が予め定められた範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて前記画像に含まれる第1色の線を検出する第1処理部と、
前記第1処理部が処理を実行した後、前記画像から、輝度が予め定められた輝度範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて、前記画像に含まれていて前記第1色とは異なる第2色の線を特定する第2処理部と、
を備える線検出装置。 - 請求項1に記載の線検出装置において、
前記第2処理部は、前記予め定められた輝度範囲を、前記検出された第1色の線の輝度を用いて定める、線検出装置。 - 請求項1に記載の線検出装置において、
前記第1色は黄色であり、前記第2色は白色である、線検出装置。 - 請求項1~3のいずれか一項に記載の線検出装置において、
前記第2処理部は、前記第1処理部が前記第1色の線を検出できなかった時に、前記第2色の線を特定する線検出装置。 - 請求項1~4のいずれか一項に記載の線検出装置において、
前記画像は、前記移動体に搭載された撮像装置によって撮像されている、線検出装置。 - 請求項5に記載の線検出装置において、
前記画像は前記移動体の前方を撮像した画像である、線検出装置。 - コンピュータが、
移動体が走行する走行路を含む画像を処理することにより、当該画像に含まれる第1色の線を検出し、
前記第1色の線の検出処理を実行した後、前記画像から、輝度が予め定められた輝度範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて、前記画像に含まれていて前記第1色とは異なる第2色の線を特定する、線検出方法。 - コンピュータに、
移動体が走行する走行路を含む画像を処理することにより、当該画像に含まれる第1色の線を検出する処理と、
前記第1色の線の検出処理を実行した後、前記画像から、輝度が予め定められた輝度範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて、前記画像に含まれていて前記第1色とは異なる第2色の線を特定する処理と、
を実行させるプログラム。 - コンピュータが実行可能なプログラムを記憶した記憶媒体であって、
前記プログラムは、コンピュータに、
移動体が走行する走行路を含む画像を処理することにより、当該画像に含まれる第1色の線を検出する処理と、
前記第1色の線の検出処理を実行した後、前記画像から、輝度が予め定められた輝度範囲に位置する画素を抽出し、前記画像内における前記抽出した画素の分布を用いて、前記画像に含まれていて前記第1色とは異なる第2色の線を特定する処理と、
を実行させる記憶媒体。
Priority Applications (6)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2018/009162 WO2019171565A1 (ja) | 2018-03-09 | 2018-03-09 | 線検出装置、線検出方法、プログラム、及び記憶媒体 |
| US16/979,498 US11348344B2 (en) | 2018-03-09 | 2018-03-09 | Line detection device, line detection method, program, and storage medium |
| JP2020504610A JPWO2019171565A1 (ja) | 2018-03-09 | 2018-03-09 | 線検出装置、線検出方法、プログラム、及び記憶媒体 |
| EP18908694.5A EP3764321B1 (en) | 2018-03-09 | 2018-03-09 | Line detection device, line detection method, program, and storage medium |
| JP2022097161A JP2022126747A (ja) | 2018-03-09 | 2022-06-16 | 線検出装置、線検出方法、プログラム、及び記憶媒体 |
| JP2024071440A JP2024091918A (ja) | 2018-03-09 | 2024-04-25 | 線検出装置、線検出方法、プログラム、及び記憶媒体 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2018/009162 WO2019171565A1 (ja) | 2018-03-09 | 2018-03-09 | 線検出装置、線検出方法、プログラム、及び記憶媒体 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019171565A1 true WO2019171565A1 (ja) | 2019-09-12 |
Family
ID=67845641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2018/009162 Ceased WO2019171565A1 (ja) | 2018-03-09 | 2018-03-09 | 線検出装置、線検出方法、プログラム、及び記憶媒体 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US11348344B2 (ja) |
| EP (1) | EP3764321B1 (ja) |
| JP (3) | JPWO2019171565A1 (ja) |
| WO (1) | WO2019171565A1 (ja) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006209209A (ja) * | 2005-01-25 | 2006-08-10 | Honda Elesys Co Ltd | レーンマーク抽出装置 |
| JP2007018154A (ja) * | 2005-07-06 | 2007-01-25 | Honda Motor Co Ltd | 車両及びレーンマーク認識装置 |
| JP2014164492A (ja) | 2013-02-25 | 2014-09-08 | Denso Corp | 区画線認識装置 |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4365350B2 (ja) * | 2005-06-27 | 2009-11-18 | 本田技研工業株式会社 | 車両及び車線認識装置 |
| CN101978392B (zh) * | 2008-03-26 | 2013-01-16 | 本田技研工业株式会社 | 车辆用图像处理装置 |
| JP5083658B2 (ja) * | 2008-03-26 | 2012-11-28 | 本田技研工業株式会社 | 車両用車線認識装置、車両、及び車両用車線認識プログラム |
| US8670592B2 (en) * | 2008-04-24 | 2014-03-11 | GM Global Technology Operations LLC | Clear path detection using segmentation-based method |
| JP5664152B2 (ja) * | 2009-12-25 | 2015-02-04 | 株式会社リコー | 撮像装置、車載用撮像システム及び物体識別装置 |
| JP2012155612A (ja) * | 2011-01-27 | 2012-08-16 | Denso Corp | 車線検出装置 |
