JP6020568B2 - Three-dimensional object detection apparatus and three-dimensional object detection method - Google Patents

Description

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. 2012-166513 filed on July 27, 2012. For designated countries that are allowed to be incorporated by reference, 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.

  2. Description of the Related Art Conventionally, there is known a technique for converting two captured images captured at different times into a bird's-eye view image and detecting a three-dimensional object based on the difference between the two converted bird's-eye view images (Patent Literature). 1).

JP 2008-227646 A

  When a solid object existing in a predetermined detection area is detected as an adjacent vehicle based on a captured image captured by the camera, if a foreign object such as a raindrop is attached to the lens of the camera, the foreign object such as a raindrop Even if the adjacent vehicle can be detected once in the detection area, the adjacent vehicle can be continuously detected while the adjacent vehicle exists in the detection area. There were cases where it was difficult.

  The problem to be solved by the present invention is to provide a three-dimensional object detection device that can appropriately detect an adjacent vehicle even when foreign matter such as raindrops adheres to a lens of a camera.

  The present invention detects a three-dimensional object based on a captured image, calculates the movement speed of the detected three-dimensional object as a first movement speed, and calculates the movement speed of the three-dimensional object from the time change of the light source existing behind the host vehicle. Calculated as the second moving speed, and based on the first moving speed and the second moving speed, the relative moving speed of the three-dimensional object in consideration of the adhesion of foreign matter on the lens is calculated as the estimated moving speed, and based on the estimated moving speed, The relative movement distance that the three-dimensional object has moved after the detection of the object is calculated as the detection determination distance. Then, at the first timing when the three-dimensional object is detected, the detection of the three-dimensional object is promoted, and after the first timing, the detection determination distance is promoted at the second timing at which the detection determination distance is equal to or greater than a predetermined reference distance. The above-described problem is solved by suppressing detection of a three-dimensional object.

  According to the present invention, detection of a three-dimensional object or another vehicle is promoted at the first timing when the three-dimensional object is detected, the detection determination distance becomes equal to or greater than a predetermined reference distance, and the three-dimensional object (other vehicle) exists in the detection region. Since the detection of the three-dimensional object or other vehicle is suppressed at the second timing at which it can be determined that the three-dimensional object or other vehicle does not exist, even if a foreign object such as raindrops is attached to the lens, It is possible to continuously detect the three-dimensional object while it is in the room.

