WO2013157301A1 - 立体物検出装置及び立体物検出方法 - Google Patents
立体物検出装置及び立体物検出方法 Download PDFInfo
- Publication number
- WO2013157301A1 WO2013157301A1 PCT/JP2013/054765 JP2013054765W WO2013157301A1 WO 2013157301 A1 WO2013157301 A1 WO 2013157301A1 JP 2013054765 W JP2013054765 W JP 2013054765W WO 2013157301 A1 WO2013157301 A1 WO 2013157301A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- dimensional object
- detected
- vehicle
- periodicity
- value
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/165—Anti-collision systems for passive traffic, e.g. including static obstacles, trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Definitions
- the present invention relates to a three-dimensional object detection device and a three-dimensional object detection method.
- This application claims priority based on Japanese Patent Application No. 2012-092912 filed on Apr. 16, 2012.
- the contents described in the application are incorporated into the present application by reference and made a part of the description of the present application.
- Patent Literature a detection device that includes a camera that images the side of a vehicle and detects a three-dimensional object such as an off-road implantation by matching an image captured by the camera with a pattern stored in advance.
- the shadow image of a tree with a trunk that keeps its shape and leaves that change its shape has periodicity and irregularity, so it grasps the characteristics of the image uniformly.
- the problem to be solved by the present invention is to prevent erroneous detection of the shadow of a tree having periodicity and irregularity as another vehicle traveling in the adjacent lane adjacent to the traveling lane of the own vehicle. It is providing the solid-object detection apparatus which can detect the other vehicle which drive
- the present invention calculates a periodicity evaluation value for evaluating periodicity and an irregularity evaluation value for evaluating irregularity based on difference waveform information or edge information of a captured image, and calculates the calculated period If the sex evaluation value is equal to or greater than the first periodicity evaluation threshold and less than the second periodicity evaluation threshold, and the calculated irregularity evaluation value is less than the predetermined irregularity evaluation threshold, the detected three-dimensional object Is determined to be the shadow of a tree that exists along the traveling path of the host vehicle.
- the periodicity evaluation value calculated from the difference waveform information or edge information calculated from the captured image is within the predetermined value range, and the irregularity evaluation value calculated from the difference waveform information or edge information is also the predetermined value range.
- the threshold When it is equal to or greater than the threshold, it is possible to identify that the image information includes a shadow of a tree having periodicity and irregularity. It is possible to prevent erroneous detection as another vehicle that travels in the adjacent lane adjacent to the travel lane. As a result, it is possible to provide a three-dimensional object detection device that detects, with high accuracy, other vehicles that travel in the adjacent lane adjacent to the travel lane of the host vehicle.
- FIG. 1 is a schematic configuration diagram of a vehicle according to an embodiment to which a three-dimensional object detection device of the present invention is applied. It is a top view (three-dimensional object detection by difference waveform information) which shows the driving state of the vehicle of FIG. It is a block diagram which shows the detail of the computer of FIG. 4A and 4B are diagrams for explaining the outline of processing of the alignment unit in FIG. 3, in which FIG. 3A is a plan view showing a moving state of the vehicle, and FIG. It is the schematic which shows the mode of the production
- FIG. 4 is a flowchart (No. 1) illustrating a three-dimensional object detection method using differential waveform information executed by the viewpoint conversion unit, the alignment unit, the smear detection unit, and the three-dimensional object detection unit of FIG. 3.
- FIG. 1 is a flowchart (No. 1) illustrating a three-dimensional object detection method using differential waveform information executed by the viewpoint conversion unit, the alignment unit, the smear detection unit, and the three-dimensional object detection unit of FIG. 3.
- FIG. 4 is a flowchart (part 2) illustrating a three-dimensional object detection method using differential waveform information executed by the viewpoint conversion unit, the alignment unit, the smear detection unit, and the three-dimensional object detection unit of FIG. 3. It is a figure (three-dimensional object detection by edge information) which shows the running state of vehicles of Drawing 1, (a) is a top view showing the positional relationship of a detection field etc., and (b) shows the positional relationship of a detection field etc. in real space. It is a perspective view shown. 4A and 4B are diagrams for explaining the operation of the luminance difference calculation unit in FIG. 3, in which FIG.
- 3A is a diagram illustrating a positional relationship among attention lines, reference lines, attention points, and reference points in a bird's eye view image; It is a figure which shows the positional relationship of the attention line, reference line, attention point, and reference point.
- 4A and 4B are diagrams for explaining the detailed operation of the luminance difference calculation unit in FIG. 3, in which FIG. 3A is a diagram illustrating a detection region in a bird's-eye view image, and FIG. It is a figure which shows the positional relationship of a reference point.
- FIG. 4 is a flowchart (part 1) illustrating a three-dimensional object detection method using edge information executed by a viewpoint conversion unit, a luminance difference calculation unit, an edge line detection unit, and a three-dimensional object detection unit in FIG. 3;
- FIG. 4 is a flowchart (part 1) illustrating a three-dimensional object detection method using edge information executed by a viewpoint conversion unit, a luminance difference calculation unit, an edge line detection unit, and a three-dimensional object detection unit in FIG. 3;
- FIG. 4 is a flowchart (part 2) illustrating a three-dimensional object detection method using edge information executed by the viewpoint conversion unit, the luminance difference calculation unit, the edge line detection unit, and the three-dimensional object detection unit of FIG. 3.
- It is a figure which shows the example of an image for demonstrating edge detection operation
- FIG.25 (a) shows the difference image PDt in time t
- FIG.25 (b) shows the difference image PDt-1 in imprint t-1.
- FIG.25 (a) shows the difference image PDt in time t
- FIG.25 (b) shows the difference image PDt-1 in imprint t-1.
- FIG.25 (a) shows the difference image PDt in time t
- FIG.25 (b) shows the difference image PDt-1 in imprint t-1.
- FIG. 1 is a schematic configuration diagram of a vehicle according to an embodiment to which a three-dimensional object detection device 1 of the present invention is applied.
- the three-dimensional object detection device 1 of the present example is careful when the driver of the host vehicle V is driving. Is a device that detects, as an obstacle, other vehicles that are likely to be contacted, for example, other vehicles that may be contacted when the host vehicle V changes lanes.
- the three-dimensional object detection device 1 of this example detects another vehicle that travels in an adjacent lane (hereinafter also simply referred to as an adjacent lane) adjacent to the lane in which the host vehicle travels. Further, the three-dimensional object detection device 1 of the present example can calculate the detected movement distance and movement speed of the other vehicle.
- the three-dimensional object detection device 1 is mounted on the own vehicle V, and the three-dimensional object detected around the own vehicle travels in the adjacent lane next to the lane on which the own vehicle V travels.
- An example of detecting a vehicle will be shown.
- the three-dimensional object detection device 1 of this example includes a camera 10, a vehicle speed sensor 20, a calculator 30, a brightness sensor 50, and a current position detection device 60.
- the camera 10 is attached to the host vehicle V so that the optical axis is at an angle ⁇ from the horizontal to the lower side at a height h at the rear of the host vehicle V.
- the camera 10 images a predetermined area in the surrounding environment of the host vehicle V from this position.
- the vehicle speed sensor 20 detects the traveling speed of the host vehicle V, and calculates the vehicle speed from the wheel speed detected by, for example, a wheel speed sensor that detects the rotational speed of the wheel.
- the computer 30 detects a three-dimensional object behind the vehicle, and calculates a moving distance and a moving speed for the three-dimensional object in this example.
- the brightness sensor 50 detects the brightness around the host vehicle V.
- the brightness sensor 50 may be configured by an illuminometer, or may be configured to acquire brightness information from image information of the camera 10.
- the current brightness around the host vehicle V is detected based on the current position and time by referring to the calendar information that associates the spot with the sunset time without directly detecting the brightness. You can also.
- the current position detection device 60 can also acquire position information from a navigation device of the host vehicle V equipped with GPS or a portable navigation device with built-in GPS.
- FIG. 2 is a plan view showing a traveling state of the host vehicle V in FIG.
- the camera 10 images the vehicle rear side at a predetermined angle of view a.
- the angle of view a of the camera 10 is set to an angle of view at which the left and right lanes can be imaged in addition to the lane in which the host vehicle V travels.
- the area that can be imaged includes detection target areas A1 and A2 on the adjacent lane that is behind the host vehicle V and that is adjacent to the left and right of the travel lane of the host vehicle V.
- FIG. 3 is a block diagram showing details of the computer 30 of FIG. 3, the camera 10, the vehicle speed sensor 20, the brightness sensor 50, and the current position detection device 60 are also illustrated in order to clarify the connection relationship.
- the computer 30 includes a viewpoint conversion unit 31, a positioning unit 32, a three-dimensional object detection unit 33, a detection area setting unit 34, and a smear detection unit 40.
- the calculation unit 30 of the present embodiment has a configuration relating to a three-dimensional object detection block using differential waveform information.
- the calculation unit 30 of the present embodiment can also be configured with respect to a three-dimensional object detection block using edge information.
- a block configuration A configured by the alignment unit 32 and the three-dimensional object detection unit 33 is surrounded by a broken line, a luminance difference calculation unit 35, an edge line detection unit 36, It can be configured by replacing the block configuration B configured by the three-dimensional object detection unit 37.
- both the block configuration A and the block configuration B can be provided, so that the solid object can be detected using the difference waveform information and the solid object can be detected using the edge information.
- the block configuration A and the block configuration B can be provided, either the block configuration A or the block configuration B can be operated according to environmental factors such as brightness. Each configuration will be described below.
- the three-dimensional object detection device 1 of the present embodiment exists in the detection area A1 of the right adjacent lane or the detection area A2 of the left adjacent lane behind the vehicle based on image information obtained by the monocular camera 1 that captures the rear of the vehicle. A three-dimensional object is detected.
- the detection area setting unit 34 sets detection areas A1 and A2 in the captured image information and on the right and left sides behind the host vehicle V, respectively.
- the positions of the detection areas A2 and A2 are not particularly limited, and can be set as appropriate according to the processing conditions.
- the viewpoint conversion unit 31 inputs captured image data of a predetermined area obtained by imaging with the camera 10 and converts the input captured image data into a bird's-eye view image data in a bird's-eye view state.
- the state viewed from a bird's-eye view is a state viewed from the viewpoint of a virtual camera looking down from above, for example, vertically downward.
- This viewpoint conversion can be executed as described in, for example, Japanese Patent Application Laid-Open No. 2008-219063.
- the viewpoint conversion of captured image data to bird's-eye view image data is based on the principle that a vertical edge peculiar to a three-dimensional object is converted into a straight line group passing through a specific fixed point by viewpoint conversion to bird's-eye view image data. This is because a planar object and a three-dimensional object can be distinguished if used. Note that the result of the image conversion processing by the viewpoint conversion unit 31 is also used in detection of a three-dimensional object by edge information described later.
- the alignment unit 32 sequentially inputs the bird's-eye view image data obtained by the viewpoint conversion of the viewpoint conversion unit 31 and aligns the positions of the inputted bird's-eye view image data at different times.
- 4A and 4B are diagrams for explaining the outline of the processing of the alignment unit 32, where FIG. 4A is a plan view showing the moving state of the host vehicle V, and FIG. 4B is an image showing the outline of the alignment.
- the host vehicle V at the current time is located at V1, and the host vehicle V one hour before is located at V2.
- the other vehicle VX is located in the rear direction of the own vehicle V and is in parallel with the own vehicle V, the other vehicle VX at the current time is located at V3, and the other vehicle VX one hour before is located at V4.
- the host vehicle V has moved a distance d at one time.
- “one hour before” may be a past time for a predetermined time (for example, one control cycle) from the current time, or may be a past time for an arbitrary time.
- the bird's-eye view image PB t at the current time is as shown in Figure 4 (b).
- the bird's-eye view image PB t becomes a rectangular shape for the white line drawn on the road surface, but a relatively accurate is a plan view state, tilting occurs about the position of another vehicle VX at position V3.
- the white line drawn on the road surface has a rectangular shape and is relatively accurately viewed in plan, but the other vehicle VX at the position V4 The fall will occur.
- the vertical edges of solid objects are straight lines along the collapse direction by the viewpoint conversion processing to bird's-eye view image data. This is because the plane image on the road surface does not include a vertical edge, but such a fall does not occur even when the viewpoint is changed.
- the alignment unit 32 performs alignment of the bird's-eye view images PB t and PB t ⁇ 1 as described above on the data. At this time, the alignment unit 32 is offset a bird's-eye view image PB t-1 before one unit time, to match the position and bird's-eye view image PB t at the current time.
- the image on the left side and the center image in FIG. 4B show a state that is offset by the movement distance d ′.
- This offset amount d ′ is a movement amount on the bird's-eye view image data corresponding to the actual movement distance d of the host vehicle V shown in FIG. It is determined based on the time until the time.
- the alignment unit 32 takes the difference between the bird's-eye view images PB t and PB t ⁇ 1 and generates data of the difference image PD t .
- the pixel value of the difference image PD t may be an absolute value of the difference between the pixel values of the bird's-eye view images PB t and PB t ⁇ 1 , and the absolute value may be used to cope with a change in illuminance environment. “1” may be set when a predetermined threshold value p is exceeded, and “0” may be set when the threshold value p is not exceeded.
- the image on the right side of FIG. 4B is the difference image PD t .
- the three-dimensional object detection unit 33 detects a three-dimensional object based on the data of the difference image PD t shown in FIG. At this time, the three-dimensional object detection unit 33 of this example also calculates the movement distance of the three-dimensional object in the real space. In detecting the three-dimensional object and calculating the movement distance, the three-dimensional object detection unit 33 first generates a differential waveform. Note that the moving distance of the three-dimensional object per time is used for calculating the moving speed of the three-dimensional object. The moving speed of the three-dimensional object can be used to determine whether or not the three-dimensional object is a vehicle.
- Three-dimensional object detection unit 33 of the present embodiment when generating the differential waveform sets a detection area in the difference image PD t.
- the three-dimensional object detection device 1 of the present example is another vehicle that the driver of the host vehicle V pays attention to, in particular, the lane in which the host vehicle V that may be contacted when the host vehicle V changes lanes travels. Another vehicle traveling in the adjacent lane is detected as a detection target. For this reason, in this example which detects a solid object based on image information, two detection areas are set on the right side and the left side of the host vehicle V in the image obtained by the camera 1. Specifically, in the present embodiment, rectangular detection areas A1 and A2 are set on the left and right sides behind the host vehicle V as shown in FIG.
- the other vehicle detected in the detection areas A1 and A2 is detected as an obstacle traveling in the adjacent lane adjacent to the lane in which the host vehicle V is traveling.
- Such detection areas A1 and A2 may be set from a relative position with respect to the host vehicle V, or may be set based on the position of the white line.
- the movement distance detection device 1 may use, for example, an existing white line recognition technique.
- the three-dimensional object detection unit 33 recognizes the sides (sides along the traveling direction) of the set detection areas A1 and A2 on the own vehicle V side as the ground lines L1 and L2 (FIG. 2).
- the ground line means a line in which the three-dimensional object contacts the ground.
- the ground line is set as described above, not a line in contact with the ground. Even in this case, from experience, the difference between the ground line according to the present embodiment and the ground line obtained from the position of the other vehicle VX is not too large, and there is no problem in practical use.
- FIG. 5 is a schematic diagram illustrating how a differential waveform is generated by the three-dimensional object detection unit 33 illustrated in FIG. 3.
- the three-dimensional object detection unit 33 calculates a differential waveform from a portion corresponding to the detection areas A ⁇ b> 1 and A ⁇ b> 2 in the difference image PD t (right diagram in FIG. 4B) calculated by the alignment unit 32.
- DW t is generated.
- the three-dimensional object detection unit 33 generates a differential waveform DW t along the direction in which the three-dimensional object falls by viewpoint conversion.
- the difference waveform DW t is generated for the detection area A2 in the same procedure.
- the three-dimensional object detection unit 33 defines a line La in the direction in which the three-dimensional object falls on the data of the difference image DW t . Then, the three-dimensional object detection unit 33 counts the number of difference pixels DP indicating a predetermined difference on the line La.
- the difference pixel DP indicating the predetermined difference is a predetermined threshold value when the pixel value of the difference image DW t is an absolute value of the difference between the pixel values of the bird's-eye view images PB t and PB t ⁇ 1.
- the pixel value of the difference image DW t is expressed by “0” and “1”, the pixel indicates “1”.
- the three-dimensional object detection unit 33 counts the number of difference pixels DP and then obtains an intersection point CP between the line La and the ground line L1. Then, the three-dimensional object detection unit 33 associates the intersection CP with the count number, determines the horizontal axis position based on the position of the intersection CP, that is, the position on the vertical axis in the right diagram of FIG. The axis position, that is, the position on the right and left axis in the right diagram of FIG. 5 is determined and plotted as the count number at the intersection CP.
- the three-dimensional object detection unit 33 defines lines Lb, Lc... In the direction in which the three-dimensional object falls, counts the number of difference pixels DP, and determines the horizontal axis position based on the position of each intersection CP. Then, the vertical axis position is determined from the count number (number of difference pixels DP) and plotted.
- the three-dimensional object detection unit 33 generates the differential waveform DW t as shown in the right diagram of FIG.
- the line La and the line Lb in the direction in which the three-dimensional object collapses have different distances overlapping the detection area A1. For this reason, if the detection area A1 is filled with the difference pixels DP, the number of difference pixels DP is larger on the line La than on the line Lb. For this reason, when the three-dimensional object detection unit 33 determines the vertical axis position from the count number of the difference pixels DP, the three-dimensional object detection unit 33 is normalized based on the distance at which the lines La and Lb in the direction in which the three-dimensional object falls and the detection area A1 overlap. Turn into. As a specific example, in the left diagram of FIG.
- the three-dimensional object detection unit 33 normalizes the count number by dividing it by the overlap distance.
- the difference waveform DW t the line La on the direction the three-dimensional object collapses, the value of the differential waveform DW t corresponding to Lb is substantially the same.
- the three-dimensional object detection unit 33 calculates the movement distance by comparison with the differential waveform DW t ⁇ 1 one time before. That is, the three-dimensional object detection unit 33 calculates the movement distance from the time change of the difference waveforms DW t and DW t ⁇ 1 .
- the three-dimensional object detection unit 33 divides the differential waveform DW t into a plurality of small areas DW t1 to DW tn (n is an arbitrary integer equal to or greater than 2).
- FIG. 6 is a diagram illustrating the small areas DW t1 to DW tn divided by the three-dimensional object detection unit 33.
- the small areas DW t1 to DW tn are divided so as to overlap each other, for example, as shown in FIG. For example, the small area DW t1 and the small area DW t2 overlap, and the small area DW t2 and the small area DW t3 overlap.
- the three-dimensional object detection unit 33 obtains an offset amount (amount of movement of the differential waveform in the horizontal axis direction (vertical direction in FIG. 6)) for each of the small areas DW t1 to DW tn .
- the offset amount is determined from the difference between the differential waveform DW t in the difference waveform DW t-1 and the current time before one unit time (distance in the horizontal axis direction).
- three-dimensional object detection unit 33 for each small area DW t1 ⁇ DW tn, when moving the differential waveform DW t1 before one unit time in the horizontal axis direction, the differential waveform DW t at the current time The position where the error is minimized (the position in the horizontal axis direction) is determined, and the amount of movement in the horizontal axis between the original position of the differential waveform DW t ⁇ 1 and the position where the error is minimized is obtained as an offset amount. Then, the three-dimensional object detection unit 33 counts the offset amount obtained for each of the small areas DW t1 to DW tn and forms a histogram.
- FIG. 7 is a diagram illustrating an example of a histogram obtained by the three-dimensional object detection unit 33.