| JP6141787B2 (ja) * | 2014-04-01 | 2017-06-07 | 本田技研工業株式会社 | レーンマーク認識装置 |
| JP6220327B2 (ja) * | 2014-07-23 | 2017-10-25 | 株式会社Soken | 走行区画線認識装置、走行区画線認識プログラム |
| JP6702849B2 (ja) * | 2016-12-22 | 2020-06-03 | 株式会社Soken | 区画線認識装置 |
-
2018
- 2018-03-09 US US16/979,498 patent/US11348344B2/en active Active
- 2018-03-09 WO PCT/JP2018/009162 patent/WO2019171565A1/ja not_active Ceased
- 2018-03-09 JP JP2020504610A patent/JPWO2019171565A1/ja not_active Ceased
- 2018-03-09 EP EP18908694.5A patent/EP3764321B1/en active Active
-
2022
- 2022-06-16 JP JP2022097161A patent/JP2022126747A/ja active Pending
-
2024
- 2024-04-25 JP JP2024071440A patent/JP2024091918A/ja active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006209209A (ja) * | 2005-01-25 | 2006-08-10 | Honda Elesys Co Ltd | レーンマーク抽出装置 |
| JP2007018154A (ja) * | 2005-07-06 | 2007-01-25 | Honda Motor Co Ltd | 車両及びレーンマーク認識装置 |
| JP2014164492A (ja) | 2013-02-25 | 2014-09-08 | Denso Corp | 区画線認識装置 |
Non-Patent Citations (1)
| Title |
|---|
| TANAKA, NAOKI ET AL.: "A Robust White Line Detection Method for Road Surface Maintenance", THE IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS ( JAPANESE EDITION, vol. J 9 1, no. 8, 1 August 2008 (2008-08-01), pages 2129 - 2136, XP009523003 * |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2024091918A (ja) | 2024-07-05 |
| EP3764321A1 (en) | 2021-01-13 |
| JP2022126747A (ja) | 2022-08-30 |
| EP3764321A4 (en) | 2021-10-27 |
| US11348344B2 (en) | 2022-05-31 |
| EP3764321B1 (en) | 2025-08-27 |
| JPWO2019171565A1 (ja) | 2021-03-18 |
| US20210042537A1 (en) | 2021-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11295426B2 (en) | Image processing system, server apparatus, image processing method, and image processing program | |
| US10501088B2 (en) | Road surface state determination apparatus, imaging apparatus, imaging system, and road surface state determination method | |
| JP5267596B2 (ja) | 移動体検出装置 | |
| US9898669B2 (en) | Traveling road surface detection device and traveling road surface detection method | |
| JP6483446B2 (ja) | 複合線判定装置及び複合線判定方法 | |
| CN113344906B (zh) | 车路协同中相机评估方法、装置、路侧设备和云控平台 | |
| JP6361313B2 (ja) | 車両検出方法及び装置 | |
| JP4972116B2 (ja) | 車両の周辺監視装置 | |
| JP2018073275A (ja) | 画像認識装置 | |
| JP2023014131A (ja) | 線検出装置、線検出方法、プログラム、及び記憶媒体 | |
| JP2020095619A (ja) | 画像処理装置および画像処理方法 | |
| JP7109528B2 (ja) | 車載画像情報処理装置、車載画像情報送信装置および画像情報処理方法 | |
| JP2019159526A (ja) | 線検出装置、線検出方法、プログラム、及び記憶媒体 | |
| WO2019171565A1 (ja) | 線検出装置、線検出方法、プログラム、及び記憶媒体 | |
| JP2019159530A (ja) | 線検出装置、線検出方法、プログラム、及び記憶媒体 | |
| JP2007011490A (ja) | 道路パラメータ検出装置および道路パラメータ検出方法 | |
| JP6152646B2 (ja) | 複眼カメラ装置、及びそれを備えた車両 | |
| JP2019159528A (ja) | 線検出装置、線検出方法、プログラム、及び記憶媒体 | |
| JP2019159527A (ja) | 線検出装置、線検出方法、プログラム、及び記憶媒体 | |
| JP2019159525A (ja) | 線検出装置、線検出方法、プログラム、及び記憶媒体 | |
| JP2011180835A (ja) | 対象物の位置を算出するための装置 | |
| JP2020095625A (ja) | 画像処理装置および画像処理方法 | |
| JP2026074056A (ja) | 線検出装置、線検出方法、プログラム、及び記憶媒体 | |
| CN110598505A (zh) | 障碍物悬空状态判断方法、装置及终端 | |
| JP6936557B2 (ja) | 探索処理装置、及びステレオカメラ装置 |
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: 18908694 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2020504610 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: 2018908694 Country of ref document: EP |
|
| WWG | Wipo information: grant in national office |
Ref document number: 2018908694 Country of ref document: EP |