It is a schematic block diagram of the vehicle carrying a solid-object detection apparatus. It is a top view which shows the driving state of the vehicle of FIG. It is a block diagram which shows the detail of a computer. It is a figure for demonstrating the outline | summary of the process of a position alignment part, (a) is a top view which shows the movement state of a vehicle, (b) is an image which shows the outline | summary of position alignment. It is the schematic which shows the mode of the production | generation of the difference waveform by a solid-object detection part. It is a figure which shows an example of threshold value (alpha) for detecting a differential waveform and a solid object. It is a figure which shows the small area | region divided | segmented by the solid-object detection part. It is a figure which shows an example of the histogram obtained by a solid-object detection part. It is a figure which shows the weighting by a solid-object detection part. It is a figure which shows the other example of the histogram obtained by a solid-object detection part. It is a figure which shows an example of the captured image imaged when the raindrop has adhered to the lens of the camera. (A) is a figure which shows an example of the differential waveform produced | generated in the scene where the adjacent vehicle exists in a detection area, but the raindrop does not adhere to the position corresponding to this detection area, (B) FIG. 6B is a diagram illustrating an example of a differential waveform generated in a scene in which no adjacent vehicle exists in the detection area but raindrops are attached to a position corresponding to the detection area, and FIG. It is a figure which shows an example of the difference waveform produced | generated in the scene where the adjacent vehicle exists in an area | region, and the raindrop has adhered to the position corresponding to this detection area. (A) is a figure which shows an example of the difference vehicle speed when the foreign material has adhered to the lens, and the difference vehicle speed when the foreign material has adhered to the lens, (B) is the difference vehicle speed shown to (A). It is a figure which shows the movement distance of the adjacent vehicle calculated based on. (A) is a figure which shows an example of the headlight vehicle speed when the foreign material has adhered to the lens, and the headlight vehicle speed when the foreign material has adhered to the lens, (B) is shown to (A). It is a figure which shows the moving distance of the adjacent vehicle calculated based on the headlight vehicle speed. It is a figure which shows an example of the relationship between the weight Whl of the headlight vehicle speed at the time of calculating an estimated vehicle speed, the weight Wsa of a difference vehicle speed, and the adhesion amount of foreign matters, such as a raindrop, in a lens. It is a figure for demonstrating the detection determination distance Dist. It is a flowchart which shows the adjacent vehicle detection process which concerns on 1st Embodiment. It is a flowchart which shows the threshold value change process which concerns on 1st Embodiment. It is a block diagram which shows the detail of the computer which concerns on 2nd Embodiment. It is a figure which shows the driving | running | working state of a vehicle, (a) is a top view which shows positional relationships, such as a detection area, (b) is a perspective view which shows positional relationships, such as a detection area in real space. It is a figure for demonstrating operation | movement of the brightness | luminance difference calculation part which concerns on 2nd Embodiment, (a) is a figure which shows the positional relationship of the attention line, reference line, attention point, and reference point in a bird's-eye view image, (b). FIG. 4 is a diagram illustrating a positional relationship among attention lines, reference lines, attention points, and reference points in real space. It is a figure for demonstrating the detailed operation | movement of the brightness | luminance difference calculation part which concerns on 2nd Embodiment, (a) is a figure which shows the detection area | region in a bird's-eye view image, (b) is the attention line and reference line in a bird's-eye view image. It is a figure which shows the positional relationship of an attention point and a reference point. It is a figure which shows the example of an image for demonstrating edge detection operation | movement. It is a figure which shows the luminance distribution on an edge line and an edge line, (a) is a figure which shows luminance distribution in case a solid object (adjacent vehicle) exists in a detection area, (b) is a figure which shows a solid object in a detection area. It is a figure which shows the luminance distribution when it does not exist. It is a flowchart which shows the adjacent vehicle detection method which concerns on 2nd Embodiment. It is a flowchart which shows the threshold value change process which concerns on 2nd Embodiment. It is a block diagram which shows the detail of the computer which concerns on 3rd Embodiment. It is a block diagram which shows the detail of the computer which concerns on 4th Embodiment.

<< First Embodiment >>
FIG. 1 is a schematic configuration diagram of a vehicle equipped with a three-dimensional object detection device 1 according to the present embodiment. The three-dimensional object detection device 1 according to the present embodiment is intended to detect another vehicle (hereinafter also referred to as an adjacent vehicle V2) existing in an adjacent lane that may be contacted when the host vehicle V1 changes lanes. To do. As shown in FIG. 1, the three-dimensional object detection device 1 according to the present embodiment includes a camera 10, a vehicle speed sensor 20, and a calculator 30.

  As shown in FIG. 1, the camera 10 is attached to the vehicle V <b> 1 so that the optical axis is at an angle θ from the horizontal to the lower side at the position of the height h behind the host vehicle V <b> 1. The camera 10 captures an image of a predetermined area in the surrounding environment of the host vehicle V1 from this position. The vehicle speed sensor 20 detects the traveling speed of the host vehicle V1, 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 an adjacent vehicle existing in an adjacent lane behind the host vehicle.

  FIG. 2 is a plan view showing a traveling state of the host vehicle V1 of FIG. As shown in the figure, the camera 10 images the vehicle rear side at a predetermined angle of view a. At this time, the angle of view a of the camera 10 is set to an angle of view at which the left and right lanes (adjacent lanes) can be imaged in addition to the lane in which the host vehicle V1 travels.

  FIG. 3 is a block diagram showing details of the computer 30 of FIG. In FIG. 3, the camera 10 and the vehicle speed sensor 20 are also illustrated in order to clarify the connection relationship.