- the offset amount which is the amount of movement that minimizes the error between each of the small areas DW t1 to DW tn and the differential waveform DW t ⁇ 1 one time before, has some variation.
- the three-dimensional object detection unit 33 forms a histogram of offset amounts including variations, and calculates a movement distance from the histogram.
- the three-dimensional object detection unit 33 calculates the moving distance of the three-dimensional object from the maximum value of the histogram. That is, in the example illustrated in FIG.
- the three-dimensional object detection unit 33 calculates the offset amount indicating the maximum value of the histogram as the movement distance ⁇ * .
- the moving distance ⁇ * is a relative moving distance of the other vehicle VX with respect to the host vehicle V. For this reason, when calculating the absolute movement distance, the three-dimensional object detection unit 33 calculates the absolute movement distance based on the obtained movement distance ⁇ * and the signal from the vehicle speed sensor 20.
- the three-dimensional object detection unit 33 weights each of the plurality of small areas DW t1 to DW tn and forms a histogram by counting the offset amount obtained for each of the small areas DW t1 to DW tn according to the weight. May be.
- FIG. 8 is a diagram illustrating weighting by the three-dimensional object detection unit 33.
- the small area DW m (m is an integer of 1 to n ⁇ 1) is flat. That is, in the small area DW m , the difference between the maximum value and the minimum value of the number of pixels indicating a predetermined difference is small. Three-dimensional object detection unit 33 to reduce the weight for such small area DW m. This is because the flat small area DW m has no characteristics and is likely to have a large error in calculating the offset amount.
- the small region DW m + k (k is an integer equal to or less than nm) is rich in undulations. That is, in the small area DW m , the difference between the maximum value and the minimum value of the number of pixels indicating a predetermined difference is large.
- Three-dimensional object detection unit 33 increases the weight for such small area DW m. This is because the small region DW m + k rich in undulations is characteristic and there is a high possibility that the offset amount can be accurately calculated. By weighting in this way, the calculation accuracy of the movement distance can be improved.
- the differential waveform DW t is divided into a plurality of small areas DW t1 to DW tn in order to improve the calculation accuracy of the movement distance.
- the small area DW t1 is divided. It is not necessary to divide into ⁇ DW tn .
- the three-dimensional object detection unit 33 calculates the moving distance from the offset amount of the differential waveform DW t when the error between the differential waveform DW t and the differential waveform DW t ⁇ 1 is minimized. That is, the method for obtaining the offset amount of the difference waveform DW t in the difference waveform DW t-1 and the current time before one unit time is not limited to the above disclosure.
- the computer 30 includes a smear detection unit 40.
- the smear detection unit 40 detects a smear generation region from data of a captured image obtained by imaging with the camera 10. Since smear is a whiteout phenomenon that occurs in a CCD image sensor or the like, the smear detection unit 40 may be omitted when the camera 10 using a CMOS image sensor or the like that does not generate such smear is employed.
- FIG. 9 is an image diagram for explaining the processing by the smear detection unit 40 and the calculation processing of the differential waveform DW t thereby.
- data of the captured image P in which the smear S exists is input to the smear detection unit 40.
- the smear detection unit 40 detects the smear S from the captured image P.
- There are various methods for detecting the smear S For example, in the case of a general CCD (Charge-Coupled Device) camera, the smear S is generated only in the downward direction of the image from the light source.
- CCD Charge-Coupled Device
- a region having a luminance value equal to or higher than a predetermined value from the lower side of the image to the upper side of the image and continuous in the vertical direction is searched, and this is identified as a smear S generation region.
- the smear detection unit 40 generates smear image SP data in which the pixel value is set to “1” for the place where the smear S occurs and the other place is set to “0”. After the generation, the smear detection unit 40 transmits the data of the smear image SP to the viewpoint conversion unit 31.
- the viewpoint conversion unit 31 to which the data of the smear image SP is input converts the viewpoint into a state of bird's-eye view. Thereby, the viewpoint conversion unit 31 generates data of the smear bird's-eye view image SB t .
- the viewpoint conversion unit 31 transmits the data of the smear bird's-eye view image SB t to the alignment unit 33. Further, the viewpoint conversion unit 31 transmits the data of the smear bird's-eye view image SB t ⁇ 1 one hour before to the alignment unit 33.
- the alignment unit 32 performs alignment of the smear bird's-eye view images SB t and SB t ⁇ 1 on the data.
- the specific alignment is the same as the case where the alignment of the bird's-eye view images PB t and PB t ⁇ 1 is executed on the data.
- the alignment unit 32 performs a logical sum on the smear S generation region of each smear bird's-eye view image SB t , SB t ⁇ 1 . Thereby, the alignment part 32 produces
- the alignment unit 32 transmits the data of the mask image MP to the three-dimensional object detection unit 33.
- the three-dimensional object detection unit 33 sets the count number of the frequency distribution to zero for the portion corresponding to the smear S generation region in the mask image MP. That is, when the differential waveform DW t as shown in FIG. 9 is generated, the three-dimensional object detection unit 33 sets the count number SC by the smear S to zero and generates a corrected differential waveform DW t ′. Become.
- the three-dimensional object detection unit 33 obtains the moving speed of the vehicle V (camera 10), and obtains the offset amount for the stationary object from the obtained moving speed. After obtaining the offset amount of the stationary object, the three-dimensional object detection unit 33 calculates the moving distance of the three-dimensional object after ignoring the offset amount corresponding to the stationary object among the maximum values of the histogram.
- FIG. 10 is a diagram illustrating another example of a histogram obtained by the three-dimensional object detection unit 33.
- a stationary object exists in addition to the other vehicle VX within the angle of view of the camera 10, two maximum values ⁇ 1 and ⁇ 2 appear in the obtained histogram.
- one of the two maximum values ⁇ 1, ⁇ 2 is the offset amount of the stationary object.
- the three-dimensional object detection unit 33 calculates the offset amount for the stationary object from the moving speed, ignores the maximum value corresponding to the offset amount, and calculates the moving distance of the three-dimensional object by using the remaining maximum value. To do.
- the three-dimensional object detection unit 33 stops calculating the movement distance.
- step S0 the computer 30 sets a detection area based on a predetermined rule. This detection area setting method will be described in detail later.
- the computer 30 receives data of the image P captured by the camera 10 and generates a smear image SP by the smear detection unit 40 (S1).
- the viewpoint conversion unit 31 generates data of the bird's-eye view image PB t from the data of the captured image P from the camera 10, and also generates data of the smear bird's-eye view image SB t from the data of the smear image SP (S2). .
- the alignment unit 33 aligns the data of the bird's-eye view image PB t and the data of the bird's-eye view image PB t ⁇ 1 one hour ago, and the data of the smear bird's-eye view image SB t one hour ago. And the data of the smear bird's-eye view image SB t-1 are aligned (S3).
- the alignment unit 33 generates data for the difference image PD t and also generates data for the mask image MP (S4).
- three-dimensional object detection unit 33, the data of the difference image PD t, and a one unit time before the difference image PD t-1 of the data generates a difference waveform DW t (S5).
- the three-dimensional object detection unit 33 After generating the differential waveform DW t , the three-dimensional object detection unit 33 sets the count number corresponding to the smear S generation region in the differential waveform DW t to zero, and suppresses the influence of the smear S (S6).
- the three-dimensional object detection unit 33 determines whether or not the peak of the differential waveform DW t is greater than or equal to the first threshold value ⁇ (S7).
- the peak of the difference waveform DW t is not equal to or greater than the first threshold value ⁇ , that is, when there is almost no difference, it is considered that there is no three-dimensional object in the captured image P.
- the three-dimensional object detection unit 33 does not have a three-dimensional object and has another vehicle as an obstacle. It is determined not to do so (FIG. 12: S16). Then, the processes shown in FIGS. 11 and 12 are terminated.
- the three-dimensional object detection unit 33 determines that a three-dimensional object exists, and sets the difference waveform DW t to a plurality of difference waveforms DW t .
- the area is divided into small areas DW t1 to DW tn (S8).
- the three-dimensional object detection unit 33 performs weighting for each of the small areas DW t1 to DW tn (S9).
- the three-dimensional object detection unit 33 calculates an offset amount for each of the small areas DW t1 to DW tn (S10), and generates a histogram with weights added (S11).
- the three-dimensional object detection unit 33 calculates a relative movement distance that is a movement distance of the three-dimensional object with respect to the host vehicle V based on the histogram (S12). Next, the three-dimensional object detection unit 33 calculates the absolute movement speed of the three-dimensional object from the relative movement distance (S13). At this time, the three-dimensional object detection unit 33 calculates the relative movement speed by differentiating the relative movement distance with respect to time, and adds the own vehicle speed detected by the vehicle speed sensor 20 to calculate the absolute movement speed.
- the three-dimensional object detection unit 33 determines whether the absolute movement speed of the three-dimensional object is 10 km / h or more and the relative movement speed of the three-dimensional object with respect to the host vehicle V is +60 km / h or less (S14). When both are satisfied (S14: YES), the three-dimensional object detection unit 33 determines that the three-dimensional object is the other vehicle VX (S15). Then, the processes shown in FIGS. 11 and 12 are terminated. On the other hand, when either one is not satisfied (S14: NO), the three-dimensional object detection unit 33 determines that there is no other vehicle (S16). Then, the processes shown in FIGS. 11 and 12 are terminated.
- the rear side of the host vehicle V is set as the detection areas A1 and A2, and the vehicle V travels in the adjacent lane that travels next to the travel lane of the host vehicle to which attention should be paid while traveling.
- Emphasis is placed on detecting the vehicle VX, and in particular, whether or not there is a possibility of contact when the host vehicle V changes lanes. This is to determine whether or not there is a possibility of contact with another vehicle VX traveling in the adjacent lane adjacent to the traveling lane of the own vehicle when the own vehicle V changes lanes. For this reason, the process of step S14 is performed.
- step S14 it is determined whether the absolute moving speed of the three-dimensional object is 10 km / h or more and the relative moving speed of the three-dimensional object with respect to the vehicle V is +60 km / h or less.
- the absolute moving speed of the stationary object may be detected to be several km / h. Therefore, by determining whether the speed is 10 km / h or more, it is possible to reduce the possibility of determining that the stationary object is the other vehicle VX.
- the relative speed of the three-dimensional object with respect to the host vehicle V may be detected at a speed exceeding +60 km / h. Therefore, the possibility of erroneous detection due to noise can be reduced by determining whether the relative speed is +60 km / h or less.
- step S14 it may be determined that the absolute movement speed is not negative or not 0 km / h. Further, in the present embodiment, since emphasis is placed on whether or not there is a possibility of contact when the host vehicle V changes lanes, when another vehicle VX is detected in step S15, the driver of the host vehicle is notified. A warning sound may be emitted or a display corresponding to a warning may be performed by a predetermined display device.
- the number of pixels indicating a predetermined difference is counted on the data of the difference image PD t along the direction in which the three-dimensional object falls by viewpoint conversion.
- the difference waveform DW t is generated by frequency distribution.
- the pixel indicating the predetermined difference on the data of the difference image PD t is a pixel that has changed in an image at a different time, in other words, a place where a three-dimensional object exists.
- the difference waveform DW t is generated by counting the number of pixels along the direction in which the three-dimensional object collapses and performing frequency distribution at the location where the three-dimensional object exists.
- the differential waveform DW t is generated from the information in the height direction for the three-dimensional object. Then, the moving distance of the three-dimensional object is calculated from the time change of the differential waveform DW t including the information in the height direction. For this reason, compared with the case where only one point of movement is focused on, the detection location before the time change and the detection location after the time change are specified including information in the height direction. The same location is likely to be obtained, and the movement distance is calculated from the time change of the same location, so that the calculation accuracy of the movement distance can be improved.
- the count number of the frequency distribution is set to zero for the portion corresponding to the smear S generation region in the differential waveform DW t .
- the waveform portion generated by the smear S in the differential waveform DW t is removed, and a situation in which the smear S is mistaken as a three-dimensional object can be prevented.
- the moving distance of the three-dimensional object is calculated from the offset amount of the differential waveform DW t when the error of the differential waveform DW t generated at different times is minimized. For this reason, the movement distance is calculated from the offset amount of the one-dimensional information called the waveform, and the calculation cost can be suppressed in calculating the movement distance.
- the differential waveform DW t generated at different times is divided into a plurality of small regions DW t1 to DW tn .
- a plurality of waveforms representing respective portions of the three-dimensional object are obtained.
- weighting is performed for each of the plurality of small areas DW t1 to DW tn , and the offset amount obtained for each of the small areas DW t1 to DW tn is counted according to the weight to form a histogram. For this reason, the moving distance can be calculated more appropriately by increasing the weight for the characteristic area and decreasing the weight for the non-characteristic area. Therefore, the calculation accuracy of the moving distance can be further improved.
- the weight is increased as the difference between the maximum value and the minimum value of the number of pixels indicating a predetermined difference increases. For this reason, the characteristic undulation region having a large difference between the maximum value and the minimum value has a larger weight, and the flat region having a small undulation has a smaller weight.
- the moving distance is calculated by increasing the weight in the area where the difference between the maximum value and the minimum value is large. The accuracy can be further improved.
- the moving distance of the three-dimensional object is calculated from the maximum value of the histogram obtained by counting the offset amount obtained for each of the small areas DW t1 to DW tn . For this reason, even if there is a variation in the offset amount, a more accurate movement distance can be calculated from the maximum value.
- the offset amount for a stationary object is obtained and this offset amount is ignored, it is possible to prevent a situation in which the calculation accuracy of the moving distance of the three-dimensional object is lowered due to the stationary object.
- the calculation of the moving distance of the three-dimensional object is stopped. For this reason, it is possible to prevent a situation in which an erroneous movement distance having a plurality of maximum values is calculated.
- the vehicle speed of the host vehicle V is determined based on a signal from the vehicle speed sensor 20, but the present invention is not limited to this, and the speed may be estimated from a plurality of images at different times. In this case, a vehicle speed sensor becomes unnecessary, and the configuration can be simplified.
- the captured image at the current time and the image one hour before are converted into a bird's-eye view, the converted bird's-eye view is aligned, the difference image PD t is generated, and the generated difference image PD
- t is evaluated along the falling direction (the falling direction of the three-dimensional object when the captured image is converted into a bird's eye view)
- the differential waveform DW t is generated, but the present invention is not limited to this.
- the differential waveform DW t may be generated by evaluating along the direction corresponding to the falling direction (that is, the direction in which the falling direction is converted into the direction on the captured image).
- the difference image PD t is generated from the difference between the two images subjected to the alignment, and the difference image PD t is converted into a bird's eye view
- the bird's-eye view does not necessarily have to be clearly generated as long as the evaluation can be performed along the direction in which the user falls.
- FIGS. 13A and 13B are diagrams illustrating an imaging range and the like of the camera 10 in FIG. 3.
- FIG. 13A is a plan view
- FIG. 13B is a perspective view in real space on the rear side from the host vehicle V. Show.
- the camera 10 has a predetermined angle of view a, and images the rear side from the host vehicle V included in the predetermined angle of view a.
- the angle of view “a” of the camera 10 is set so that the imaging range of the camera 10 includes the adjacent lane in addition to the lane in which the host vehicle V travels.
- the detection areas A1 and A2 in this example are trapezoidal in a plan view (when viewed from a bird's eye), and the positions, sizes, and shapes of the detection areas A1 and A2 are determined based on the distances d 1 to d 4. Is done.
- the detection areas A1 and A2 in the example shown in the figure are not limited to a trapezoidal shape, and may be other shapes such as a rectangle when viewed from a bird's eye view as shown in FIG. Note that the detection area setting unit 34 in the present embodiment can also set the detection areas A1 and A2 by the method described above.
- the distance d1 is a distance from the host vehicle V to the ground lines L1 and L2.
- the ground lines L1 and L2 mean lines on which a three-dimensional object existing in the lane adjacent to the lane in which the host vehicle V travels contacts the ground.
- the purpose of the present embodiment is to detect other vehicles VX and the like (including two-wheeled vehicles) traveling in the left and right lanes adjacent to the lane of the host vehicle V on the rear side of the host vehicle V.
- a distance d1 which is a position to be the ground lines L1 and L2 of the other vehicle VX is obtained from a distance d11 from the own vehicle V to the white line W and a distance d12 from the white line W to a position where the other vehicle VX is predicted to travel. It can be determined substantially fixedly.
- the distance d1 is not limited to being fixedly determined, and may be variable.
- the computer 30 recognizes the position of the white line W with respect to the host vehicle V by a technique such as white line recognition, and determines the distance d11 based on the recognized position of the white line W.
- the distance d1 is variably set using the determined distance d11.
- the distance d1 is It shall be fixedly determined.
- the distance d2 is a distance extending from the rear end portion of the host vehicle V in the vehicle traveling direction.
- the distance d2 is determined so that the detection areas A1 and A2 are at least within the angle of view a of the camera 10.
- the distance d2 is set so as to be in contact with the range divided into the angle of view a.
- the distance d3 is a distance indicating the length of the detection areas A1, A2 in the vehicle traveling direction. This distance d3 is determined based on the size of the three-dimensional object to be detected. In the present embodiment, since the detection target is the other vehicle VX or the like, the distance d3 is set to a length including the other vehicle VX.
- the distance d4 is a distance indicating a height set so as to include a tire such as the other vehicle VX in the real space.
- the distance d4 is a length shown in FIG. 13A in the bird's-eye view image.
- the distance d4 may be a length that does not include a lane that is further adjacent to the left and right adjacent lanes in the bird's-eye view image (that is, a lane that is adjacent to two lanes).
- the distances d1 to d4 are determined, and thereby the positions, sizes, and shapes of the detection areas A1 and A2 are determined. More specifically, the position of the upper side b1 of the detection areas A1 and A2 forming a trapezoid is determined by the distance d1. The starting point position C1 of the upper side b1 is determined by the distance d2. The end point position C2 of the upper side b1 is determined by the distance d3. The side b2 of the detection areas A1 and A2 having a trapezoidal shape is determined by a straight line L3 extending from the camera 10 toward the starting point position C1.
- a side b3 of trapezoidal detection areas A1 and A2 is determined by a straight line L4 extending from the camera 10 toward the end position C2.
- the position of the lower side b4 of the detection areas A1 and A2 having a trapezoidal shape is determined by the distance d4.
- the areas surrounded by the sides b1 to b4 are set as the detection areas A1 and A2.
- the detection areas A ⁇ b> 1 and A ⁇ b> 2 are true squares (rectangles) in the real space behind the host vehicle V.
- the viewpoint conversion unit 31 inputs captured image data of a predetermined area obtained by imaging with the camera 10.
- the viewpoint conversion unit 31 performs viewpoint conversion processing on the bird's-eye view image data in a bird's-eye view state on the input captured image data.
- the bird's-eye view is a state seen from the viewpoint of a virtual camera looking down from above, for example, vertically downward (or slightly obliquely downward).
- This viewpoint conversion process can be realized by a technique described in, for example, Japanese Patent Application Laid-Open No. 2008-219063.
- the luminance difference calculation unit 35 calculates a luminance difference with respect to the bird's-eye view image data subjected to viewpoint conversion by the viewpoint conversion unit 31 in order to detect the edge of the three-dimensional object included in the bird's-eye view image. For each of a plurality of positions along a vertical imaginary line extending in the vertical direction in the real space, the brightness difference calculating unit 35 calculates a brightness difference between two pixels in the vicinity of each position.
- the luminance difference calculation unit 35 can calculate the luminance difference by either a method of setting only one vertical virtual line extending in the vertical direction in the real space or a method of setting two vertical virtual lines.
- the brightness difference calculation unit 35 applies a first vertical imaginary line corresponding to a line segment extending in the vertical direction in the real space and a vertical direction in the real space different from the first vertical imaginary line with respect to the bird's-eye view image that has undergone viewpoint conversion.