  As shown in FIG. 3, the computer 30 includes a viewpoint conversion unit 31, an alignment unit 32, a difference waveform generation unit 33, a three-dimensional object detection unit 34, a difference vehicle speed calculation unit 35, and a headlight detection unit 36. , A headlight vehicle speed calculation unit 37, an estimated vehicle speed calculation unit 38, a detection determination distance calculation unit 39, and a threshold value change unit 40. Below, each structure is demonstrated.

  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 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.

  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 V1, and FIG. 4B is an image showing the outline of the alignment.

As shown in FIG. 4 (a), the host vehicle V1 of the current time is located in P _1, one unit time before the vehicle V1 is located in the P _{1 '.} Further, there is a parallel running state with the vehicle V1 is located is adjacent vehicle V2 laterally after the vehicle V1, located in P ₂ adjacent vehicle V2 is the current time, one unit time before the adjacent vehicle V2 is P ₂ Suppose it is located at '. Furthermore, it is assumed that the host vehicle V1 has moved a distance d at one time. Note that “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.

In this state, the bird's-eye view image PB _t at the current time is as shown in Figure 4 (b). In 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, the adjacent vehicle V2 (position P ₂₎ is tilting occurs. Similarly, for the bird's-eye view image PB _{t-1 one} hour before, the white line drawn on the road surface has a rectangular shape and is in a state of being relatively accurately viewed in plan, but the adjacent vehicle V2 (position P _2). ') Will fall down. As described above, the vertical edges of solid objects (including the edges that rise in the three-dimensional space from the road surface in addition to the vertical edges in the strict sense) 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 V1 shown in FIG. 4 (a). It is determined based on the time until the time.

  In the present embodiment, the alignment unit 32 aligns the positions of the bird's-eye view images at different times on the bird's-eye view, and obtains the aligned bird's-eye view image. This can be performed with accuracy according to the type of detection target and the required detection accuracy. For example, it may be a strict alignment process that aligns positions based on the same time and the same position, or may be a loose alignment process that grasps the coordinates of each bird's-eye view image.

In addition, after the alignment, the alignment unit 32 calculates the difference between the bird's-eye view images PB _t and PB _t−1 and generates data of the difference image PD _t . Here, in the present embodiment, the alignment unit 32 converts the difference between the pixel values of the bird's-eye view images PB _t and PB _t−1 to an absolute value in order to cope with a change in the illumination environment, and the absolute value is a predetermined value. When the difference value is equal to or greater than the threshold value th, the pixel value of the difference image PD _t is set to “1”, and when the absolute value is less than the predetermined difference threshold value th, the pixel value of the difference image PD _t is set to “0”. Thus, data of the difference image PD _t as shown on the right side of FIG. 4B can be generated. Note that the value of the difference threshold th may be changed by the threshold changing unit 40 as will be described later. If the value of the difference threshold th is changed by the threshold changing unit 40, the value is changed by the threshold changing unit 40. The pixel value of the difference image PD _t is detected using the difference threshold th that has been changed.

Then, the difference waveform generation unit 33 generates a difference waveform based on the data of the difference image PD _t shown in FIG. Specifically, the differential waveform generation unit 33 generates a differential waveform in a detection region set to the left and right rear of the host vehicle V1.

  Here, the three-dimensional object detection device 1 of the present example is intended to calculate the movement distance for the adjacent vehicle V2 that may be contacted when the host vehicle V1 changes lanes. For this reason, in this example, as shown in FIG. 2, rectangular detection areas A1 and A2 are set on the left and right rear sides of the host vehicle V1. Such detection areas A1, A2 may be set from a relative position with respect to the host vehicle V1, or may be set based on the position of the white line. When setting the position of the white line as a reference, the three-dimensional object detection device 1 may use, for example, an existing white line recognition technique.

  In this example, as shown in FIG. 2, the sides (sides along the traveling direction) of the set detection areas A1 and A2 on the own vehicle V1 side are recognized as the ground lines L1 and L2. In general, the ground line means a line in which the three-dimensional object contacts the ground. However, in the present embodiment, 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 original adjacent vehicle V2 is not too large, and there is no problem in practical use.

FIG. 5 is a schematic diagram illustrating how the differential waveform generator 33 generates a differential waveform. As illustrated in FIG. 5, the differential waveform generation unit 33 calculates a differential waveform from a portion corresponding to the detection areas A1 and A2 in the differential image PD _t (right diagram in FIG. 4B) calculated by the alignment unit 32. DW _t is generated. At this time, the differential waveform generation unit 33 generates the differential waveform DW _t along the direction in which the three-dimensional object falls due to viewpoint conversion. In the example shown in FIG. 5, only the detection area A1 is described for convenience, but the difference waveform DW _t is generated for the detection area A2 in the same procedure.

Specifically, first, the differential waveform generation unit 33 defines a line La in a direction in which the three-dimensional object falls on the data of the differential image PD _t . Then, the difference waveform generation unit 33 counts the number of difference pixels DP indicating a predetermined difference on the line La. In the present embodiment, the difference pixel DP indicating the predetermined difference is expressed by the pixel value of the difference image PD _t as “0” and “1”, and the pixel indicating “1” is counted as the difference pixel DP. .

  The differential waveform generation unit 33 counts the number of differential pixels DP, and then obtains an intersection CP between the line La and the ground line L1. Then, the differential waveform generation 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.

Similarly, the differential waveform generation unit 33 defines lines Lb, Lc... In the direction in which the three-dimensional object falls, counts the number of differential 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 differential waveform generation unit 33 generates the differential waveform DW _t as shown in the right diagram of FIG.

Here, the difference pixel PD on the data of the difference image PD _t is a pixel that has changed in the images at different times, in other words, a location where a three-dimensional object exists. For this reason, 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. In particular, since the number of pixels is counted along the direction in which the three-dimensional object falls, the differential waveform DW _t is generated from the information in the height direction for the three-dimensional object.

As shown in the left diagram of FIG. 5, 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 determining the vertical axis position from the count number of the difference pixel DP, the difference waveform generation unit 33 is normalized based on the distances where the lines La and Lb in the direction in which the three-dimensional object falls and the detection area A1 overlap. Turn into. As a specific example, in the left diagram of FIG. 5, there are six difference pixels DP on the line La, and there are five difference pixels DP on the line Lb. Therefore, in determining the vertical axis position from the count number in FIG. 5, the differential waveform generation unit 33 normalizes the count number by dividing it by the overlap distance. Thus, as shown in 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 34 detects a three-dimensional object existing in the detection areas A1 and A2 based on the difference waveform DW _t generated by the difference waveform generation unit 33. Here, FIG. 6 is a diagram for explaining a method of detecting a three-dimensional object by the three-dimensional object detection unit 34, and illustrates an example of the difference waveform DW _t and a threshold value α for detecting the three-dimensional object. As illustrated in FIG. 6, the three-dimensional object detection unit 34 determines whether or not the peak of the generated differential waveform DW _t is _equal to or greater than a predetermined threshold value α corresponding to the peak position of the differential waveform DW _t. Then, it is determined whether or not a three-dimensional object exists in the detection areas A1 and A2. Then, when the peak of the difference waveform DW _t is less than the predetermined threshold value α, the three-dimensional object detection unit 34 determines that there is no three-dimensional object in the detection areas A1 and A2, while the peak of the difference waveform DW _t Is greater than or equal to a predetermined threshold value α, it is determined that a three-dimensional object exists in the detection areas A1 and A2. Further, in the present embodiment, the three-dimensional object detection unit 34 is an adjacent vehicle V2 in which the detected three-dimensional object exists in the adjacent lane based on the moving speed of the three-dimensional object calculated by the differential vehicle speed calculation unit 35 described later. By determining whether or not, the adjacent vehicle V2 is detected.

The difference vehicle speed calculation unit 35 calculates the relative moving speed of the three-dimensional object detected by the three-dimensional object detection unit 34 as the difference vehicle speed based on the comparison between the difference waveform DW _{t at} the current time and the difference waveform DW _t-1 one time before. To do. That is, the difference vehicle speed calculation unit 35 calculates the relative movement speed of the three-dimensional object as the difference vehicle speed from the time change of the difference waveforms DW _t and DW _t−1 . When the three-dimensional object detected by the three-dimensional object detection unit 34 is the adjacent vehicle V2, the difference vehicle speed calculation unit 35 calculates the difference in the relative vehicle speed of the adjacent vehicle V2 from the time change of the difference waveforms DW _t and DW _t−1. It will be calculated as the vehicle speed.