- a second vertical imaginary line corresponding to the extending line segment is set.
- the luminance difference calculation unit 35 continuously obtains a luminance difference between a point on the first vertical imaginary line and a point on the second vertical imaginary line along the first vertical imaginary line and the second vertical imaginary line.
- the operation of the luminance difference calculation unit 35 will be described in detail.
- the luminance difference calculation unit 35 corresponds to a line segment extending in the vertical direction in the real space and passes through the detection area A1 (hereinafter referred to as the attention line La).
- the luminance difference calculation unit 35 corresponds to a line segment extending in the vertical direction in the real space and also passes through the second vertical virtual line Lr (hereinafter referred to as a reference line Lr) passing through the detection area A1.
- the reference line Lr is set at a position separated from the attention line La by a predetermined distance in the real space.
- the line corresponding to the line segment extending in the vertical direction in the real space is a line that spreads radially from the position Ps of the camera 10 in the bird's-eye view image.
- This radially extending line is a line along the direction in which the three-dimensional object falls when converted to bird's-eye view.
- the luminance difference calculation unit 35 sets the attention point Pa (point on the first vertical imaginary line) on the attention line La.
- the luminance difference calculation unit 35 sets a reference point Pr (a point on the second vertical plate) on the reference line Lr.
- the attention line La, the attention point Pa, the reference line Lr, and the reference point Pr have the relationship shown in FIG. 14B in the real space.
- the attention line La and the reference line Lr are lines extending in the vertical direction in the real space, and the attention point Pa and the reference point Pr are substantially the same height in the real space. This is the point that is set.
- the attention point Pa and the reference point Pr do not necessarily have the same height, and an error that allows the attention point Pa and the reference point Pr to be regarded as the same height is allowed.
- the luminance difference calculation unit 35 obtains a luminance difference between the attention point Pa and the reference point Pr. If the luminance difference between the attention point Pa and the reference point Pr is large, it is considered that an edge exists between the attention point Pa and the reference point Pr. Therefore, the edge line detection unit 36 shown in FIG. 3 detects an edge line based on the luminance difference between the attention point Pa and the reference point Pr.
- FIG. 15 is a diagram illustrating a detailed operation of the luminance difference calculation unit 35, in which FIG. 15 (a) shows a bird's-eye view image in a bird's-eye view state, and FIG. 15 (b) is shown in FIG. 15 (a). It is the figure which expanded a part B1 of the bird's-eye view image. Although only the detection area A1 is illustrated and described in FIG. 15, the luminance difference is calculated in the same procedure for the detection area A2.
- the other vehicle VX When the other vehicle VX is reflected in the captured image captured by the camera 10, the other vehicle VX appears in the detection area A1 in the bird's-eye view image as shown in FIG. As shown in the enlarged view of the area B1 in FIG. 15A in FIG. 15B, it is assumed that the attention line La is set on the rubber part of the tire of the other vehicle VX on the bird's-eye view image.
- the luminance difference calculation unit 35 first sets the reference line Lr.
- the reference line Lr is set along the vertical direction at a position away from the attention line La by a predetermined distance in the real space.
- the reference line Lr is set at a position separated from the attention line La by 10 cm in real space.
- the reference line Lr is set on the wheel of the tire of the other vehicle VX that is separated from the rubber of the tire of the other vehicle VX by, for example, 10 cm on the bird's eye view image.
- the luminance difference calculation unit 35 sets a plurality of attention points Pa1 to PaN on the attention line La.
- attention point Pai when an arbitrary point is indicated
- the number of attention points Pa set on the attention line La may be arbitrary.
- N attention points Pa are set on the attention line La.
- the luminance difference calculation unit 35 sets the reference points Pr1 to PrN so as to be the same height as the attention points Pa1 to PaN in the real space. Then, the luminance difference calculation unit 35 calculates the luminance difference between the attention point Pa and the reference point Pr having the same height. Thereby, the luminance difference calculation unit 35 calculates the luminance difference between the two pixels for each of a plurality of positions (1 to N) along the vertical imaginary line extending in the vertical direction in the real space. For example, the luminance difference calculating unit 35 calculates a luminance difference between the first attention point Pa1 and the first reference point Pr1, and the second difference between the second attention point Pa2 and the second reference point Pr2. Will be calculated.
- the luminance difference calculation unit 35 continuously calculates the luminance difference along the attention line La and the reference line Lr. That is, the luminance difference calculation unit 35 sequentially obtains the luminance difference between the third to Nth attention points Pa3 to PaN and the third to Nth reference points Pr3 to PrN.
- the luminance difference calculation unit 35 repeatedly executes the above-described processing such as setting the reference line Lr, setting the attention point Pa and the reference point Pr, and calculating the luminance difference while shifting the attention line La in the detection area A1. That is, the luminance difference calculation unit 35 repeatedly executes the above processing while changing the position of each of the attention line La and the reference line Lr by the same distance in the presence direction of the ground line L1 in the real space. For example, the luminance difference calculation unit 35 sets the reference line Lr as the reference line Lr in the previous processing, sets the reference line Lr for the attention line La, and sequentially obtains the luminance difference. It will be.
- the edge line detection unit 36 detects an edge line from the continuous luminance difference calculated by the luminance difference calculation unit 35.
- the first attention point Pa ⁇ b> 1 and the first reference point Pr ⁇ b> 1 are located in the same tire portion, and thus the luminance difference is small.
- the second to sixth attention points Pa2 to Pa6 are located in the rubber part of the tire, and the second to sixth reference points Pr2 to Pr6 are located in the wheel part of the tire. Therefore, the luminance difference between the second to sixth attention points Pa2 to Pa6 and the second to sixth reference points Pr2 to Pr6 becomes large. Therefore, the edge line detection unit 36 may detect that an edge line exists between the second to sixth attention points Pa2 to Pa6 and the second to sixth reference points Pr2 to Pr6 having a large luminance difference. it can.
- the edge line detection unit 36 firstly follows the following Equation 1 to determine the i-th attention point Pai (coordinate (xi, yi)) and the i-th reference point Pri (coordinate ( xi ′, yi ′)) and the i th attention point Pai are attributed.
- Equation 1 t represents a threshold value
- I (xi, yi) represents the luminance value of the i-th attention point Pai
- I (xi ′, yi ′) represents the luminance value of the i-th reference point Pri.
- the attribute s (xi, yi) of the attention point Pai is “1”.
- the attribute s (xi, yi) of the attention point Pai is “ ⁇ 1”.
- the edge line detection unit 36 determines whether or not the attention line La is an edge line from the continuity c (xi, yi) of the attribute s along the attention line La based on Equation 2 below.
- the continuity c (xi, yi) is “1”.
- the attribute s (xi, yi) of the attention point Pai is not the same as the attribute s (xi + 1, yi + 1) of the adjacent attention point Pai + 1
- the continuity c (xi, yi) is “0”.
- the edge line detection unit 36 obtains the sum for the continuity c of all the points of interest Pa on the line of interest La.
- the edge line detection unit 36 normalizes the continuity c by dividing the obtained sum of continuity c by the number N of points of interest Pa.
- the edge line detection unit 36 determines that the attention line La is an edge line when the normalized value exceeds the threshold ⁇ .
- the threshold value ⁇ is a value set in advance through experiments or the like.
- the edge line detection unit 36 determines whether or not the attention line La is an edge line based on Equation 3 below. Then, the edge line detection unit 36 determines whether or not all the attention lines La drawn on the detection area A1 are edge lines. [Equation 3] ⁇ c (xi, yi) / N> ⁇
- the three-dimensional object detection unit 37 detects a three-dimensional object based on the amount of edge lines detected by the edge line detection unit 36.
- the three-dimensional object detection device 1 detects an edge line extending in the vertical direction in real space. The fact that many edge lines extending in the vertical direction are detected means that there is a high possibility that a three-dimensional object exists in the detection areas A1 and A2. For this reason, the three-dimensional object detection unit 37 detects a three-dimensional object based on the amount of edge lines detected by the edge line detection unit 36. Furthermore, prior to detecting the three-dimensional object, the three-dimensional object detection unit 37 determines whether or not the edge line detected by the edge line detection unit 36 is correct.
- the three-dimensional object detection unit 37 determines whether or not the luminance change along the edge line of the bird's-eye view image on the edge line is larger than a predetermined threshold value. When the luminance change of the bird's-eye view image on the edge line is larger than the threshold value, it is determined that the edge line is detected by erroneous determination. On the other hand, when the luminance change of the bird's-eye view image on the edge line is not larger than the threshold value, it is determined that the edge line is correct.
- This threshold value is a value set in advance by experiments or the like.
- FIG. 16 is a diagram illustrating the luminance distribution of the edge line.
- FIG. 16A illustrates the edge line and the luminance distribution when another vehicle VX as a three-dimensional object exists in the detection area A1, and
- FIG. Indicates an edge line and a luminance distribution when there is no solid object in the detection area A1.
- the attention line La set in the tire rubber portion of the other vehicle VX is determined to be an edge line in the bird's-eye view image.
- the luminance change of the bird's-eye view image on the attention line La is gentle. This is because the tire of the other vehicle VX is extended in the bird's-eye view image by converting the image captured by the camera 10 into a bird's-eye view image.
- the attention line La set in the white character portion “50” drawn on the road surface in the bird's-eye view image is erroneously determined as an edge line.
- the brightness change of the bird's-eye view image on the attention line La has a large undulation. This is because a portion with high brightness in white characters and a portion with low brightness such as a road surface are mixed on the edge line.
- the three-dimensional object detection unit 37 determines whether or not the edge line is detected by erroneous determination. When the luminance change along the edge line is larger than a predetermined threshold, the three-dimensional object detection unit 37 determines that the edge line is detected by erroneous determination. And the said edge line is not used for the detection of a solid object. Thereby, white characters such as “50” on the road surface, weeds on the road shoulder, and the like are determined as edge lines, and the detection accuracy of the three-dimensional object is prevented from being lowered.
- the three-dimensional object detection unit 37 calculates the luminance change of the edge line by any one of the following mathematical formulas 4 and 5.
- the luminance change of the edge line corresponds to the evaluation value in the vertical direction in the real space.
- Equation 4 evaluates the luminance distribution by the sum of the squares of the differences between the i-th luminance value I (xi, yi) on the attention line La and the adjacent i + 1-th luminance value I (xi + 1, yi + 1).
- Equation 5 evaluates the luminance distribution by the sum of the absolute values of the differences between the i-th luminance value I (xi, yi) on the attention line La and the adjacent i + 1-th luminance value I (xi + 1, yi + 1).
- the attribute b (xi, yi) of the attention point Pa (xi, yi) is “1”. Become. If the relationship is other than that, the attribute b (xi, yi) of the attention point Pai is '0'.
- This threshold value t2 is set in advance by an experiment or the like in order to determine that the attention line La is not on the same three-dimensional object. Then, the three-dimensional object detection unit 37 sums up the attributes b for all the attention points Pa on the attention line La, obtains an evaluation value in the vertical equivalent direction, and determines whether the edge line is correct.
- 17 and 18 are flowcharts showing details of the three-dimensional object detection method according to the present embodiment.
- FIG. 17 and FIG. 18 for the sake of convenience, the processing for the detection area A1 will be described, but the same processing is executed for the detection area A2.
- step S20 the computer 30 sets a detection area based on a predetermined rule. This detection area setting method will be described in detail later.
- step S21 the camera 10 captures an image of a predetermined area specified by the angle of view a and the attachment position.
- step S22 the viewpoint conversion unit 31 inputs the captured image data captured by the camera 10 in step S21, performs viewpoint conversion, and generates bird's-eye view image data.
- step S23 the luminance difference calculation unit 35 sets the attention line La on the detection area A1. At this time, the luminance difference calculation unit 35 sets a line corresponding to a line extending in the vertical direction in the real space as the attention line La.
- luminance difference calculation part 35 sets the reference line Lr on detection area
- step S25 the luminance difference calculation unit 35 sets a plurality of attention points Pa on the attention line La.
- the luminance difference calculation unit 35 sets the attention points Pa as many as not causing a problem at the time of edge detection by the edge line detection unit 36.
- step S26 the luminance difference calculation unit 35 sets the reference point Pr so that the attention point Pa and the reference point Pr are substantially the same height in the real space. Thereby, the attention point Pa and the reference point Pr are arranged in a substantially horizontal direction, and it becomes easy to detect an edge line extending in the vertical direction in the real space.
- step S27 the luminance difference calculation unit 35 calculates the luminance difference between the attention point Pa and the reference point Pr that have the same height in the real space.
- the edge line detection unit 36 calculates the attribute s of each attention point Pa in accordance with Equation 1 above.
- step S28 the edge line detection unit 36 calculates the continuity c of the attribute s of each attention point Pa in accordance with Equation 2 above.
- step S29 the edge line detection unit 36 determines whether or not the value obtained by normalizing the total sum of continuity c is greater than the threshold value ⁇ according to the above formula 3.
- the edge line detection unit 36 detects the attention line La as an edge line in step S30. Then, the process proceeds to step S31.
- the edge line detection unit 36 does not detect the attention line La as an edge line, and the process proceeds to step S31.
- step S31 the computer 30 determines whether or not the processing in steps S23 to S30 has been executed for all the attention lines La that can be set on the detection area A1. If it is determined that the above processing has not been performed for all the attention lines La (S31: NO), the processing returns to step S23, a new attention line La is set, and the processing up to step S31 is repeated. On the other hand, when it is determined that the above process has been performed for all the attention lines La (S31: YES), the process proceeds to step S32 in FIG.
- step S32 of FIG. 18 the three-dimensional object detection unit 37 calculates a luminance change along the edge line for each edge line detected in step S30 of FIG.
- the three-dimensional object detection unit 37 calculates the luminance change of the edge line according to any one of the above formulas 4, 5, and 6.
- step S33 the three-dimensional object detection unit 37 excludes edge lines whose luminance change is larger than a predetermined threshold from the edge lines. That is, it is determined that an edge line having a large luminance change is not a correct edge line, and the edge line is not used for detecting a three-dimensional object. As described above, this is to prevent characters on the road surface, roadside weeds, and the like included in the detection area A1 from being detected as edge lines. Therefore, the predetermined threshold value is a value set based on a luminance change generated by characters on the road surface, weeds on the road shoulder, or the like obtained in advance by experiments or the like.
- step S34 the three-dimensional object detection unit 37 determines whether or not the amount of the edge line is equal to or larger than the second threshold value ⁇ .
- the second threshold value ⁇ is set based on the number of edge lines of the four-wheeled vehicle that have appeared in the detection region A1 in advance through experiments or the like.
- the three-dimensional object detection unit 37 detects that a three-dimensional object exists in the detection area A1 in step S35.
- the three-dimensional object detection unit 37 determines that there is no three-dimensional object in the detection area A1. Thereafter, the processing illustrated in FIGS. 17 and 18 ends.
- the detected three-dimensional object may be determined to be another vehicle VX that travels in the adjacent lane adjacent to the lane in which the host vehicle V travels, and the relative speed of the detected three-dimensional object with respect to the host vehicle V is taken into consideration. It may be determined whether the vehicle is another vehicle VX traveling in the adjacent lane.
- the vertical direction in the real space with respect to the bird's-eye view image A vertical imaginary line is set as a line segment extending to. Then, for each of a plurality of positions along the vertical imaginary line, a luminance difference between two pixels in the vicinity of each position can be calculated, and the presence or absence of a three-dimensional object can be determined based on the continuity of the luminance difference.
- the attention line La corresponding to the line segment extending in the vertical direction in the real space and the reference line Lr different from the attention line La are set for the detection areas A1 and A2 in the bird's-eye view image. Then, a luminance difference between the attention point Pa on the attention line La and the reference point Pr on the reference line Lr is continuously obtained along the attention line La and the reference line La. In this way, the luminance difference between the attention line La and the reference line Lr is obtained by continuously obtaining the luminance difference between the points. In the case where the luminance difference between the attention line La and the reference line Lr is high, there is a high possibility that there is an edge of the three-dimensional object at the set position of the attention line La.
- a three-dimensional object can be detected based on a continuous luminance difference.
- the detection accuracy of a three-dimensional object can be improved.
- the luminance difference between two points of approximately the same height near the vertical imaginary line is obtained.
- the luminance difference is obtained from the attention point Pa on the attention line La and the reference point Pr on the reference line Lr, which are substantially the same height in the real space, and thus the luminance when there is an edge extending in the vertical direction. The difference can be detected clearly.
- FIG. 19 is a diagram illustrating an example of an image for explaining the processing of the edge line detection unit 36.
- 102 is an adjacent image.
- a region where the brightness of the first striped pattern 101 is high and a region where the brightness of the second striped pattern 102 is low are adjacent to each other, and a region where the brightness of the first striped pattern 101 is low and the second striped pattern 102. Is adjacent to a region with high brightness.
- the portion 103 located at the boundary between the first striped pattern 101 and the second striped pattern 102 tends not to be perceived as an edge depending on human senses.
- the edge line detection unit 36 determines the part 103 as an edge line only when there is continuity in the attribute of the luminance difference in addition to the luminance difference in the part 103, the edge line detection unit 36 An erroneous determination of recognizing a part 103 that is not recognized as an edge line as a sensation as an edge line can be suppressed, and edge detection according to a human sensation can be performed.
- the edge line detection unit 36 when the luminance change of the edge line detected by the edge line detection unit 36 is larger than a predetermined threshold value, it is determined that the edge line has been detected by erroneous determination.
- the captured image acquired by the camera 10 is converted into a bird's-eye view image, the three-dimensional object included in the captured image tends to appear in the bird's-eye view image in a stretched state.
- the luminance change of the bird's-eye view image in the stretched direction tends to be small.
- the bird's-eye view image includes a high luminance region such as a character portion and a low luminance region such as a road surface portion.
- the brightness change in the stretched direction tends to increase in the bird's-eye view image. Therefore, by determining the luminance change of the bird's-eye view image along the edge line as in this example, the edge line detected by the erroneous determination can be recognized, and the detection accuracy of the three-dimensional object can be improved.
- the edge line detection unit 36 when the luminance change of the edge line detected by the edge line detection unit 36 is larger than a predetermined threshold value, it is determined that the edge line has been detected by erroneous determination.
- the captured image acquired by the camera 10 is converted into a bird's-eye view image, the three-dimensional object included in the captured image tends to appear in the bird's-eye view image in a stretched state.
- the luminance change of the bird's-eye view image in the stretched direction tends to be small.
- the bird's-eye view image includes a high luminance region such as a character portion and a low luminance region such as a road surface portion.
- the brightness change in the stretched direction tends to increase in the bird's-eye view image. Therefore, by determining the luminance change of the bird's-eye view image along the edge line as in this example, the edge line detected by the erroneous determination can be recognized, and the detection accuracy of the three-dimensional object can be improved.
- the three-dimensional object detection units 33 and 37 can also send detection results to an external vehicle controller for notification to the occupant and vehicle control.
- the three-dimensional object detection device 1 of this example includes the two three-dimensional object detection units 33 (or the three-dimensional object detection unit 37), the three-dimensional object determination unit 34, the stationary object determination unit 38, and the control unit. 39.
- the three-dimensional object determination unit 34 determines whether or not the detected three-dimensional object is the other vehicle VX existing in the detection areas A1 and A2. Judgment finally.
- the three-dimensional object detection unit 33 (or three-dimensional object detection unit 37) detects a three-dimensional object reflecting the determination result of the stationary object determination unit 38.
- the stationary object determination unit 38 determines whether the three-dimensional object detected by the three-dimensional object detection unit 33 (or the three-dimensional object detection unit 37) is a shadow of a tree existing along the traveling path of the host vehicle V.