More specifically, the differential vehicle speed calculation unit 35 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) as shown in FIG. FIG. 7 is a diagram illustrating the small areas DW _{t1 to} DW _tn divided by the differential vehicle speed calculation unit 35. 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.

Next, the differential vehicle speed calculation unit 35 obtains an offset amount (a movement amount of the differential waveform in the horizontal axis direction (vertical direction in FIG. 7)) for each of the small areas DW _{t1 to} DW _tn . Here, 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). In this case, the difference speed calculation unit 35, 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 difference vehicle speed calculation unit 35 counts the offset amount obtained for each of the small areas DW _{t1 to} DW _tn and forms a histogram.

FIG. 8 is a diagram illustrating an example of a histogram obtained by the differential vehicle speed calculation unit 35. As shown in FIG. 8, there is some variation in 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. For this reason, the differential vehicle speed calculation unit 35 forms a histogram of the offset amount including variations, and calculates the movement distance from the histogram. At this time, the differential vehicle speed calculation unit 35 calculates the moving distance of the three-dimensional object (adjacent vehicle V2) from the maximum value of the histogram. That is, in the example shown in FIG. 8, the difference vehicle speed calculation unit 35 calculates the offset amount indicating the maximum value of the histogram as the movement distance τ ^* . As described above, in this embodiment, even if the offset amount varies, it is possible to calculate a more accurate movement distance from the maximum value. The moving distance τ ^* is a relative moving distance of the three-dimensional object (adjacent vehicle V2) with respect to the own vehicle. For this reason, when calculating the absolute movement distance, the difference vehicle speed calculation unit 35 calculates the absolute movement distance based on the obtained movement distance τ ^* and the signal from the vehicle speed sensor 20.

As described above, in the present embodiment, by calculating the moving distance of the three-dimensional object (adjacent vehicle V2) 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. Therefore, 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. In addition, by dividing the differential waveform DW _t generated at different times into a plurality of small regions DW _{t1 to} DW _tn , a plurality of waveforms representing the respective locations of the three-dimensional object can be obtained. Since the offset amount can be obtained for each of the positions, and the movement distance can be obtained from a plurality of offset amounts, the calculation accuracy of the movement distance can be improved. Further, in the present embodiment, by calculating the moving distance of the three-dimensional object from the time change of the differential waveform DW _t including the information in the height direction, compared with a case where attention is paid only to one point of movement, Since the detection location before the time change and the detection location after the time change are specified including information in the height direction, it is likely to be the same location in the three-dimensional object, and the movement distance is calculated from the time change of the same location, and the movement Distance calculation accuracy can be improved.

Incidentally, the difference speed calculation unit 35 Upon histogram is weighted for each of a plurality of small areas _DW t1 _{~DW tn,} the offset amount determined for each small area _DW t1 _{~DW tn} histogram of counts in response to the weight May be. FIG. 9 is a diagram illustrating weighting by the differential vehicle speed calculation unit 35.

As shown in FIG. 9, 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. The difference vehicle speed calculation unit 35 reduces the weight for such a 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.

On the other hand, the small area 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. The differential vehicle speed calculation unit 35 increases the weight for such a 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.

Although dividing the differential waveform DW _t into a plurality of small areas DW _t1 ~DW _tn in the above embodiment in order to improve the calculation accuracy of the moving distance, if the calculation accuracy of the moving distance is not less required small regions DW _t1 It is not necessary to divide into ~ DW _tn . In this case, the difference vehicle speed calculation unit 35 calculates the movement distance from the offset amount of the difference waveform DW _t when the error between the difference waveform DW _t and the difference 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.

  In the present embodiment, the differential vehicle speed calculation unit 35 obtains the moving speed of the host vehicle V1 (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 differential vehicle speed calculation unit 35 ignores the offset amount corresponding to the stationary object among the maximum values of the histogram and calculates the moving distance of the three-dimensional object.

  FIG. 10 is a diagram illustrating another example of a histogram obtained by the differential vehicle speed calculation unit 35. When a stationary object is present in addition to a three-dimensional object within the angle of view of the camera 10, two maximum values τ1 and τ2 appear in the obtained histogram. In this case, one of the two maximum values τ1, τ2 is the offset amount of the stationary object. For this reason, the differential vehicle speed calculation unit 35 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 using the remaining maximum value. To do. Thereby, the situation where the calculation accuracy of the moving distance of a solid object falls by a stationary object can be prevented.

  Even if the offset amount corresponding to the stationary object is ignored, if there are a plurality of maximum values, it is assumed that there are a plurality of three-dimensional objects within the angle of view of the camera 10. However, it is extremely rare that a plurality of three-dimensional objects exist in the detection areas A1 and A2. For this reason, the differential vehicle speed calculation unit 35 stops the calculation of the movement distance. Thereby, in the present embodiment, it is possible to prevent a situation in which an erroneous movement distance having a plurality of maximum values is calculated.

  The headlight detector 36 detects the headlight of the adjacent vehicle V2 that travels behind the host vehicle V1 based on the captured image captured by the camera 10. Specifically, the headlight detection unit 36 detects the light source that can be determined as the headlight of the adjacent vehicle V2 based on the captured image, thereby detecting the light source as the headlight of the adjacent vehicle V2. In the present embodiment, the headlight detection unit 36 detects an image area whose brightness difference from the surrounding area is greater than or equal to a predetermined value and a size greater than or equal to a predetermined value as a headlight candidate area of the adjacent vehicle V2. To do. Further, the headlight detection unit 36 distinguishes between the headlight of the adjacent vehicle V2 and a light source such as a streetlight in the vehicle width direction from the host vehicle V1 to the candidate area, and the rear from the camera 10 to the candidate area. Based on the distance or the like, the headlight of the adjacent vehicle V2 is detected by specifying an image region corresponding to the headlight of the adjacent vehicle V2 from among the headlight candidate regions of the plurality of adjacent vehicles V2.

  The headlight vehicle speed calculation unit 37 calculates the relative vehicle speed of the adjacent vehicle V2 with respect to the host vehicle V1 as the headlight vehicle speed based on the headlight of the adjacent vehicle V2 detected by the headlight detection unit 36. Specifically, the headlight vehicle speed calculation unit 37 calculates the movement distance of the headlight in a predetermined time based on the change in the position of the headlight of the adjacent vehicle V2 detected at different times, and calculates the calculated headlight By differentiating the moving distance with respect to time, the relative vehicle speed of the headlight of the adjacent vehicle V2 is calculated as the headlight vehicle speed.

  Based on the difference vehicle speed calculated by the difference vehicle speed calculation unit 35 and the headlight vehicle speed calculated by the headlight vehicle speed calculation unit 37, the estimated vehicle speed calculation unit 38 considers adhesion of foreign matters such as raindrops to the lens. The relative speed of the adjacent vehicle V2 is calculated as the estimated vehicle speed.

Here, FIG. 11 is a diagram illustrating an example of a captured image captured in a scene where raindrops are attached to the lens. FIG. 12A shows an example of a differential waveform DW _t generated in a scene where the adjacent vehicle V2 exists in the detection area but no raindrops are attached to the position corresponding to the detection area. FIG. 12B is an example of the differential waveform DW _t generated in a scene in which the adjacent vehicle V2 does not exist in the detection area, but raindrops are attached to the position corresponding to the detection area. FIG. Further, FIG. 12C shows a scene in which the adjacent vehicle V2 exists in the detection area and raindrops are attached to the position corresponding to the detection area, like the detection area A1 shown in FIG. in is a diagram showing an example of a generated difference waveform DW _t.