- the stationary object determination unit 38 of the present embodiment detects a shadow of a tree (hereinafter also referred to as a tree shade). If a tree exists between the host vehicle V and a light source such as the sun, the shadow of the tree may be reflected in the detection areas A1 and A2. Trees have different configurations such as trunks, thick branches, thin branches, long branches, short branches, leaves, and the like. Each of these configurations behaves differently in the same environment. For example, even if it is blown by winds of the same strength (wind speed), the trunk hardly moves and its position remains unchanged, but thick branches and short branches swing slightly and their positions also vary somewhat. In addition, thin branches, long branches, and leaves swing greatly and their positions change greatly.
- a part of the tree shape does not change, but the other part changes, and in response to this, the shape and position of the other part also changes although the shadow and part of the tree do not change.
- the shadow of the trunk part shows strong periodic and regular features, but the shadow of the leaf part shows periodic and regular features. Does not appear strongly. For this reason, if the shadow of a tree is analyzed as a single image, it is difficult to find distinctive features, both periodic and regular. That is, it is difficult to determine the shadow characteristics of trees based on periodic characteristics, and it is also difficult to determine based on regular characteristics.
- structures such as guardrails provided at regular intervals on the shoulder of the traveling road have a constant shape, and the features extracted from the captured image appear periodically.
- the periodicity is higher than the shadow of the tree described above.
- an artificial structure such as a guardrail is immovable as a whole and maintains the same shape over time, so there is no variation in the features extracted from the captured image.
- Low irregularity high regularity.
- grass grows along the shoulder of the traveling road, and its shape is indefinite, so the features extracted from the captured image appear aperiodically, and thus the above-mentioned It can be said that the periodicity is lower than the shadow of trees.
- natural objects such as grass are generally indefinite and do not maintain the same shape over time, the characteristics extracted from the captured image can vary. It can be said that irregularity is high (regularity is low). This is because grass does not have a rigid portion that becomes a trunk like a tree, and its shape tends to change according to the external environment such as wind and rain. It should be noted that the image information of snow accumulated on the shoulder tends to show the same characteristics as the image information of grass.
- the other vehicle VX that is the object to be finally detected by the three-dimensional object detection device 1 of the present embodiment travels on the adjacent lane next to the traveling lane of the host vehicle V as shown in FIG. Since the timing at which the vehicle VX exists in the detection areas A1 and A2 cannot be controlled and the features cannot always be extracted periodically from the captured image, the trees that exist along the travel path of the host vehicle V described above It can be said that the periodicity is lower than the shadow of. On the other hand, since the basic structure of the other vehicle VX is common and maintains the same shape with time, there is no variation in the features extracted from the captured image, so the irregularity is lower than the shadow of the tree described above ( It is highly regular). Moreover, when the periodicity evaluation place is low and irregularity is low, the detected three-dimensional object is highly likely to be another vehicle.
- FIG. 23 is a diagram showing a relationship H between the periodicity evaluation value and the irregularity evaluation value for a structure Q2, such as a guardrail, a tree shade Q1, grass / snow Q3, and another vehicle VX.
- a structure Q2 such as a guardrail, a tree shade Q1, grass / snow Q3, and another vehicle VX.
- the periodicity evaluation value As shown in FIG. 23, regarding the periodicity, since the structures Q2 such as guardrails are regularly arranged on the road shoulder, there is a tendency to show a periodicity evaluation value equal to or higher than a predetermined threshold (second periodicity evaluation threshold). is there. In addition, since the traveling interval of each other vehicle VX is uncontrollable, the periodicity evaluation value tends to be less than a predetermined threshold (first periodicity evaluation threshold). Moreover, as shown in the figure, regarding irregularity, the structure Q2 such as a guardrail and the other vehicle VX tend to exhibit a low irregularity evaluation value because their shapes are constant.
- a method for identifying a stationary object from various three-dimensional objects included in a captured image there is a method using a point having high periodicity such as a structure Q2 such as a guardrail, and irregularities of natural objects such as grass and snow Q3.
- a point having high periodicity such as a structure Q2 such as a guardrail
- irregularities of natural objects such as grass and snow Q3.
- the inventors have proposed a method using a high point, as described above, the shadow (tree shade) Q1 of the tree has a medium periodicity and a moderate irregularity. There is a problem that it is difficult to distinguish from snow Q3.
- the three-dimensional object detection device 1 of the present embodiment is intended to detect the other vehicle VX, it can be identified as “a stationary object other than the other vehicle VX without distinguishing it from a structure Q2, such as a guardrail, grass, and snow Q3. It can also be considered that it should be identified as.
- an object other than the other vehicle VX is a moving object, a stationary object, a three-dimensional object, or a plane. It is necessary to design image processing and object detection processing according to the characteristics of the image to be detected depending on whether the object is an object, or an object other than the other vehicle VX is grass / snow or in the shade of a tree. is there.
- the shape of the guardrail Q2 can be predicted, it is considered that there is an upper limit on the height of the grass Q3, such as a process of predicting an image area in which the guardrail Q2 is reflected and applying a feedback process to the image processing.
- the characteristics of the other vehicle VX, the guardrail Q2, the grass / snow Q3, and the tree shade Q1 are analyzed from two viewpoints of periodicity and irregularity, and the periodicity and irregularity are analyzed.
- the shade Q1 can be accurately identified from the images of various objects included in the captured image based on the nature.
- the stationary object determination unit 38 can perform processing for determining a shadow of a tree based on differential waveform information or processing for determining a shadow of a tree based on edge information.
- the stationary object determination unit 38 calculates a periodicity evaluation value for evaluating the periodicity of the difference waveform information based on the difference waveform information generated by the three-dimensional object detection unit 33, and based on the difference waveform information. Then, an irregularity evaluation value for evaluating the irregularity of the differential waveform information is calculated.
- the calculation method of the periodicity evaluation value based on the difference waveform information is not particularly limited, and can be determined based on the degree to which the features extracted from the difference waveform information are repeated at a predetermined period. For example, the number of peaks extracted from the difference waveform information is greater than or equal to a predetermined value, the variation between peaks is less than the predetermined value, and the area difference of the peak portion of the difference waveform information corresponding to the vehicle speed of the host vehicle V ( It can be determined that the smaller the ratio of the area difference to the peak, the higher the periodicity.
- the calculation method of the irregularity evaluation value based on the difference waveform information is not particularly limited, and the determination can be made based on the degree of variation of the features extracted from the difference waveform information. For example, the number of peaks extracted from the difference waveform information is less than a predetermined value, the variation between peaks is greater than or equal to a predetermined value, and the area difference of the peak portion of the difference waveform information corresponding to the vehicle speed of the host vehicle V ( It can be determined that the larger the ratio of the area difference to the peak, the higher the irregularity.
- a specific method for calculating periodicity and irregularity based on the difference waveform information will be described in detail later.
- the stationary object determination unit 38 calculates a periodicity evaluation value for evaluating the periodicity of the edge information based on the edge information generated by the three-dimensional object detection unit 37, and the edge information based on the edge information. An irregularity evaluation value for evaluating the irregularity of information is calculated.
- the calculation method of the periodicity evaluation value based on the edge information is not particularly limited, and can be determined based on the degree to which the feature extracted from the edge information is repeated at a predetermined period. For example, the number of peaks extracted from the edge information is greater than or equal to a predetermined value, the variation between the peaks is less than the predetermined value, and the difference in the edge amount of the peak portion of the edge information corresponding to the vehicle speed of the host vehicle V is It can be determined that the smaller the value, the higher the periodicity. A specific method for calculating the periodicity based on the edge information will be described later in detail.
- the method for calculating the irregularity evaluation value based on the edge information is not particularly limited, and the determination can be made based on the degree of variation of the feature extracted from the edge information. For example, the number of peaks extracted from the edge information is less than a predetermined value, the variation between peaks is greater than or equal to a predetermined value, and the edge amount difference in the peak portion of the edge information corresponding to the vehicle speed of the host vehicle V is large. It can be determined that the irregularity is high. A specific method for calculating periodicity and irregularity based on edge information will be described in detail later.
- the stationary object determination unit 38 has the calculated periodicity evaluation value equal to or greater than the first periodicity evaluation threshold and less than the second periodicity evaluation threshold, and the calculated irregularity evaluation value is a predetermined irregularity evaluation.
- the threshold value it is determined that the three-dimensional object detected by the three-dimensional object detection unit 33 is a shadow of a tree existing along the traveling path of the host vehicle V. Thereby, it is possible to identify an image of the shade Q3 having a medium periodicity and irregularity.
- the first periodicity evaluation threshold value is smaller than the second periodicity evaluation threshold value.
- the first periodicity evaluation threshold and the second periodicity evaluation threshold described below are different values depending on whether the periodicity is determined based on the difference waveform information and when the periodicity is determined based on the edge information.
- the irregularity evaluation threshold different values can be set depending on whether the periodicity is determined based on the difference waveform information and when the periodicity is determined based on the edge information.
- the second periodicity evaluation threshold can be set based on the periodicity obtained experimentally for the structure Q2 such as a guardrail.
- the periodicity evaluation value is equal to or greater than the set second periodicity evaluation threshold, it can be determined that the detected three-dimensional object is a structure Q2 such as a guardrail. Since the periodicity of the structure Q2 such as the guardrail and the periodicity of the tree shade Q3 can be distinguished relatively clearly, by setting the second periodicity evaluation threshold based on the periodicity of the structure Q2 such as the guardrail, the tree shadow Q3 and grass / snow Q2 can be accurately distinguished from structures Q2 such as guardrails.
- the first periodicity evaluation threshold value can be set based on the periodicity of a moving body such as another vehicle VX that is experimentally obtained. That is, when the periodicity evaluation value is less than the first periodicity evaluation threshold, it can be determined that the detected three-dimensional object is a moving object, for example, another vehicle VX. Although the periodicity of the other vehicle VX and the periodicity of the grass / snow Q2 are both low, an identifiable difference can be found, so the first periodicity evaluation threshold is set based on the periodicity of the other vehicle VX. Thus, the shade Q3 and the grass / snow Q2 can be accurately identified from the other vehicle VX.
- the irregularity evaluation threshold can be set based on the irregularity of grass / snow Q3 or the irregularity of the shade Q1 that is experimentally obtained. That is, when the periodicity evaluation value is greater than or equal to the first periodicity evaluation threshold and less than the second periodicity evaluation threshold, and the irregularity evaluation value is greater than or equal to the irregularity evaluation value threshold, the three-dimensional object detection unit 33 When the detected three-dimensional object can be determined to be grass or snow Q3 existing along the traveling path of the host vehicle V, and the irregularity evaluation value is less than the irregularity evaluation threshold, the three-dimensional object It can be determined that the three-dimensional object detected by the detection unit 33 is the shade Q1 existing along the traveling path of the host vehicle V.
- Grass / snow Q2 and tree shade Q1 both have irregularities, and it is not easy to identify them.
- tree shade Q1 and grass / snow Q2 are narrowed down based on the periodicity evaluation value. Therefore, by identifying the tree shade Q1 or the grass / snow Q2 based on the irregularity evaluation value, the tree shade Q1 can be accurately identified from the grass / snow Q2.
- the stationary object determination unit 38 of the present embodiment changes the first periodicity evaluation threshold to a high value.
- the stationary object determination unit 38 of the present embodiment makes it difficult to detect the periodicity of the grass / snow Q3 and the shade Q1 in a dark situation where the brightness is less than the predetermined value, that is, the grass / snow Q3 and the shade Q1.
- the stationary object determination unit 38 of the present embodiment refers to the map information 383 in which each position information is associated with information on whether the position is an urban area or a suburban area, and the current position detection device 60 If the detected current position is an urban area, the first periodicity evaluation threshold is changed to a low value. Whether each position is an urban area or a suburban area can be defined in advance according to the number of structures along the road.
- buildings, advertising towers, signboards, and other structures are often provided along roads in urban areas, and shadows of these structures may be reflected in the detection areas A1 and A2.
- These structures have a low periodicity because the arrangement interval is not constant, and when the shadows of these structures overlap with the shadows of trees and grass along the road, the periodicity tends to decrease. That is, in an urban area where there are many advertising towers, billboards, and other structures, the periodicity of the shade Q1 or grass / snow Q3 reflected in the road detection areas A1 and A2 tends to be low.
- the stationary object determination unit 38 of the present embodiment reduces the first periodicity evaluation threshold, which is the lower limit threshold for determining the grass / snow Q3 and the shade Q1. Can be changed to a value. As a result, even in urban areas, the periodicity of grass / snow Q3 and shade Q1 can be accurately determined.
- the stationary object determination unit 38 of the present embodiment determines that the detected three-dimensional object is a moving object when the periodicity evaluation value is less than the first periodicity evaluation threshold. Similarly, when the periodicity evaluation value is less than the first periodicity evaluation threshold and the irregularity evaluation value is less than the predetermined irregularity evaluation threshold, the stationary object determination unit 38 detects the detected three-dimensional object. It is determined that the object is a moving object. In particular, when both the periodicity evaluation value and the irregularity evaluation value are low, the stationary object determination unit 38 determines that there is a high probability that the moving object is another vehicle.
- the three-dimensional object determination unit 34 of the present embodiment finally determines whether or not the three-dimensional object detected by the three-dimensional object detection units 33 and 37 is the other vehicle VX existing in the detection areas A1 and A2. Specifically, when the detection result of the three-dimensional object by the three-dimensional object detection units 33 and 37 continues for a predetermined time T, the three-dimensional object is present in the detection areas A1 and A2. It is determined that the vehicle is another vehicle VX.
- the three-dimensional object determination unit 34 has a predetermined value range such as the number of peaks of the differential waveform extracted from the differential waveform information, a peak value, a moving speed, and the state continues for a predetermined time or longer.
- the three-dimensional object is the other vehicle VX existing in the detection areas A1 and A2, the continuity of the edges extracted from the edge information, the normalized value of the sum, the edge line
- the amount of the vehicle is in the predetermined value range and the state continues for a predetermined time or more
- it is finally determined whether or not the three-dimensional object is the other vehicle VX existing in the detection regions A1 and A2. Also good.
- the three-dimensional object determination unit 34 of the present embodiment detects the three-dimensional object on the right detection region or the left side. It is determined that the other vehicle VX exists in the detection area.
- the three-dimensional object determination unit 34 determines that the detected three-dimensional object is the other vehicle VX existing in the detection areas A1 and A2, processing such as notification to the occupant is executed.
- the three-dimensional object determination unit 34 can suppress determining that the detected three-dimensional object is the other vehicle VX according to the control command of the control unit 38.
- control unit 39 determines that the captured image includes the image of the tree shade Q1 and the shadow of the tree is reflected in the detection areas A1 and A2 by the stationary object determination unit 38.
- control executed in each one or more of the three-dimensional object detection units 33 and 37, the three-dimensional object determination unit 34, the stationary object determination unit 38, or the control unit 39 that is itself in the next process. Instructions can be generated.
- the control command of the present embodiment is a command for controlling the operation of each unit so that it is suppressed that the detected three-dimensional object is the other vehicle VX. This is to prevent the detected three-dimensional object from being mistakenly regarded as another vehicle VX because the detected three-dimensional object is likely to be a tree shadow when the detection areas A1 and A2 have a shadow of the tree. is there. Since the computer 30 of the present embodiment is a computer, control commands for the three-dimensional object detection process, the three-dimensional object determination process, and the stationary object determination process may be incorporated in advance in the program of each process, or may be transmitted at the time of execution.
- the control command of the present embodiment may be a command for reducing sensitivity when detecting a three-dimensional object based on differential waveform information, or a command for decreasing sensitivity when detecting a three-dimensional object based on edge information.
- the control command stops the process of determining the detected three-dimensional object as the other vehicle, It may be a command for a result that makes it be judged that the vehicle is not a vehicle.
- the control unit 39 of the present embodiment detects the solid object, and the detected three-dimensional object. Is sent to the three-dimensional object detection units 33 and 37 or the three-dimensional object determination unit 34 to suppress the determination that the vehicle is the other vehicle VX. This makes it difficult for the three-dimensional object detection units 33 and 37 to detect the three-dimensional object. Further, it is difficult for the three-dimensional object determination unit 34 to determine that the detected three-dimensional object is the other vehicle VX existing in the detection area A.
- control unit 39 generates a control command with a content to stop the detection process of the three-dimensional object when it is determined that the three-dimensional object detected by the stationary object determination unit 38 is highly likely to be a shadow of the tree. Then, it may be output to the three-dimensional object detection units 33 and 37, or a control command with content for stopping the determination processing of the three-dimensional object or a control command with content for determining that the detected three-dimensional object is not another vehicle is generated. Alternatively, it may be output to the three-dimensional object determination unit 34. Thereby, the effect similar to the above can be obtained.
- control unit 39 determines that the solid object detected by the stationary object determination unit 38 is highly likely to be a shadow of the tree in the previous process, the shadow of the tree is reflected in the detection areas A1 and A2. It is determined that there is a high possibility that an error will occur in the processing based on the image information. If a three-dimensional object is detected in the same manner as usual, the three-dimensional object detected based on the image of the tree shade Q reflected in the detection areas A1 and A2 may be erroneously determined as the other vehicle VX.
- the control unit 39 of the present embodiment suppresses the fact that the three-dimensional object detected based on the image of the shade Q is erroneously determined as the other vehicle VX.
- the threshold value relating to the difference in pixel values when generating is increased.
- the control unit 39 makes it difficult to detect the three-dimensional object.
- a control command for increasing the first threshold value ⁇ is generated and output to the three-dimensional object detection unit 33.
- the first threshold value ⁇ is the first threshold value ⁇ for determining the peak of the differential waveform DW t in step S7 of FIG. 11 (see FIG. 5).
- the control unit 39 can output a control command for increasing or decreasing the threshold value p regarding the difference between pixel values in the difference waveform information to the three-dimensional object detection unit 33.
- control unit 39 determines that the three-dimensional object detected by the stationary object determination unit 38 is highly likely to be a shadow of a tree
- the control unit 39 performs predetermined processing on the difference image of the bird's-eye view image.
- a control command for counting the number of pixels indicating the difference and outputting the frequency distribution value to a low value can be output to the three-dimensional object detection unit 33.
- the value obtained by counting the number of pixels indicating a predetermined difference on the difference image of the bird's-eye view image and performing frequency distribution is the value on the vertical axis of the difference waveform DW t generated in step S5 of FIG.
- the control unit 39 determines the other vehicle VX based on the tree shadow Q1 reflected in the detection areas A1 and A2. Judge that there is a high possibility of false detection. For this reason, in the next processing, the frequency-distributed value of the differential waveform DW t is changed to a low value so that it is difficult to detect the three-dimensional object or the other vehicle VX in the detection areas A1 and A2. As described above, when it is determined that the detected three-dimensional object is likely to be a shadow of a tree, the output value is decreased to detect the other vehicle VX traveling next to the traveling lane of the host vehicle V. Since the sensitivity is adjusted, it is possible to prevent erroneous detection of the other vehicle VX caused by the shade Q1 reflected in the detection areas A1 and A2.
- control unit 39 determines that the three-dimensional object detected in the previous processing is highly likely to be a shadow of the tree, in the detection areas A1 and A2. It is determined that there is a high possibility of misdetecting the other vehicle VX based on the reflected tree shade Q1. For this reason, if it is determined that the detected three-dimensional object is likely to be a shadow of a tree, the control unit 39 according to the present embodiment increases the predetermined threshold relating to the luminance used when detecting edge information. The control command to be output is output to the three-dimensional object detection unit 37.