For example, in the scene where the adjacent vehicle V2 exists in the detection area but no raindrop is attached to the position corresponding to the detection area, as shown in FIG. 12A, the difference caused by the adjacent vehicle V2 Waveform DW _t is generated. On the other hand, even when the adjacent vehicle V2 does not exist in the detection area, if raindrops are attached to the position corresponding to the detection area, as shown in FIG. The resulting differential waveform DW _t is generated.

Therefore, when the adjacent vehicle V2 exists in the detection area and raindrops are attached to the position corresponding to the detection area as in the detection area A1 shown in FIG. as shown, the differences due to foreign matter such as raindrops on the lens will be included in the differential waveform DW _t, it may not be adequately generate a difference waveform DW _t due to the adjacent vehicle V2. Further, when the adjacent vehicle V2 exists in the detection area and raindrops are attached at a position corresponding to the detection area, the image of the adjacent vehicle V2 is caused by foreign matters such as raindrops attached to the lens. In some cases, the image of the adjacent vehicle V2 cannot be appropriately captured due to distortion or blurring. In such a case, as shown in FIG. 12C, the differential waveform DW _t resulting from the adjacent vehicle V2 Is difficult to generate. As a result, an error may occur between the differential vehicle speed calculated based on the differential waveform DW _t and the actual relative vehicle speed of the adjacent vehicle V2.

Here, FIG. 13A is a diagram illustrating an example of the differential vehicle speed calculated when a foreign object adheres to the lens and the differential vehicle speed calculated when a foreign object does not adhere to the lens. FIG. 13B is a diagram showing the moving distance of the adjacent vehicle V2 calculated based on the differential vehicle speed shown in FIG. For example, when no foreign matter is attached to the lens, the differential waveform DW _t attributed to the adjacent vehicle V2 can be appropriately generated. Therefore, the adjacent vehicle V2 is based on the differential waveform DW _t attributed to the adjacent vehicle V2. The relative vehicle speed can be appropriately calculated as the differential vehicle speed. Therefore, as shown in FIG. 13A, the error between the differential vehicle speed when no foreign matter is attached to the lens and the actual relative vehicle speed of the adjacent vehicle V2 becomes small. On the other hand, when foreign matter such as raindrops is attached to the lens, as described above, the differential waveform DW _t caused by the adjacent vehicle V2 cannot be appropriately generated by foreign matter such as raindrops. As shown in FIG. 13A, the relative vehicle speed of the adjacent vehicle V2 cannot be appropriately calculated as the differential vehicle speed, and the differential vehicle speed and the actual relative vehicle speed of the adjacent vehicle V2 when a foreign object is attached to the lens. May increase the error. Therefore, when foreign matter such as raindrops adheres to the lens, as shown in FIG. 13B, the movement distance of the adjacent vehicle V2 calculated based on the differential vehicle speed and the actual movement distance of the adjacent vehicle V2 And the position of the adjacent vehicle V2 may not be properly detected based on the differential vehicle speed.

On the other hand, since the headlight light image is less affected by foreign matter such as raindrops, the headlight vehicle speed is appropriately calculated compared to the differential vehicle speed even when foreign matter such as raindrops adheres to the lens. be able to. Here, FIG. 14A is a diagram illustrating an example of the headlight vehicle speed calculated when a foreign object adheres to the lens and the headlight vehicle speed calculated when no foreign object adheres to the lens. FIG. 14B is a diagram showing the moving distance of the adjacent vehicle V2 calculated based on the headlight vehicle speed in FIG. As shown in FIG. 14A, the headlight vehicle speed calculated based on the headlight of the adjacent vehicle V2 is the difference waveform DW _t of the adjacent vehicle V2 even when foreign matter such as raindrops is attached to the lens. Compared to the difference vehicle speed calculated based on the difference, the error with the actual relative vehicle speed of the adjacent vehicle V2 is small. Therefore, as shown in FIG. 14B, the adjacent vehicle V2 calculated based on the headlight vehicle speed is used. The error between the moving distance and the actual moving distance of the adjacent vehicle V2 is also reduced. Therefore, even when foreign matter such as raindrops adheres to the lens, it is possible to appropriately detect the position of the adjacent vehicle V2 based on the headlight vehicle speed.