- the predetermined threshold value relating to the luminance used when detecting edge information is the threshold value ⁇ for determining a value obtained by normalizing the sum of the continuity c of the attributes of each point of interest Pa in step S29 in FIG. 17, or the step in FIG. 34 is a second threshold value ⁇ for evaluating the amount of edge lines. That is, when it is determined that the detected three-dimensional object is highly likely a shadow of a tree, the control unit 39 according to the present embodiment detects an edge line so that the three-dimensional object is difficult to detect. A control command for increasing the second threshold ⁇ for evaluating the threshold ⁇ or the amount of the edge line used for is generated and output to the three-dimensional object detection unit 37.
- the control unit 39 when it is determined that there is a high possibility that the three-dimensional object detected by the stationary object determination unit 38 is a shadow of a tree, the control unit 39 according to the present embodiment decreases or increases the amount of detected edge information.
- a control command to be output is output to the three-dimensional object detection unit 37.
- the detected amount of edge information is a value obtained by normalizing the sum of the continuity c of the attributes of each point of interest Pa in step S29 in FIG. 17 or the amount of edge lines in step 34 in FIG.
- the control unit 39 determines the other vehicle VX based on the tree shadow Q1 reflected in the detection areas A1 and A2.
- the frequency distribution value of the differential waveform DW t is changed to be low and output.
- the detection of the three-dimensional object or the determination as the other vehicle VX is suppressed by reducing the output value. Since it can be controlled, it is possible to prevent erroneous detection due to the shade Q1 reflected in the detection areas A1 and A2.
- the control unit 39 When it is determined that the three-dimensional object detected by the stationary object determination unit 38 is a moving object, the control unit 39 according to the present embodiment finally determines that the three-dimensional object determination unit 34 determines that the three-dimensional object is another vehicle. Try to judge. In other words, the control unit 39 receives the determination that the three-dimensional object is a moving object from the stationary object determination unit 38, and is opposite to the above-described process of “suppressing the determination of the three-dimensional object as another vehicle”. The process which plays is performed. Specifically, the control unit 39 changes the threshold value relating to the difference between the pixel values when generating the difference waveform information, changes the frequency distribution value of the difference waveform DW t to a higher value, and outputs the edge information. Control is performed so that it is easy to determine that the three-dimensional object is another vehicle, for example, by lowering a predetermined threshold value related to luminance used for detection or by outputting a higher amount of detected edge information.
- the stationary object determination unit 38 moves the detected three-dimensional object on the assumption that the periodicity evaluation value is less than the first periodicity evaluation threshold and the irregularity evaluation value is less than a predetermined irregularity evaluation threshold.
- the control unit 39 causes the three-dimensional object determination unit 34 to determine that the three-dimensional object detected by the three-dimensional object detection units 33 and 37 is another vehicle.
- the process illustrated in FIG. 24 is the current three-dimensional object detection process performed using the result of the previous process after the previous three-dimensional object detection process.
- the stationary object determination unit 38 determines periodicity based on the difference waveform information or the edge information. Specifically, a periodicity evaluation value for determining periodicity is calculated.
- the periodicity evaluation value is equal to or greater than the vehicle speed of the host vehicle V when the number of peaks extracted from the differential waveform information or edge information is greater than or equal to a predetermined value, and the variation between peaks is less than the predetermined value. It is judged that the periodicity is higher as the area difference of the peak portion of the corresponding difference waveform information (ratio of the area difference to the peak) or the edge amount difference of the edge portion of the edge information (ratio of the edge difference to the peak edge amount) is smaller. can do.
- a specific method of periodicity evaluation will be described in detail later.
- step S42 the stationary object determination unit 38 determines whether or not the calculated periodicity evaluation value is greater than or equal to the second periodicity evaluation threshold. If the calculated periodicity evaluation value is equal to or greater than the second periodicity evaluation threshold value, the process proceeds to step S52, and it is determined that the detected three-dimensional object is a structure Q2 such as a guardrail. When the calculated periodicity evaluation value is less than the second periodicity evaluation threshold, the process proceeds to step S43.
- step S43 the stationary object determination unit 38 determines whether or not the calculated periodicity evaluation value is less than the first periodicity evaluation threshold.
- the first periodicity evaluation threshold is a value lower than the second periodicity evaluation threshold (a value evaluated as having low periodicity).
- the process proceeds to step S53, and it is determined that there is a high possibility that the detected three-dimensional object is the other vehicle VX. If the calculated periodicity evaluation value is greater than or equal to the first periodicity evaluation threshold, that is, if the periodicity evaluation value is greater than or equal to the first periodicity evaluation threshold and less than the second periodicity evaluation threshold, the process proceeds to step S44. move on. Through the processing so far, the shade Q1 and the grass / snow Q3 can be narrowed down based on the periodicity.
- the stationary object determination unit 38 determines irregularity based on the difference waveform information or the edge information.
- the irregularity evaluation value can be determined based on the variation degree of the feature extracted from the difference waveform information or the edge information. For example, the number of peaks extracted from difference waveform information or edge information is less than a predetermined value, the variation between peaks is greater than or equal to a predetermined value, and the area of the peak portion of the difference waveform information corresponding to the vehicle speed of the host vehicle V It can be determined that the irregularity is higher as the difference (ratio of the area difference to the peak) or the difference in the edge amount of the peak portion of the edge information (ratio of the edge difference to the peak edge amount) is larger. A specific method for evaluating irregularity will be described in detail later.
- step S45 the stationary object determination unit 38 determines whether or not the calculated irregularity evaluation value is less than the irregularity evaluation threshold. If the calculated irregularity evaluation value is greater than or equal to the irregularity evaluation threshold, the process proceeds to step S54, and it is determined that the detected three-dimensional object is grass / snow Q2.
- the calculated irregularity evaluation value is less than the irregularity evaluation threshold value, that is, the periodicity evaluation value is not less than the first periodicity evaluation threshold value and less than the second periodicity evaluation threshold value, and the irregularity evaluation value is irregularity. If it is less than the evaluation threshold, the process proceeds to step S46.
- step S46 the stationary object determination unit 38 determines that the detected three-dimensional object is the shade Q1.
- step S47 when the stationary object determining unit 38 determines that the three-dimensional object detected in the previous process is the shadow of the tree (tree shade Q1), the control unit 39 sets the detection areas A1 and A2. It is determined that there is a high possibility of misdetecting the other vehicle VX based on the reflected tree shade Q1, and it is suppressed that the three-dimensional object is detected in the next process and the three-dimensional object is determined to be the other vehicle VX. As described above, control is performed such that the threshold value used in the three-dimensional object detection process and the three-dimensional object determination process is set high or the output value compared with the threshold value is low.
- the threshold p for pixel value difference when generating the difference waveform information, the first threshold ⁇ used when determining the three-dimensional object from the difference waveform information, and the edge so that detection of the three-dimensional object is suppressed A control command for changing any one or more of the threshold value ⁇ for generating information and the second threshold value ⁇ used for determining the solid object from the edge information to the three-dimensional object detection units 33 and 37 is sent. Note that, instead of increasing the threshold value, the control unit 39 may generate a control command for decreasing the output value evaluated by the threshold value and output the control command to the three-dimensional object detection units 33 and 37.
- the first threshold value ⁇ is used to determine the peak of the differential waveform DW t in step S7 of FIG.
- the threshold value ⁇ is a threshold value for determining a value obtained by normalizing the sum of the continuity c of the attribute of each target point Pa in step S29 in FIG. 17, and the second threshold value ⁇ is the amount of the edge line in step 34 in FIG. Is a threshold value for evaluating.
- the control unit 39 detects a three-dimensional object with a control command that counts the number of pixels indicating a predetermined difference on the difference image of the bird's-eye view image and outputs the frequency-distributed value higher.
- the value obtained by counting the number of pixels indicating a predetermined difference on the difference image of the bird's-eye view image and performing frequency distribution is the value on the vertical axis of the difference waveform DW t generated in step S5 of FIG.
- the control unit 39 can output a control command for outputting a high amount of detected edge information to the three-dimensional object detection unit 37.
- the detected amount of edge information is a value obtained by normalizing the sum of the continuity c of the attributes of each point of interest Pa in step S29 in FIG. 17 or the amount of edge lines in step 34 in FIG.
- the control unit 39 normalizes the sum of the continuity c of the attribute of each attention point Pa so that a solid object is difficult to detect in the next process.
- a control command for changing the value or the amount of edge line to be high can be output to the three-dimensional object detection unit 37.
- step S48 a three-dimensional object is detected based on the difference waveform information or edge information
- step S49 the three-dimensional object detected in step S48 is the other vehicle VX.
- a determination result indicating that the other vehicle exists is output in step S50.
- step S51 The determination result that there is no other vehicle is output.
- the processing in step S48 and step S49 is the detection processing of the other vehicle VX based on the difference waveform information described in FIGS. 11 and 12, and the detection processing of the other vehicle VX based on the edge information described in FIGS. Common.
- step S49 the process proceeds to step S55, and the three-dimensional object detection process may be stopped, or the process proceeds to step S51, and the detected three-dimensional object is not detected in the other vehicle VX. Alternatively, it may be determined that there is no other vehicle VX.
- the periodicity evaluation method and the irregularity evaluation method will be described.
- the techniques known at the time of filing can be appropriately applied.
- An irregularity evaluation method using a detection method can be applied as appropriate.
- the stationary object determination unit 38 may be the alignment unit 32 or the three-dimensional object detection unit 33, or It is possible to cause the luminance difference calculation unit 35, the edge line detection unit 36, or the three-dimensional object detection unit 37 to perform a part of the processing, acquire the processing result, and finally determine periodicity or irregularity.
- the stationary object determination unit 38 calculates candidates for the movement amounts of a plurality of three-dimensional objects detected by the three-dimensional object detection unit 33.
- FIG. 25 (a) shows the difference image PDt at time t
- FIG. 25 (b) shows the difference image PDt-1 at time t-1.
- the stationary object determination unit 38 detects a grounding point (feature point) of the three-dimensional object from the difference image PDt illustrated in FIG.
- the contact point is a contact point between the three-dimensional object and the road surface.
- the stationary object determination unit 38 detects a position closest to the camera 10 of the host vehicle V as a grounding point among the detected three-dimensional objects.
- the stationary object determination unit 38 detects the ground point P1 for the three-dimensional object O1, detects the ground point P2 for the three-dimensional object O2, and detects the ground point P3 for the three-dimensional object O3.
- the stationary object determination unit 38 sets an area T with a width W for the difference image PDt at time t shown in FIG.
- the stationary object determination unit 38 sets a region T at a location corresponding to the contact points P1 to P3 of the difference image PDt-1 at time t-1.
- the stationary object determination unit 38 detects the ground contact point of the three-dimensional object from the data of the difference image PDt at time t. Also in this case, a position closest to the camera 10 of the host vehicle V among the detected three-dimensional objects is detected as a grounding point.
- the stationary object determination unit 38 detects the ground point P4 for the three-dimensional object O4, detects the ground point P5 for the three-dimensional object O5, and detects the ground point P6 for the three-dimensional object O6.
- the alignment unit 32, the three-dimensional object detection unit 33, and the stationary object determination unit 38 of the present embodiment extract feature points (ground points) of a plurality of three-dimensional objects from the image and data of a predetermined region of the bird's-eye view image.
- the stationary object determination unit 38 associates the ground points with each other. That is, the ground point P4 is associated with the ground point P1, the ground point P5 is associated with the ground point P1, and the ground point P6 is associated with the ground point P1. Similarly, the ground points P4 to P6 are associated with the ground points P2 and P3.
- the stationary object determination unit 38 calculates the distance (that is, the movement amount candidate) between the associated grounding points P1 to P6. Then, the stationary object determination unit 38 sets the calculated distance as a movement amount candidate. The stationary object determination unit 38 calculates a plurality of movement amount candidates for each three-dimensional object. As a result, the movement amount of the three-dimensional object is uniquely determined, and the situation in which an erroneous movement amount is calculated for a periodic stationary object in which similar image features appear periodically is suppressed. ing.
- the region T is provided is that the grounding points P1 to P6 can be associated with each other stably even if an error occurs in the alignment of the bird's-eye view images PBt and PBt-1 due to pitching or winging of the host vehicle V. It is. Further, the association between the ground points P1 to P6 is determined by matching processing of luminance distribution around the ground point of the bird's-eye view images Bt and PBt-1.
- the stationary object determination unit 38 counts the calculated movement amount candidates and creates a histogram (waveform data). For example, if the distance between the ground point P1 and the ground point P4, the distance between the ground point P2 and the ground point P5, and the distance between the ground point P3 and the ground point P6 are the same, the stationary object determination unit 38 counts the count value. Is “3”. In this way, the stationary object determination unit 38 counts the movement amount candidates, creates a histogram, and calculates waveform data corresponding to the distribution of each ground point in the detection region.
- the stationary object determination unit 38 calculates the moving range of the periodic stationary object in a bird's-eye view based on the imaging interval of the camera 100 and the moving speed of the host vehicle V detected by the vehicle speed sensor 20.
- the stationary object determination unit 38 calculates a moving range having a predetermined range (for example, ⁇ 10 km / h) with respect to the speed of the host vehicle V. For example, when the imaging interval of the camera 10 is 33 ms and the actual distance in the vehicle traveling direction covered by one pixel is 5 cm, the speed of a three-dimensional object that moves one pixel in one control cycle is about 5.5 km ⁇ h. Considering that the accuracy of the bird's-eye view images PBt and PBt-1 deteriorates due to vehicle motion, a margin of ⁇ 10 km ⁇ h is required to allow about 5.5 km / h.
- the stationary object determination unit 38 evaluates the period of the plurality of three-dimensional objects detected by the three-dimensional object detection unit 33, and determines whether each three-dimensional object is a periodic stationary object.
- the stationary object determination unit 38 determines whether the plurality of three-dimensional objects detected by the three-dimensional object detection unit 33 are periodic stationary objects based on the created histogram, the calculated movement range, and the periodicity evaluation value.
- the periodic stationary objects include other vehicles VX having the periodicity shown in FIG. 23, grass / snow Q3, tree shade Q1, structures Q2 such as guardrails.
- FIG. 26 is a flowchart showing processing of the alignment unit 32 and the three-dimensional object detection unit 33.
- the alignment unit 32 inputs the data of the bird's-eye view images PBt and PBt-1 at different times detected by the viewpoint conversion unit 31, and performs alignment (S1).
- the three-dimensional object detection unit 33 calculates the difference between the aligned bird's-eye view images PBt and PBt ⁇ 1 (S2).
- the three-dimensional object detection unit 33 executes binarization processing based on the predetermined value and generates data of the difference image PDt (S3).
- FIG. 27 is a flowchart illustrating periodic stationary object candidate detection processing and periodicity determination processing for evaluating periodicity
- FIG. 28 is a diagram illustrating an example of a generated histogram. As shown in FIG. 28, the calculated movement amount candidates are counted. In the example shown in FIG. 28, since a plurality of movement amounts m1, m2, m3, and m4 are detected, these count values are high.
- the stationary object determination unit 38 detects the maximum value M (peak value; peak information) from the histogram (S11). Next, the stationary object determination unit 38 sets a predetermined threshold Th1 based on the maximum value M detected in step S12 (S12).
- the predetermined threshold Th1 is set to 70% of the maximum value M. For example, when the count value of the maximum value M is “7”, the predetermined threshold Th1 is set to “4.9”. Since the predetermined threshold value Th1 is obtained from the maximum value M of the count value, an appropriate threshold value can be set even if the magnitude of the count value changes due to the positional relationship between the host vehicle V and the three-dimensional object, the sunshine conditions, or the like. .
- the predetermined threshold value Th1 is 70% of the maximum value M, but is not limited to this.
- the stationary object determination unit 38 detects local maximum values M1 to M3 (peak values; peak information) that are equal to or greater than a predetermined threshold Th1 (S13).
- a predetermined threshold Th1 S13
- the stationary object determination unit 38 detects local maximum values M1 to M3 having a count value of “5” or more.
- the stationary object determination unit 38 is a three-dimensional object (for example, a distance between two grounding points corresponding to each of the movement amount candidates corresponding to the local maximum values M and M1 to M3 (including the maximum value M). It is determined that the two solid objects having the grounding point in the case where the maximum values M and any of M1 to M3 coincide with each other are periodic stationary object candidates.
- the stationary object determination unit 38 detects the interval (peak information) between the maximum values M and M1 to M3 (including the maximum value M), and votes the detected interval (S14). That is, in the example shown in FIG. 28, the number of votes is “2” for the interval D1, and the number of votes is “1” for the interval D2.
- the stationary object determination unit 38 determines (evaluates) the periodicity (S15). At this time, the stationary object determination unit 38 evaluates the periodicity based on whether or not the number of votes in step S14 is equal to or greater than a predetermined number of votes. This number of votes is an aspect of the periodicity evaluation value, and the predetermined number of votes is an aspect of the periodicity evaluation threshold.
- the predetermined number of votes is a predetermined number of votes as a second periodicity evaluation threshold set from the viewpoint of identifying the structure Q2 such as the guardrail and the first periodicity evaluation set from the viewpoint of identifying the other vehicle VX. And a predetermined number of votes as a threshold.
- the predetermined number of votes is half of the number of detected three-dimensional objects detected from the bird's-eye view image PBt. Therefore, when the number of detected three-dimensional objects detected from the bird enemy image PBt is “4”, the predetermined number of votes is “2”.
- the predetermined number of votes is not limited to the above, and may be a fixed value.
- the stationary object determination unit 38 decreases the predetermined threshold Th1 in step S12 (S16).
- the period during which the predetermined threshold value TH1 is lowered is approximately 1 second, and the predetermined threshold value Th1 is reset every time it is determined that there is periodicity.
- periodicity is determined from the occurrence positions of the maximum values M and M1 to M3 of the count values, that is, the interval, and when it is determined that there is periodicity, the predetermined threshold value Th1 is lowered, so that periodicity is once determined. In such a case, the periodic stationary object can be easily determined.
- the predetermined threshold value Th1 is not lowered until the periodicity is once determined, so that erroneous detection of a three-dimensional object due to an alignment error or the like can be suppressed.
- step S15 when it is determined that there is no periodicity (S15: NO), the predetermined threshold value Th1 is not lowered, and the process proceeds to step S17.
- the stationary object determination unit 38 determines the periodicity from the number of votes (peak information) of occurrence positions (intervals) of local maximum values M and M1 to M3 that are equal to or larger than a predetermined threshold Th1 based on the maximum count value M of the movement amount candidates. To do. For this reason, a local maximum value having a relatively small value (for example, the symbol M4 in FIG. 28) can be ignored, and the periodicity can be judged with higher accuracy without being affected by noise.
- step S17 the stationary object determination unit 38 determines whether or not lateral movement exceeding the specified level has been detected in the host vehicle V based on the information acquired from the controller of the host vehicle V (S17).
- the controller of the host vehicle V detects that a lateral movement exceeding a specified value is detected when the turn signal is ON and a steering angle exceeding a specified value determined from the vehicle speed detected by the vehicle speed sensor is detected. to decide.
- the stationary object determination unit 38 initializes the threshold value Th1 lowered in step S16 (S18) when a lateral movement exceeding the specified value is detected (S17: YES). Thereby, a periodic stationary object can be detected according to a change in the environment after the lane change. On the other hand, when the lateral movement exceeding the specified value is not detected (S17: No), the predetermined threshold value Th1 ends without being initialized.
- FIG. 29 is a flowchart showing a periodic stationary object determination process.
- the stationary object determination unit 38 calculates a stationary equivalent movement amount (S21). That is, the stationary object determination unit 38 calculates the moving range of the periodic stationary object in the bird's eye view based on the imaging interval of the camera 10 and the moving speed of the host vehicle V detected by the vehicle speed sensor 20. At this time, the stationary object determination unit 38 calculates a moving range having a predetermined margin with respect to the speed of the host vehicle V.
- S21 stationary equivalent movement amount
- the stationary object determination unit 38 determines whether or not the maximum values M, M1, and M3 (histogram peaks) exist within the range of the movement amount detected in step S21 (S22). When the stationary object determining unit 38 determines that any of the maximum values M and M1 to M3 is within the range of the moving amount (S22: YES), the stationary object determining unit 38 determines that a periodic stationary object exists (S23).
- the periodic stationary objects are often arranged at the same interval, and the specific count value tends to increase.
- the count value of the movement amount candidate should be within the movement range considering the speed of the moving object. Therefore, when it is determined as [YES] in step S22, it can be said that a plurality of solid objects are periodic stationary objects.
- step S22 when the stationary object determination unit 38 determines that none of the maximum values M and M1 to M3 exist within the range of the movement amount (S22: No), it determines whether or not there is periodicity in step S24. To do. If it is not determined that there is periodicity (S24: No), it is determined that the three-dimensional object is a moving object (S25). On the other hand, if it is determined in step S24 that there is periodicity (S24: YES), an aperiodic maximum value is detected from a maximum value equal to or greater than a predetermined neighboring value Th1 (S26). The aperiodic maximum value corresponds to, for example, a maximum value M3 shown in FIG. The maximum value M3 is different from the other maximum values M, M1, and M2 in the interval between the adjacent maximum values. Therefore, the stationary object determination unit 38 determines that the maximum value M3 is a non-periodic maximum value without periodicity.
- the stationary object determination unit 38 determines that a periodic stationary object exists because there is periodicity and there is no aperiodic maximum value. (S23).
- the stationary object determination unit 38 determines whether or not the periodic maximum values M, M1, and M2 are lower than the previous value (S27). ). In this process, the stationary object determination unit 38 calculates the average value of the periodic maximum values M, M1, and M2 in the current process, and also calculates the average value of the periodic maximum values in the previous process. The stationary object determination unit 38 determines whether the average value of the current process is lower than the average value of the previous process by a predetermined value or more.
- the stationary object determination unit 38 asks the other vehicle or the like for the question of the vehicle V and the periodic stationary object. Is detected and a moving object is detected (S25).
- the stationary object determination unit 38 is located behind the periodic stationary object as viewed from the host vehicle V. It is determined that another vehicle VX or the like has entered, and a periodic stationary object is detected (S23).
- FIG. 30 is a diagram showing details of step S27 shown in FIG. 29, where (a) shows a case where another vehicle V0 has entered the near side of the periodic stationary object, and (b) is a scene in (a). A histogram is shown. Further, (c) shows a case where another vehicle V0 enters the back side of the periodic stationary object, and (d) shows a histogram in the scene of (c).
- a broken line indicates a histogram before entering another vehicle
- a solid line indicates a histogram after entering another vehicle.
- the stationary object determination unit 38 detects the other vehicle V0 (moving object).
- the grounding points (feature points) of a plurality of three-dimensional objects are extracted from the image and data of a predetermined region of the bird's-eye view image, and the distribution of the grounding points within the predetermined detection region is performed.
- Histograms (waveform data) corresponding to each of the three-dimensional objects are calculated based on whether the peak value of the histogram, the number of votes in the peak interval, etc. (peak information) is equal to or greater than a predetermined threshold. It is determined whether it is a candidate for a stationary object. The peak value of the histogram, the number of votes in the peak interval, etc.
- peak information can be applied as one aspect of the periodicity evaluation value
- predetermined threshold can be applied as one aspect of the periodicity evaluation threshold.
- the periodicity (repeatability) of a periodic stationary object can be more clearly extracted as peak information of waveform data, and periodic stationary object candidates can be extracted from the three-dimensional objects included in the captured image. It can be extracted more easily. This makes it possible to extract a periodic stationary object with higher accuracy.
- the stationary object determination unit 38 detects an edge distribution.
- the stationary object determination unit 38 can cause the edge detection unit 36 to detect the edge distribution and obtain the result.
- the stationary object determination unit 38 calculates a luminance difference for the bird's-eye view image data converted by the viewpoint conversion unit 31 in order to detect an edge (feature point) of the periodic stationary object included in the bird's-eye view image. Do.
- the stationary object determination unit 38 calculates the luminance difference between the two pixels near each position for each of a plurality of positions along the vertical imaginary line extending in the vertical direction in the real space.
- the stationary object determination unit 38 continuously obtains a luminance difference between a point on the first vertical imaginary line and a point on the second vertical imaginary line along the first vertical imaginary line.
- the stationary object determination unit 38 corresponds to a line segment extending in the vertical direction from a point on the ground line L1 in the real space, and passes through the detection area A1 (hereinafter referred to as the first vertical imaginary line Kai).
- the stationary object determination unit 38 corresponds to each of the plurality of attention lines Lai, corresponds to a line segment extending in the vertical direction from a point on the ground line L1 in real space, and passes through the detection region A1.
- a plurality of Lri (hereinafter referred to as reference lines Lri) are set.
- Each reference line Lri is set at a position that is separated from the corresponding attention line Lai in the real space by a predetermined distance (for example, 10 cm).
- the line corresponding to the line segment extending in the vertical direction in the real space is a line that spreads radially from the position Ps of the camera 10 in the bird's-eye view image.
- the stationary object determination unit 38 sets a plurality of attention points Paj on each attention line Lai.
- attention points Pa1 to Pa8 are set, but the number of attention points Paj is not particularly limited.
- the stationary object determination unit 38 sets a plurality of reference points Prj each corresponding to the attention point Paj on each reference line Lri.
- the attention point Paj and the reference point Prj corresponding to each other are set at substantially the same height in the real space. It should be noted that the attention point Paj and the reference point Prj do not necessarily have exactly the same height, and it is a matter of course that an error that allows the attention point Paj and the reference point Prj to be regarded as the same height is allowed.
- the stationary object determination unit 38 continuously calculates the luminance difference between the attention point Pai and the reference point Prj corresponding to each other along each attention line Lai.
- a luminance difference is calculated between the first 1 point of interest Pa1 and the first reference point Pr1
- a luminance difference is calculated between the second point of interest Pa2 and the second reference point Pr2.
- the luminance difference between the third to eighth attention points Pa3 to Pa8 and the third to eighth reference points Pr3 to Pr8 is obtained sequentially.
- the stationary object determination unit 38 determines that an edge element exists between the attention point Pai and the reference point Prj when the luminance difference between the attention point Pai and the reference point Prj is equal to or greater than a predetermined value. Then, the stationary object determination unit 38 counts how many edge elements exist along the same attention line Lai. The stationary object determination unit 38 stores the counted number of edge elements as an attribute of each attention line Lai. The stationary object determination unit 38 performs edge element detection and count processing for all attention lines Lai. In addition, the length of the part which overlaps with detection area
- FIG. 31 another vehicle V0 is shown in the detection area A1. It is assumed that the attention line Lai is set on the rubber part of the tire of the other vehicle V0, and the reference line Lri is set on the wheel of the tire separated by 10 cm from the attention line Lai. At this time, since the first attention point Pa1 and the first reference point Pr1 are located in the same tire portion, the luminance difference between them is small. On the other hand, since the second to eighth attention points Pa2 to Pa8 are located in the rubber part of the tire and the second to eighth reference points Pr2 to Pr8 are located in the wheel part of the tire, the luminance difference between them is large. Become.
- the stationary object determination unit 38 sets the second to eighth attention points Pa2 to Pa8 as It is detected that an edge element exists between the second to eighth reference points Pr2 to Pr8. Since there are seven second to eighth attention points Pa2 to Pa8 along the attention line Lai, the edge element is detected seven times, and the count value of the edge element is “7”.
- the stationary object determination unit 38 graphs the edge element count values obtained for each attention line Lai to obtain an edge distribution waveform (waveform data). Specifically, the stationary object determination unit 38 sets the edge element count value on a plane with the vertical axis representing the edge element count value and the horizontal axis representing the position of the attention line Lai on the ground line L1 in real space. Plot. When the attention lines La1 to Lan are set on the ground line L1 at regular intervals in the real space, the edge element count values obtained for the attention lines Lai are arranged in the order of the attention lines Lai to Lan. The edge distribution waveform can be obtained only by this. In the example shown in FIG. 31, the count value of the edge element is “7” at the position where the attention line Lai set in the rubber part of the tire of the other vehicle V0 intersects the ground line L1 on the bird's-eye view image. Yes.
- the stationary object determination unit 38 integrates the number of edge elements existing along the vertical imaginary line for each of the plurality of vertical imaginary lines extending in the vertical direction in the real space.
- An edge distribution waveform (waveform data) is obtained based on the integrated number of edge elements.
- the stationary object determination unit 38 detects the peak of the edge distribution waveform.
- the peak is a point at which the count value of the edge element turns from increasing to decreasing on the edge distribution waveform.
- the stationary object determination unit 38 performs peak detection on the edge distribution waveform after performing noise removal processing using, for example, a low-pass filter and a moving average filter.
- a peak having a value equal to or greater than a predetermined threshold may be detected as a peak.
- the predetermined threshold value can be set to a value that is 60% of the maximum value of the edge distribution waveform, for example.
- the stationary object determination unit 38 counts the number of peaks arranged at equal intervals among the detected peaks. Specifically, the distance between the detected peaks is calculated, peaks whose calculated peak-to-peak distance is within a predetermined range are extracted, and the number is counted.
- the stationary object determination unit 38 determines whether an object corresponding to each counted peak corresponds to a periodic stationary object candidate based on whether or not the counted number of peaks (peak information) is equal to or greater than a predetermined threshold Th2. Determine whether or not. Specifically, the stationary object determining unit 38 determines that the object corresponding to each counted peak is a periodic stationary object candidate when the number of counted peaks is equal to or greater than a predetermined threshold Th2.
- the threshold value Th2 is a value determined according to the type of a periodic stationary object that is a detection target, such as a pylon, a guardrail leg, or a utility pole, and can be obtained through an experiment or the like. Specifically, the threshold Th2 is set to a value of 3 to 100, for example.
- the stationary object determination unit 38 determines that the periodic stationary object candidate is a periodic stationary object when the periodic stationary object candidate is continuously detected for a predetermined time. Specifically, when a state where the number of peaks is equal to or greater than a predetermined threshold value Th2 is continuously detected for a predetermined time, it is determined that there is a high possibility that the detected periodic stationary object candidate is a periodic stationary object. Then, the stationary object determination unit 38 determines that the object corresponding to each counted peak is a periodic stationary object.
- the number of peaks counted in the edge distribution waveform is an aspect of the periodicity evaluation value
- the threshold Th2 is an aspect of the periodicity evaluation threshold.
- the threshold value Th2 is a threshold value as a second periodicity evaluation threshold value set from the viewpoint of identifying the structure Q2 such as the guardrail described above, and a first periodicity evaluation threshold value set from the viewpoint of identifying the other vehicle VX. And a threshold value.
- the “predetermined time” is a value determined according to the type of the periodic stationary object that is the detection target, and can be obtained through an experiment or the like. It may be a fixed value or may be varied according to the imaging interval of the camera 10 or the moving speed of the host vehicle V. Specifically, the “predetermined time” is set to 0.1 to 5 seconds, for example.
- 32 and 33 are flowcharts of the periodic stationary object detection process. 32 and 33, for the sake of convenience, the processing for the detection area A1 will be described, but the same processing can be performed for the detection area A2.
- step S31 viewpoint conversion processing is performed based on the obtained captured image data to create bird's-eye view image data.
- the stationary object determination unit 38 sets the attention line Lai extending in the vertical direction from a point on the ground line L1 in the real space. Further, a reference line Lri corresponding to a line segment extending in the vertical direction from a point on the ground line L1 in the real space and spaced apart from the corresponding attention line Lai in the real space by a predetermined distance is set.
- the attention point Paj and the reference point Prj corresponding to each other are set so as to have the same height in the real space.
- step S34 the stationary object determination unit 38 determines whether or not the luminance difference between the corresponding point of interest Paj and the reference point Prj is equal to or greater than a predetermined value. If it is determined that the luminance difference is greater than or equal to the predetermined value, it is determined that an edge element exists between the target point Paj as the determination target and the reference point Prj. In step S35, the i-th target line Lai is determined. “1” is assigned to the count value (bincount (i)). If it is determined in step S34 that the luminance difference is less than the predetermined value, it is determined that there is no edge element between the target point Paj to be determined and the reference point Prj, and the process proceeds to step S36. .
- step S36 the stationary object determination unit 38 determines whether or not the process of step S34 has been executed for all the attention points Paj on the attention line Lai that is currently being processed. If it is determined that the process of step S34 has not been executed for all the attention points Paj, the process returns to step S34, the luminance difference between the next attention point Paj + 1 and the reference point Prj + 1 is obtained, and the luminance difference is equal to or greater than a predetermined value. It is determined whether or not. In this way, the stationary object determination unit 38 sequentially and continuously obtains the luminance difference between the attention point Paj and the reference point Prj along the attention line Lai, and the obtained luminance difference becomes a predetermined value or more. If it is determined that there is an edge element.
- step S35 the stationary object determination unit 38 assigns “1” to the count value (bincount (i)) of the first attention line Lai, and then proceeds to step S37.
- a luminance difference between Paj + 1 and the reference point Prj + 1 is obtained, and it is determined whether or not the luminance difference is a predetermined value or more. If it is determined that the luminance difference is greater than or equal to the predetermined value, the stationary object determination unit 38 determines that an edge element exists between the target point Paj + 1 and the reference point Prj + 1 that are the determination targets, and in step S38, The count value (bincount (i)) of the i-th attention line lai is counted up.
- step S37 determines in step S37 that the luminance difference is less than the predetermined value, the stationary object determination unit 38 determines that there is no edge element between the target point Paj + 1 and the reference point Prj + 1 as the determination target. Then, step S38 is skipped and the process proceeds to step S39.
- step S39 the stationary object determination unit 38 determines whether or not the process of step S34 or step S37 has been executed for all the attention points Paj on the attention line Lai that is currently being processed. If it is determined that the above process has not been executed for all the attention points Paj, the process returns to step S37 to obtain the luminance difference between the next attention point Paj + 1 and the reference point Prj + 1, and the luminance difference is a predetermined value. It is determined whether it is above. If it is determined in step S39 that the above processing has been executed for all the points of interest Paj, the process proceeds to step S41.
- the stationary object determination unit 38 counts how many edge elements exist along the same attention line Lai, and stores the counted even number of edge elements as an attribute (bincount (i)) of the attention line Lai.
- step S36 determines that there is no edge element on the attention line Lai that is currently the object of processing. to decide.
- the stationary object determination unit 38 substitutes “0” for bincount (i), and proceeds to step S41.
- step S41 if the above process is executed for all n attention lines Lai, the process proceeds to step S42. If the above process is not executed, the processes after step S34 are performed.
- the peak of the edge wrinkle distribution waveform is detected.
- step S44 the distance between each detected peak is calculated.
- step S45 peaks whose calculated peak-to-peak distance is within a predetermined range are extracted, and the number is counted.
- the stationary object determination unit 38 may cause the edge line detection unit 36 and the three-dimensional object detection unit 37 to perform edge detection processing and acquire the processing result.
- step S46 the stationary object determination unit 38 determines whether or not the number of peaks counted in step S46 is equal to or greater than a predetermined threshold Th2. If it is determined that the number of peaks is equal to or greater than the predetermined threshold Th2, the stationary object determination unit 38 determines that an object corresponding to each peak is a periodic stationary object candidate, and the process proceeds to step S47.
- step S47 the stationary object determination unit 38 determines whether or not a state in which the number of peaks is equal to or greater than a predetermined threshold Th2 has been continuously detected a predetermined number of times or more. If it is determined that a state in which the number of peaks is equal to or greater than the predetermined threshold Th2 has been continuously detected a predetermined number of times or more, the stationary object determination unit 38 is an object corresponding to each counted peak is a periodic stationary object. In step S48, “1” is substituted for the flag f_shuki.
- step S47 if it is determined in step S47 that the state in which the number of peaks is equal to or greater than the predetermined threshold Th2 has not been continuously detected a predetermined number of times or more, the stationary object determination unit 38 skips step S48 and sets the flag f_shuki Maintain the value of.
- step S47 If it is determined in step S47 that the number of peaks is less than the predetermined threshold Th2, the process proceeds to step S49, and the stationary object determination unit 38 is in a state where the number of peaks is less than the predetermined threshold Th2 in step S49. It is determined whether or not it has been continuously detected a predetermined number of times.
- the number of detections in a state where the number of peaks is less than the predetermined threshold Th2 may be an aspect of the periodicity evaluation value, and the predetermined number of times may be an aspect of the periodicity evaluation threshold.
- the predetermined number is the number of times as the second periodicity evaluation threshold set from the viewpoint of identifying the structure Q2 such as the guardrail described above, and the first periodicity evaluation threshold set from the viewpoint of identifying the other vehicle VX. And a threshold value. Both the threshold value Th2 and the predetermined number of times described above can be set as the periodicity evaluation threshold value. When it is determined that the state where the number of peaks is less than the predetermined threshold Th2 has been continuously detected a predetermined number of times or more, the stationary object determination unit 38 does not correspond to the counted peaks. In step S50, “0” is substituted for the flag f_shuki.
- step S49 when the state where the number of peaks is less than the predetermined threshold value Th2 has not been detected continuously for a predetermined number of times, the stationary object determination unit 38 skips step S50 and sets the value of the flag f_shuki. To maintain.
- edges (feature points) of a plurality of three-dimensional objects are extracted from image data of a predetermined area of a bird's-eye view image, and the distribution of edges in the predetermined area Calculate the edge distribution waveform (waveform data) corresponding to the number of three-dimensional objects based on whether the number of peaks (peak information) in the edge distribution waveform is equal to or greater than a predetermined threshold. It is determined whether or not. Therefore, as in the first embodiment, the periodicity (repeatability) of the periodic stationary object can be more clearly extracted as the peak information of the waveform data, and the periodicity can be extracted from the three-dimensional object included in the captured image. Target stationary object candidates can be extracted more easily. This makes it possible to extract a periodic stationary object with higher accuracy.
- the number of edge elements existing along the vertical imaginary line is integrated, and an edge distribution waveform is obtained based on the integrated number of edge elements. Then, when the number of peaks of the edge distribution waveform is equal to or greater than a predetermined threshold Th2, it is determined that a plurality of three-dimensional objects are periodic stationary object candidates. For this reason, even if it is not determined whether the detected three-dimensional object is a stationary object or a moving object, it is possible to reliably detect a case where edges extending in the vertical direction are arranged at high density, and to periodically stop Periodic stationary object candidates that are more likely to be objects can be detected more easily.
- the stationary object determination unit 38 detects irregular edge points that are irregularly arranged without satisfying the predetermined condition of the artificial three-dimensional object from the bird's-eye view image data of the detection areas A1 and A2 subjected to the viewpoint conversion by the viewpoint conversion unit 331.
- the predetermined condition of the artificial three-dimensional object is that edge points are arranged substantially linearly at a predetermined density or more on the bird's-eye view image data of the detection areas A1 and A2.
- the stationary object determination unit 38 can cause the edge line detection unit 36 and the three-dimensional object detection unit 37 to execute the edge information processing and acquire the processing result.
- FIG. 34 is a diagram showing edge points on the bird's-eye view image data of the detection area A1.
- the edge points P located in the regions R1 and R2 are arranged substantially linearly at a predetermined density or more, and satisfy a predetermined condition of an artificial three-dimensional object.
- the edge points P located outside the regions R1 and R2 are not substantially linearly arranged with a predetermined density or more, and do not satisfy the predetermined condition of the artificial three-dimensional object.
- the stationary object determination unit 38 detects an edge point P located outside the regions R1 and R2 among the plurality of edge points P as an irregular edge point P1.
- the stationary object determination unit 38 detects the edge point P from the bird's-eye view image data of the detection areas A1 and A2.
- the edge point P is detected by performing a binarization process by applying a Laplacian filter to the bird's-eye view image data.
- the stationary object determination unit 38 detects, among the detected edge points P, regular edge points P2 that are regularly arranged to satisfy a predetermined condition of the artificial solid object.
- the stationary object determination unit 38 detects regular edge points P2 in the bird's-eye view image data of the detection areas A1 and A2 on the condition that the edge points P are arranged in a radial direction from the camera 10 at a predetermined density or more.
- the stationary object determination unit 38 defines a straight line extending in the radial direction from the camera 10 and determines a region that falls within a predetermined pixel (for example, 10 pixels) from the straight line.
- the stationary object determination unit 38 determines that the edge points P in this region are arranged substantially linearly, and determines whether the edge points P in the region are located within a predetermined distance (predetermined pixel) from each other. Thus, it is determined whether or not they are arranged at a predetermined density or higher.
- the stationary object determination unit 38 subtracts the number of the regular edge points P2 from the number of the detected edge points P to obtain the number of the irregular edge points P1. Detect as a number.
- the stationary object determination unit 38 determines whether or not there is at least one of grass, mud, and snow that includes mottle and dirt in the detection areas A1 and A2. In the determination, the stationary object determination unit 38 refers to the number of detected irregular edge points P1.
- FIG. 35 is a diagram showing edge points P in the bird's-eye view image data of the detection area A1, (a) showing the edge points P of the vehicle (tire portion), (b) showing the grass edge points P, (C) shows an edge point P of snow.
- the vehicle (tire) is an artifact.
- the edge points P tend to be regularly arranged. Therefore, as shown in FIG. 35 (a), the number of irregular edge points P1 decreases and the regular edge points P2 tend to increase for the vehicle.
- grass and snow are not artificial three-dimensional objects, as shown in FIGS. 35 (b) and 35 (c), there are few edge points P (that is, regular edge points P2) arranged substantially linearly at a predetermined density.
- the stationary object determination unit 38 can determine grass or snow by comparing the number of irregular edge points P1 with a predetermined threshold value.
- the value of the irregular edge point P1 is an aspect of the irregularity evaluation value
- the predetermined threshold to be compared is an aspect of the irregularity evaluation threshold.
- the predetermined threshold includes at least a threshold as an irregularity evaluation threshold set from the viewpoint of identifying the shade Q1 and the grass / snow Q3.
- the stationary object determination unit 38 preferably detects grass or snow based on the ratio of the number of irregular edge points P1 to the number of edge points P or the number of regular edge points P2.
- the number of edge points P may increase or decrease under the influence of the light environment at the time of image capturing. For this reason, the stationary object determination unit 38 is less susceptible to the influence of the light environment to compare the ratio and the predetermined threshold than to simply compare the number of irregular edge points P1 and the predetermined threshold. Snow can be judged accurately.
- the ratio of the number of edge points P or the number of irregular edge points P1 to the number of regular edge points P2 is an aspect of the irregularity evaluation value
- the predetermined threshold value for the ratio to be compared is irregular. It is one aspect
- the predetermined threshold includes at least a threshold as an irregularity evaluation threshold set from the viewpoint of identifying the shade Q1 and the grass / snow Q3.
- FIG. 36 is a flowchart showing the snow / grass wall detection method according to this embodiment.
- the stationary object determination unit 38 first applies a Laplacian filter to the bird's-eye view image data obtained by the viewpoint conversion of the viewpoint conversion unit 31 (S1). As a result, the pixel value of the pixel corresponding to the edge point P is increased, and the pixel values of other pixels are decreased.
- the stationary object determination unit 38 performs the binarization process on the image on which the Laplacian filter is applied (S2) to clarify the edge point P. Then, the stationary object determination unit 38 counts the number N of edge points P (S3).
- the stationary object determination unit 38 detects the regular edge point P2 in the processing of steps S4 and S5, using the condition that the edge points P are arranged in a radial direction from the camera 10 at a predetermined density or more as a condition of the artificial solid object.
- the number M of regular edge points P2 is counted. That is, the stationary object determination unit 38 first detects a vertical edge (S4), and counts the number M of edge points P around the vertical edge (for example, within 10 pixels from the vertical edge) (S5).
- the stationary object determination unit 38 counts in step S3, and subtracts the number M of regular edge points P2 calculated in step S5 from the calculated number N of edge points P, whereby the number of irregular edge points P1.
- L is calculated (S6).
- the stationary object determination unit 38 calculates the ratio (S7).
- the stationary object determination unit 38 calculates the ratio of the number L of the irregular edge points P1 to the number N of the edge points P or the number M of the regular edge points P2 from the expression L / N or L / M. . As long as this ratio includes L / N or L / M, other numbers may be added or subtracted, or may be multiplied or divided.
- the stationary object determination unit 38 determines whether or not the ratio calculated in step S7 is equal to or greater than a predetermined threshold (S8).
- a predetermined threshold S8: YES
- the stationary object determination unit 38 determines that grass or snow exists in the detection areas A1 and A2 (S9).
- the control unit 39 transmits a control command for suppressing the detection or determination of the three-dimensional object to the three-dimensional object detection unit 37 and the three-dimensional object determination unit 34 (S10).
- the three-dimensional object detection unit 37 and the three-dimensional object determination unit 34 recognize that there is an image derived from grass or snow in the detection areas A1 and A2, and prevent erroneous detection of the grass or snow as the other vehicle VX. be able to.
- the stationary object determination unit 38 determines that there is no grass or snow image in the detection areas A1 and A2.
- the irregular edge point P1 that does not satisfy the predetermined condition of the artificial three-dimensional object and is irregularly arranged is detected. It is determined whether grass and snow exist based on the number L of regular edge points P1.
- the edge points P tend to be regularly arranged because they are artifacts.
- the edge points P are easily arranged irregularly because they are not artifacts. Therefore, the former and the latter can be distinguished from the number L of irregular edge points P1. Accordingly, it is possible to improve the determination accuracy of grass and snow.
- edge point P is detected from the image data in the detection areas A1 and A2, and the regular edge point P2 regularly arranged satisfying the condition of the predetermined artificial three-dimensional object is detected. Subtract. For this reason, irregular edge points P1 arranged irregularly can be detected by grasping the whole edge points P and subtracting the regular edge points P2.
- the ratio between the number N of edge points P or the number M of regular edge points P2 and the number L of irregular edge points P1 at least one of grass and snow exists in the detection areas A1 and A2. Determine whether. For this reason, even when the number of edge points P is detected more or less due to differences in the light environment, the number N of edge points P or the number M of regular edge points P2, and the irregular edge points
- the number L of P1 is detected in the same way as a large number or a small number. Therefore, it can be said that the ratio itself is hardly affected by the light environment. Therefore, it is possible to detect grass and snow that are not easily affected by changes in the light environment.
- the regular edge points P1 are extracted on the condition that the edge points are arranged in a substantially linear manner at a predetermined density or more in a state where the image data of the detection areas A1 and A2 are viewed from a bird's-eye view. For this reason, the regular edge point P1 is likely to be detected for an object having a large number of linear components such as an artificial object, and the regular edge point P1 is difficult to be detected for grass or snow. Therefore, grass and snow can be detected more accurately.
- the regular edge points P2 are detected on condition that the edge points P are arranged in a radial direction from the camera 10 in a radial direction in a state where the image data of the detection areas A1 and A2 are viewed in a bird's eye view. Therefore, a component extending in the vertical direction in the real space is detected as the regular edge point P2, and the vertical edge point P of the vehicle that is a three-dimensional object can be captured. The difference can be clarified.
- the irregularity of the edge described above can be grasped as a feature of the difference image information of the present invention. That is, when the difference image information is generated, a predetermined difference is calculated on the difference image along the direction in which the three-dimensional object falls when the viewpoint image of the bird's eye view image is converted on the difference image of the aligned bird's eye view image. The number of pixels of the indicated pixel is counted to form a frequency distribution, but a pixel indicating a predetermined difference on this difference image is treated as an edge in the irregularity processing, and the above method is applied based on the frequency distribution of this pixel. To determine irregularities.
- the periodicity evaluation value for evaluating periodicity and the irregularity for evaluating irregularity based on the difference waveform information or edge information of the captured image.
- the image information includes a shadow of a tree having periodicity and irregularity. Therefore, it is possible to prevent erroneous detection of the shadow of a tree existing along the traveling path of the vehicle as another vehicle traveling in the adjacent lane adjacent to the traveling lane of the own vehicle. .
- the periodicity evaluation value is greater than or equal to the first periodicity evaluation threshold and less than the second periodicity evaluation threshold
- the irregularity evaluation value is the irregularity evaluation value.
- the threshold it can be determined that the three-dimensional object detected by the three-dimensional object detection unit 33 is grass or snow Q3 existing along the traveling path of the host vehicle V.
- Grass / snow Q2 and tree shade Q1 both have irregularities, and it is not easy to identify them.
- tree shade Q1 and grass / snow Q2 are narrowed down based on the periodicity evaluation value. Therefore, by identifying the tree shade Q1 or the grass / snow Q2 based on the irregularity evaluation value, the tree shade Q1 can be accurately identified from the grass / snow Q2.
- the detected three-dimensional object is a structure Q2 such as a guardrail. It can be judged that there is. Since the periodicity of the structure Q2 such as the guardrail and the periodicity of the tree shade Q3 can be distinguished relatively clearly, by setting the second periodicity evaluation threshold based on the periodicity of the structure Q2 such as the guardrail, the tree shadow Q3 and grass / snow Q2 can be accurately distinguished from structures Q2 such as guardrails. As a result, the tree shade Q1 can be accurately identified.
- the detected three-dimensional object is a moving body, for example, another vehicle VX. Judgment can be made. Although the periodicity of the other vehicle VX and the periodicity of the grass / snow Q2 are both low, an identifiable difference can be found, so the first periodicity evaluation threshold is set based on the periodicity of the other vehicle VX. Thus, the shade Q3 and the grass / snow Q2 can be accurately identified from the other vehicle VX. As a result, the tree shade Q1 can be accurately identified.
- the first periodicity which is a lower threshold for determining grass / snow Q3 and shade Q1. Since the evaluation threshold value is changed to a high value, it is possible to easily determine that the three-dimensional object is the other vehicle VX. As a result, the tree shade Q1 can be accurately determined without failing to detect the other vehicle VX even in a dark situation. Since it is difficult to detect the periodicity of the other vehicle VX in a dark situation, it is preferable from the viewpoint of ensuring safety to easily determine that the three-dimensional object is the other vehicle VX.
- the first periodicity evaluation threshold that is a lower threshold for determining grass / snow Q3 and shade Q1 Because there are many advertising towers, billboards, and other structures, the shadow of Q1 or grass / snow Q3 reflected in the road detection areas A1 and A2 tends to be low.
- the periodicity of the shade Q1 can be accurately determined.
- the host vehicle is changed by increasing the first threshold value ⁇ . Since the detection sensitivity can be adjusted so that the other vehicle VX traveling next to the V traveling lane is not easily detected, it is possible to prevent erroneous detection of the image of the shade Q1 as the other vehicle VX traveling in the adjacent lane. .
- the output value when generating the differential waveform information is lowered.
- the detection sensitivity can be adjusted so that the other vehicle VX traveling next to the traveling lane of the host vehicle V is difficult to detect, the image of the shade Q1 is erroneously detected as the other vehicle VX traveling in the adjacent lane. Can be prevented.
- the threshold for determination when generating edge information is increased.
- the detection sensitivity can be adjusted so that the other vehicle VX traveling next to the traveling lane of the host vehicle V is difficult to detect, so the image of the shade Q1 is erroneously detected as the other vehicle VX traveling in the adjacent lane. Can be prevented.
- the camera 10 corresponds to an imaging unit according to the present invention
- the viewpoint conversion unit 31 corresponds to an image conversion unit according to the present invention
- the alignment unit 32 and the three-dimensional object detection unit 33 include a three-dimensional object detection according to the present invention.
- the brightness difference calculation unit 35, the edge line detection unit 36, and the three-dimensional object detection unit 37 correspond to a three-dimensional object detection unit according to the present invention
- the three-dimensional object determination unit 34 corresponds to a three-dimensional object determination unit.
- the stationary object determination unit 38 corresponds to a stationary object determination unit
- the control unit 39 corresponds to a control unit
- the vehicle speed sensor 20 corresponds to a vehicle speed sensor
- the brightness sensor 50 corresponds to a brightness detection unit.
- the current position detection device 60 corresponds to current position detection means.
- SYMBOLS 1 Three-dimensional object detection apparatus 10 ... Camera 20 ... Vehicle speed sensor 30 ... Computer 31 ... Viewpoint conversion part 32 ... Position alignment part 33, 37 ... Three-dimensional object detection part 34 ... Three-dimensional object judgment part 35 ... Luminance difference calculation part 36 ... Edge detection Unit 38 ... stationary object determination unit 40 ... smear detection unit 50 ... brightness sensor 60 ... current position sensors A1, A2 ... detection area CP ... intersection DP ... difference pixels DW t , DW t '... difference waveforms DW t1 to DW m , DW m + k to DW tn ... small areas L1, L2 ... ground lines La and Lb ...
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
Description
本出願は、2012年4月16日に出願された日本国特許出願の特願2012―092912に基づく優先権を主張するものであり、文献の参照による組み込みが認められる指定国については、上記の出願に記載された内容を参照により本出願に組み込み、本出願の記載の一部とする。
本実施形態の立体物検出装置1は、車両後方を撮像する単眼のカメラ1により得られた画像情報に基づいて車両後方の右側隣接車線の検出領域A1又は左側隣接車線の検出領域A2に存在する立体物を検出する。検出領域設定部34は、撮像された画像情報内であって、自車両Vの後方の右側及び左側のそれぞれに検出領域A1,A2を設定する。この検出領域A2,A2の位置は特に限定されず、また、処理条件に応じて適宜に設定することができる。
次に、図3に示すブロックAに代えて動作させることが可能である、輝度差算出部35、エッジ線検出部36及び立体物検出部37で構成されるエッジ情報を利用した立体物の検出ブロックBについて説明する。図13は、図3のカメラ10の撮像範囲等を示す図であり、図13(a)は平面図、図13(b)は、自車両Vから後側方における実空間上の斜視図を示す。図13(a)に示すように、カメラ10は所定の画角aとされ、この所定の画角aに含まれる自車両Vから後側方を撮像する。カメラ10の画角aは、図2に示す場合と同様に、カメラ10の撮像範囲に自車両Vが走行する車線に加えて、隣接する車線も含まれるように設定されている。
[数1]
I(xi,yi)>I(xi’,yi’)+tのとき
s(xi,yi)=1
I(xi,yi)<I(xi’,yi’)-tのとき
s(xi,yi)=-1
上記以外のとき
s(xi,yi)=0
[数2]
s(xi,yi)=s(xi+1,yi+1)のとき(且つ0=0を除く)、
c(xi,yi)=1
上記以外のとき、
c(xi,yi)=0
[数3]
Σc(xi,yi)/N>θ
[数4]
鉛直相当方向の評価値=Σ[{I(xi,yi)-I(xi+1,yi+1)}2]
[数5]
鉛直相当方向の評価値=Σ|I(xi,yi)-I(xi+1,yi+1)|
[数6]
鉛直相当方向の評価値=Σb(xi,yi)
但し、|I(xi,yi)-I(xi+1,yi+1)|>t2のとき、
b(xi,yi)=1
上記以外のとき、
b(xi,yi)=0
図3に戻り、本例の立体物検出装置1は、上述した2つの立体物検出部33(又は立体物検出部37)と、立体物判断部34と、静止物判断部38と、制御部39とを備える。立体物判断部34は、立体物検出部33(又は立体物検出部37)による検出結果に基づいて、検出された立体物が検出領域A1,A2に存在する他車両VXであるか否かを最終的に判断する。立体物検出部33(又は立体物検出部37)は、静止物判断部38の判断結果を反映させた立体物の検出を行う。静止物判断部38は、立体物検出部33(又は立体物検出部37)により検出された立体物が自車両Vの走行路に沿って存在する樹木の影であるか否かを判断する。
また、周期性評価地が低く、かつ不規則性も低い場合には、検出された立体物は他車両である可能性が高い。
なお、エッジ情報に基づいて周期性及び不規則性を算出する具体的な手法は後に詳述する。
制御部39は、前回の処理で、静止物判断部38により検出された立体物は樹木の影である可能性が高いと判断された場合には、検出領域A1,A2に樹木の影が映り込んでおり、画像情報に基づく処理に誤りが発生する可能性が高いと判断する。このまま、通常と同じ手法で立体物を検出すると、検出領域A1,A2に映り込んだ木陰Qの像に基づいて検出された立体物を誤って他車両VXと判断する場合がある。このため、本実施形態の制御部39は、次回の処理においては、木陰Qの像に基づいて検出された立体物が誤って他車両VXと判断されることを抑制するために、差分波形情報を生成する際の画素値の差分に関する閾値を高く変更する。このように、検出領域A1,A2に木陰Q1が映り込んでいる場合には、判断の閾値を高く変更することにより、立体物の検出又は他車両VXであるとの判断が抑制されるので、木陰Q1に起因する誤検出することを防止することができる。
静止物判断部38は視点変換部331により視点変換された検出領域A1,A2の鳥瞰視画像データから、予め定められた人工的立体物の条件を満たさず不規則に並ぶ不規則エッジ点を検出するものである。ここで、予め定められた人工的立体物の条件とは、検出領域A1,A2の鳥瞰視画像データ上において、略直線的に所定密度以上でエッジ点が並んでいることである。なお不規則性の判断処理において、静止物判断部38は、エッジ情報の処理を、エッジ線検出部36、立体物検出部37に実行させ、その処理結果を取得することができる。
(1)本実施形態の立体物検出装置1によれば、撮像画像の差分波形情報又はエッジ情報に基づいて周期性を評価するための周期性評価値と不規則性を評価するための不規則性評価値とを算出し、周期性評価値が所定値域内であり、不規則性評価値が所定の閾値以上である場合に周期性と不規則性を備える樹木の影が画像情報に含まれていることを識別することができるので、車両の走行路に沿って存在する樹木の影を自車両の走行車線の隣の隣接車線を走行する他車両として誤検出することを防止することができる。この結果、自車両の走行車線の隣の隣接車線を走行する他車両VXを、高い精度で検出する立体物検出装置を提供することができる。
差分波形情報に基づく処理であっても、エッジ情報に基づく処理であっても同様の作用及び効果を奏する。
10…カメラ
20…車速センサ
30…計算機
31…視点変換部
32…位置合わせ部
33,37…立体物検出部
34…立体物判断部
35…輝度差算出部
36…エッジ検出部
38…静止物判断部
40…スミア検出部
50…明るさセンサ
60…現在位置センサ
A1,A2…検出領域
CP…交点
DP…差分画素
DWt,DWt’…差分波形
DWt1~DWm,DWm+k~DWtn…小領域
L1,L2…接地線
La,Lb…立体物が倒れ込む方向上の線
P…撮像画像
PBt…鳥瞰視画像
PDt…差分画像
MP…マスク画像
S…スミア
SP…スミア画像
SBt…スミア鳥瞰視画像
V…自車両
VX…他車両
Claims (13)
- 車両に搭載され、車両後方を撮像する撮像手段と、
前記撮像手段により得られた画像を鳥瞰視画像に視点変換する画像変換手段と、
前記画像変換手段により得られた異なる時刻の鳥瞰視画像の位置を鳥瞰視上で位置合わせし、当該位置合わせされた鳥瞰視画像の差分画像上において、前記鳥瞰視画像を視点変換した際に立体物が倒れ込む方向に沿って、前記差分画像上において所定の差分を示す画素数をカウントして度数分布化することで差分波形情報を生成し、当該差分波形情報に基づいて、前記車両後方の右側及び左側のそれぞれに設定された検出領域に存在する立体物を検出する立体物検出手段と、を備え、
前記差分波形情報に基づいて、当該差分波形情報の周期性を評価するための周期性評価値を算出するとともに、前記差分波形情報に基づいて、当該差分波形情報の不規則性を評価するための不規則性評価値を算出し、前記算出された周期性評価値が第1周期性評価閾値以上かつ第2周期性評価閾値未満であり、前記算出された不規則性評価値が所定の不規則性評価閾値未満である場合には、前記立体物検出手段により検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断する静止物判断手段と、
前記立体物検出手段により検出された立体物が前記検出領域に存在する他車両であるか否かを判断する立体物判断手段と、
前記静止物判断手段により前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記立体物判断手段により前記検出された立体物が他車両であると判断されることを抑制する制御手段と、を備えることを特徴とする立体物検出装置。 - 車両に搭載され、車両後方を撮像する撮像手段と、
前記撮像手段により得られた画像を鳥瞰視画像に視点変換する画像変換手段と、
前記画像変換手段により得られた鳥瞰視画像において、鳥瞰視画像に視点変換した際に立体物が倒れ込む方向に沿って、互いに隣接する画像領域の輝度差が所定閾値以上であるエッジ情報を検出し、当該エッジ情報に基づいて前記車両後方の右側及び左側のそれぞれに設定された検出領域に存在する立体物を検出する立体物検出手段と、を備え、
前記エッジ情報に基づいて、当該エッジ情報の周期性を評価するための周期性評価値を算出するとともに、前記エッジ情報に基づいて、当該エッジ情報の不規則性を評価するための不規則性評価値を算出し、前記算出された周期性評価値が第1周期性評価閾値以上かつ第2周期性評価閾値未満であり、前記算出された不規則性評価値が所定の不規則性評価閾値未満である場合には、前記立体物検出手段により検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断する静止物判断手段と、
前記立体物検出手段により検出された立体物が前記検出領域に存在する他車両であるか否かを判断する立体物判断手段と、
前記静止物判断手段により前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記立体物判断手段により前記検出された立体物が他車両であると判断されることを抑制する制御手段と、を備えることを特徴とする立体物検出装置。 - 前記静止物判断手段は、前記算出された周期性評価値が第1周期性評価閾値未満である場合には、前記立体物検出手段により検出された立体物が移動体であると判断することを特徴とする請求項1又は2に記載の立体物検出装置。
- 前記車両周囲の明るさを検出する明るさ検出手段をさらに備え、
前記静止物判断手段は、明るさ検出手段により検出された明るさが所定値未満である場合には、第1周期性評価閾値を高い値に変更することを特徴とする請求項1~3の何れか一項に記載の立体物検出装置。 - 前記車両の現在位置を検出する現在位置検出手段をさらに備え、
前記静止物判断手段は、各位置情報に当該位置が都市地域であるか郊外地域であるかの情報を対応づけた地図情報を参照し、現在位置検出手段により検出された現在位置が都市地域に含まれる場合には、第1周期性評価閾値を低い値に変更することを特徴とする請求項1~4の何れか一項に記載の立体物検出装置。 - 前記制御手段は、前記静止物判断手段により前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記立体物の判断処理を中止する内容の制御命令又は前記検出された立体物が他車両ではないと判断する内容の制御命令を生成し、前記立体物判断手段に出力することを特徴とする請求項1~5の何れか一項に記載の立体物検出装置。
- 前記立体物検出手段は、前記差分波形情報と第1閾値αとに基づいて立体物を検出し、
前記制御手段は、前記静止物判断手段により前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記第1閾値αを前記立体物が検出され難いように高く変更する制御命令を前記立体物検出手段に出力することを特徴とする請求項1に従属する請求項3~6の何れか一項に記載の立体物検出装置。 - 前記制御手段は、前記静止物判断手段により前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記鳥瞰視画像の差分画像上において所定の差分を示す画素数をカウントして度数分布化された値を低くする制御命令を生成し、当該制御命令を前記立体物検出手段に出力することを特徴とする請求項7に記載の立体物検出装置。
- 前記立体物検出手段は、前記エッジ情報と第2閾値βとに基づいて立体物を検出し、
前記制御手段は、前記静止物判断手段により前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記第2閾値βを前記立体物が検出され難いように高く変更する制御命令を前記立体物検出手段に出力することを特徴とする請求項2に従属する請求項3~6の何れか一項に記載の立体物検出装置。 - 前記制御手段は、前記静止物判断手段により前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記検出したエッジ情報の量を低く出力する制御命令を前記立体物検出手段に出力することを特徴とする請求項9に記載の立体物検出装置。
- 前記静止物判断手段は、前記算出された周期性評価値が第1周期性評価閾値未満であり、かつ前記算出された不規則性評価値が所定の不規則性評価閾値未満である場合には、前記立体物検出手段により検出された立体物が移動体であると判断し、
前記制御手段は、前記静止物判断手段により前記検出された立体物が移動体であると判断された場合には、前記立体物判断手段により前記検出された立体物が他車両であると判断させることを特徴とする請求項1~10の何れか一項に記載の立体物検出装置。 - 車両に搭載されたカメラにより撮像された車両後方の画像情報を鳥瞰視画像に視点変換するステップと、
前記支店変換された異なる時刻の鳥瞰視画像の位置を鳥瞰視上で位置合わせし、当該位置合わせされた鳥瞰視画像の差分画像上において、前記鳥瞰視画像を視点変換した際に立体物が倒れ込む方向に沿って、前記差分画像上において所定の差分を示す画素数をカウントして度数分布化することで差分波形情報を生成し、当該差分波形情報に基づいて、前記車両後方の右側及び左側のそれぞれに設定された検出領域に存在する立体物を検出するステップと、
前記検出された立体物が前記検出領域に存在する他車両であるか否かを判断するステップと、
前記差分波形情報に基づいて、当該差分波形情報の周期性を評価するための周期性評価値を算出するとともに、前記差分波形情報に基づいて、当該差分波形情報の不規則性を評価するための不規則性評価値を算出し、前記算出された周期性評価値が第1周期性評価閾値以上かつ第2周期性評価閾値未満であり、前記算出された不規則性評価値が所定の不規則性評価閾値未満である場合には、前記立体物検出手段により検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断するステップと、
前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記検出された立体物が他車両であると判断されることを抑制するステップと、を備えることを特徴とする立体物検出方法。 - 車両に搭載されたカメラにより撮像された車両後方の画像情報を鳥瞰視画像に視点変換するステップと、
前記得られた鳥瞰視画像において、鳥瞰視画像に視点変換した際に立体物が倒れ込む方向に沿って、互いに隣接する画像領域の輝度差が所定閾値以上であるエッジ情報を検出し、当該エッジ情報に基づいて前記車両後方の右側及び左側のそれぞれに設定された検出領域に存在する立体物を検出するステップと、
前記検出された立体物が前記検出領域に存在する他車両であるか否かを判断するステップと、
前記エッジ情報に基づいて、当該エッジ情報の周期性を評価するための周期性評価値を算出するとともに、前記エッジ情報に基づいて、当該エッジ情報の不規則性を評価するための不規則性評価値を算出し、前記算出された周期性評価値が第1周期性評価閾値以上かつ第2周期性評価閾値未満であり、前記算出された不規則性評価値が所定の不規則性評価閾値未満である場合には、前記立体物検出手段により検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断するステップと、
前記検出された立体物が前記自車両の走行路に沿って存在する樹木の影であると判断された場合には、前記検出された立体物が他車両であると判断されることを抑制するステップと、を有することを特徴とする立体物検出方法。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/385,540 US9141870B2 (en) | 2012-04-16 | 2013-02-25 | Three-dimensional object detection device and three-dimensional object detection method |
CN201380020430.3A CN104246821B (zh) | 2012-04-16 | 2013-02-25 | 三维物体检测装置和三维物体检测方法 |
JP2014511132A JP5867596B2 (ja) | 2012-04-16 | 2013-02-25 | 立体物検出装置及び立体物検出方法 |
EP13778354.4A EP2843615B1 (en) | 2012-04-16 | 2013-02-25 | Device for detecting three-dimensional object and method for detecting three-dimensional object |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012-092912 | 2012-04-16 | ||
JP2012092912 | 2012-04-16 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013157301A1 true WO2013157301A1 (ja) | 2013-10-24 |
Family
ID=49383270
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/054765 WO2013157301A1 (ja) | 2012-04-16 | 2013-02-25 | 立体物検出装置及び立体物検出方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US9141870B2 (ja) |
EP (1) | EP2843615B1 (ja) |
JP (1) | JP5867596B2 (ja) |
CN (1) | CN104246821B (ja) |
WO (1) | WO2013157301A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017076276A (ja) * | 2015-10-15 | 2017-04-20 | 株式会社日本自動車部品総合研究所 | 静止物検出装置、及びプログラム |
CN110088803A (zh) * | 2016-12-26 | 2019-08-02 | 日立汽车系统株式会社 | 摄像装置 |
JP2021177136A (ja) * | 2020-05-07 | 2021-11-11 | 株式会社トヨタマップマスター | 情報処理装置、情報処理方法及び情報処理プログラム |
Families Citing this family (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5413516B2 (ja) * | 2010-08-19 | 2014-02-12 | 日産自動車株式会社 | 立体物検出装置及び立体物検出方法 |
JP5614504B2 (ja) * | 2011-09-12 | 2014-10-29 | 日産自動車株式会社 | 立体物検出装置 |
JP5708689B2 (ja) * | 2013-03-13 | 2015-04-30 | 株式会社デンソー | 物体検出装置 |
DE102013216994A1 (de) * | 2013-08-27 | 2015-03-05 | Robert Bosch Gmbh | Geschwindigkeitsassistent für ein Kraftfahrzeug |
US9903719B2 (en) * | 2013-09-03 | 2018-02-27 | Litel Instruments | System and method for advanced navigation |
US10223800B2 (en) * | 2014-03-28 | 2019-03-05 | Hewlett-Packard Development Company, L.P. | Determine presence of quasi-periodic two-dimensional object |
DE102014105297A1 (de) * | 2014-04-14 | 2015-10-15 | Connaught Electronics Ltd. | Verfahren zum Detektieren eines Objekts in einem Umgebungsbereich eines Kraftfahrzeugs mittels eines Kamerasystems des Kraftfahrzeugs, Kamerasystem und Kraftfahrzeug |
US10929702B2 (en) * | 2015-09-10 | 2021-02-23 | Sync-Rx, Ltd | Automatic image feature removal |
US10019805B1 (en) * | 2015-09-29 | 2018-07-10 | Waymo Llc | Detecting vehicle movement through wheel movement |
JP6466811B2 (ja) * | 2015-09-30 | 2019-02-06 | 株式会社Soken | 走行区画線認識装置 |
JP6623729B2 (ja) * | 2015-12-04 | 2019-12-25 | 株式会社ソシオネクスト | 測距システム、移動体及び部品 |
DE102016003424B4 (de) * | 2016-03-21 | 2023-09-28 | Elektrobit Automotive Gmbh | Verfahren und Vorrichtung zum Erkennen von Verkehrszeichen |
US10183677B2 (en) * | 2016-09-20 | 2019-01-22 | Ford Global Technologies, Llc | Ice and snow detection systems and methods |
US10339708B2 (en) * | 2016-11-01 | 2019-07-02 | Google Inc. | Map summarization and localization |
US10671873B2 (en) * | 2017-03-10 | 2020-06-02 | Tusimple, Inc. | System and method for vehicle wheel detection |
DE112017007347T5 (de) * | 2017-03-30 | 2019-12-12 | Mitsubishi Electric Corporation | Objekterkennungsvorrichtung und fahrzeug |
US10789727B2 (en) * | 2017-05-18 | 2020-09-29 | Panasonic Intellectual Property Corporation Of America | Information processing apparatus and non-transitory recording medium storing thereon a computer program |
JP7072641B2 (ja) * | 2018-04-16 | 2022-05-20 | 三菱電機株式会社 | 路面検出装置、路面検出装置を利用した画像表示装置、路面検出装置を利用した障害物検知装置、路面検出方法、路面検出方法を利用した画像表示方法、および路面検出方法を利用した障害物検知方法 |
JP7327992B2 (ja) | 2019-05-10 | 2023-08-16 | フォルシアクラリオン・エレクトロニクス株式会社 | 立体物検出装置、及び立体物検出方法 |
JP2022548645A (ja) | 2019-09-17 | 2022-11-21 | カーボン オートノマス ロボティック システムズ, インコーポレイテッド | 自律レーザ雑草根絶 |
CN114730526A (zh) * | 2019-11-28 | 2022-07-08 | 三菱电机株式会社 | 物体识别装置、物体识别方法及物体识别程序 |
CN111160214B (zh) * | 2019-12-25 | 2022-03-15 | 电子科技大学 | 一种基于数据融合的3d目标检测方法 |
US20220299635A1 (en) * | 2021-03-17 | 2022-09-22 | Carbon Autonomous Robotic Systems Inc. | Systems and methods for point to point object matching and targeting |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007219393A (ja) * | 2006-02-20 | 2007-08-30 | Doshisha | 画像から音楽を生成する音楽生成装置 |
JP2008158958A (ja) * | 2006-12-26 | 2008-07-10 | Nissan Motor Co Ltd | 路面判別方法および路面判別装置。 |
JP2008219063A (ja) | 2007-02-28 | 2008-09-18 | Sanyo Electric Co Ltd | 車両周辺監視装置及び方法 |
JP2008227646A (ja) | 2007-03-09 | 2008-09-25 | Clarion Co Ltd | 障害物検知装置 |
JP2009265783A (ja) * | 2008-04-23 | 2009-11-12 | Sanyo Electric Co Ltd | 運転支援システム及び車両 |
JP2010533282A (ja) * | 2007-06-08 | 2010-10-21 | テレ アトラス ベスローテン フエンノートシャップ | 多視点パノラマを生成する方法及び装置 |
JP2011198007A (ja) | 2010-03-19 | 2011-10-06 | Konica Minolta Business Technologies Inc | プレゼンテーションシステム、管理装置およびプログラム |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6411898B2 (en) * | 2000-04-24 | 2002-06-25 | Matsushita Electric Industrial Co., Ltd. | Navigation device |
DE10035223A1 (de) * | 2000-07-20 | 2002-01-31 | Daimler Chrysler Ag | Vorrichtung und Verfahren zur Überwachung der Umgebung eines Objekts |
JP4596978B2 (ja) * | 2005-03-09 | 2010-12-15 | 三洋電機株式会社 | 運転支援システム |
JP2010141836A (ja) | 2008-12-15 | 2010-06-24 | Sanyo Electric Co Ltd | 障害物検知装置 |
JP5251927B2 (ja) | 2010-06-21 | 2013-07-31 | 日産自動車株式会社 | 移動距離検出装置及び移動距離検出方法 |
JP5413516B2 (ja) * | 2010-08-19 | 2014-02-12 | 日産自動車株式会社 | 立体物検出装置及び立体物検出方法 |
MX321872B (es) | 2011-02-21 | 2014-07-11 | Nissan Motor | Sistema de deteccion de objeto estacionario periodico y metodo de deteccion de objeto estacionario periodico. |
JP5614504B2 (ja) | 2011-09-12 | 2014-10-29 | 日産自動車株式会社 | 立体物検出装置 |
-
2013
- 2013-02-25 EP EP13778354.4A patent/EP2843615B1/en active Active
- 2013-02-25 JP JP2014511132A patent/JP5867596B2/ja active Active
- 2013-02-25 CN CN201380020430.3A patent/CN104246821B/zh active Active
- 2013-02-25 US US14/385,540 patent/US9141870B2/en active Active
- 2013-02-25 WO PCT/JP2013/054765 patent/WO2013157301A1/ja active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007219393A (ja) * | 2006-02-20 | 2007-08-30 | Doshisha | 画像から音楽を生成する音楽生成装置 |
JP2008158958A (ja) * | 2006-12-26 | 2008-07-10 | Nissan Motor Co Ltd | 路面判別方法および路面判別装置。 |
JP2008219063A (ja) | 2007-02-28 | 2008-09-18 | Sanyo Electric Co Ltd | 車両周辺監視装置及び方法 |
JP2008227646A (ja) | 2007-03-09 | 2008-09-25 | Clarion Co Ltd | 障害物検知装置 |
JP2010533282A (ja) * | 2007-06-08 | 2010-10-21 | テレ アトラス ベスローテン フエンノートシャップ | 多視点パノラマを生成する方法及び装置 |
JP2009265783A (ja) * | 2008-04-23 | 2009-11-12 | Sanyo Electric Co Ltd | 運転支援システム及び車両 |
JP2011198007A (ja) | 2010-03-19 | 2011-10-06 | Konica Minolta Business Technologies Inc | プレゼンテーションシステム、管理装置およびプログラム |
Non-Patent Citations (1)
Title |
---|
See also references of EP2843615A4 |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017076276A (ja) * | 2015-10-15 | 2017-04-20 | 株式会社日本自動車部品総合研究所 | 静止物検出装置、及びプログラム |
CN110088803A (zh) * | 2016-12-26 | 2019-08-02 | 日立汽车系统株式会社 | 摄像装置 |
CN110088803B (zh) * | 2016-12-26 | 2023-05-12 | 日立安斯泰莫株式会社 | 摄像装置 |
JP2021177136A (ja) * | 2020-05-07 | 2021-11-11 | 株式会社トヨタマップマスター | 情報処理装置、情報処理方法及び情報処理プログラム |
JP7417466B2 (ja) | 2020-05-07 | 2024-01-18 | 株式会社トヨタマップマスター | 情報処理装置、情報処理方法及び情報処理プログラム |
Also Published As
Publication number | Publication date |
---|---|
US20150071490A1 (en) | 2015-03-12 |
EP2843615A1 (en) | 2015-03-04 |
US9141870B2 (en) | 2015-09-22 |
EP2843615B1 (en) | 2016-12-07 |
CN104246821A (zh) | 2014-12-24 |
EP2843615A4 (en) | 2015-05-27 |
JPWO2013157301A1 (ja) | 2015-12-21 |
CN104246821B (zh) | 2016-08-17 |
JP5867596B2 (ja) | 2016-02-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5867596B2 (ja) | 立体物検出装置及び立体物検出方法 | |
JP5997276B2 (ja) | 立体物検出装置及び異物検出装置 | |
JP5614504B2 (ja) | 立体物検出装置 | |
JP5896027B2 (ja) | 立体物検出装置及び立体物検出方法 | |
JP5776795B2 (ja) | 立体物検出装置 | |
JP5874831B2 (ja) | 立体物検出装置 | |
JP5682735B2 (ja) | 立体物検出装置 | |
JP5794378B2 (ja) | 立体物検出装置及び立体物検出方法 | |
JP5783319B2 (ja) | 立体物検出装置及び立体物検出方法 | |
JP5871069B2 (ja) | 立体物検出装置及び立体物検出方法 | |
WO2013125335A1 (ja) | 立体物検出装置及び立体物検出方法 | |
JP6003987B2 (ja) | 立体物検出装置及び立体物検出方法 | |
WO2013129360A1 (ja) | 立体物検出装置 | |
JP5768927B2 (ja) | 立体物検出装置 | |
JP5817913B2 (ja) | 立体物検出装置及び立体物検出方法 | |
WO2013129359A1 (ja) | 立体物検出装置 |
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: 13778354 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2014511132 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14385540 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2013778354 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2013778354 Country of ref document: EP |