In the case where foreign matter such as raindrops on the lens of the camera 10 is not attached, since no anomalies mentioned above, based on the difference waveform DW _t, the relative vehicle speed (difference speed) of the adjacent vehicle V2 properly detected can do. On the other hand, even when no foreign matter such as raindrops is attached to the lens, if the rear distance from the own vehicle V1 to the adjacent vehicle V2 is shortened by a certain distance or more, the position change of the headlight of the adjacent vehicle V2 is appropriately detected. In some cases, it is difficult to properly detect the relative vehicle speed of the adjacent vehicle V2 based on the headlight of the adjacent vehicle V2.

Therefore, the estimated vehicle speed calculation unit 38 sets the weight Wsa of the differential vehicle speed VELsa and the weight Whl of the headlight vehicle speed VELhl according to the amount of adhesion of foreign matters such as raindrops attached to the lens. Then, the weighted average is performed on the weighted difference vehicle speed VELsa and the headlight vehicle speed VELhl, so that the relative vehicle speed of the adjacent vehicle V2 in consideration of adhesion of foreign matters such as raindrops on the lens is calculated as the estimated vehicle speed VELest.

  Specifically, the estimated vehicle speed calculation unit 38 detects the amount of foreign matter such as raindrops adhering to the lens, and as shown in FIG. 15, the greater the amount of foreign matter adhering to the lens, the greater the difference vehicle speed VELsa. The weight Whl of the headlight vehicle speed VELhl is increased with respect to the weight Wsa. Accordingly, as the amount of foreign matter such as raindrops attached to the lens increases, the relative vehicle speed of the adjacent vehicle V2 can be obtained based on the headlight vehicle speed that is less affected by foreign matter such as raindrops. Even when the foreign matter adheres, the relative vehicle speed of the adjacent vehicle V2 can be determined appropriately. On the other hand, the estimated vehicle speed calculation unit 38 decreases the weight Whl of the headlight vehicle speed VELhl with respect to the weight Wsa of the differential vehicle speed VELsa as the amount of foreign matter such as raindrops attached to the lens of the camera 10 decreases. As a result, when the amount of foreign matter such as raindrops attached to the lens is small, the relative vehicle speed of the adjacent vehicle V2 can be obtained based on the differential vehicle speed, so the rear distance from the host vehicle V1 to the adjacent vehicle V2 Even when is short, the relative vehicle speed of the adjacent vehicle V2 can be determined appropriately. FIG. 15 is a diagram showing an example of the relationship between the weight Whl of the headlight vehicle speed VELhl and the weight Wsa of the differential vehicle speed VELsa when calculating the estimated vehicle speed VErest, and the amount of foreign matter such as raindrops on the lens.

  A method for detecting the amount of foreign matter attached to the lens of the camera 10 is not particularly limited. For example, the estimated vehicle speed calculation unit 38 can detect the amount of raindrops attached to the lens of the camera 10 based on the detection result of a raindrop sensor (not shown) and the operation status of the wiper. That is, the estimated vehicle speed calculation unit 38 determines that the more raindrops detected by the raindrop sensor, or the stronger the operation intensity of the wiper, the more raindrops are attached to the lens of the camera 10. It is possible to detect the amount of foreign matter adhering to the ten lenses. Moreover, the foreign material adhering to the lens of the camera 10 is not limited to raindrops, and includes, for example, scales and muddy water after the raindrops are dried. For example, if the estimated vehicle speed calculation unit 38 cannot detect the edge caused by the adjacent vehicle V2 for a predetermined time or more after detecting the headlight of the adjacent vehicle V2, the scale of the lens of the camera 10 is attached with water scale. Can be determined.

Further, as shown in FIG. 15, the estimated vehicle speed calculation 38 determines whether or not the host vehicle V1 is a scene overtaking the adjacent vehicle V2 or a scene where the host vehicle is overtaken by the adjacent vehicle V2. Based on the result, a weight Wsa for the differential vehicle speed VELsa and a weight Whl for the headlight vehicle speed VELhl are set. For example, in a scene where the own vehicle V1 is overtaken adjacent vehicle V2, than the difference speed VELsa based on differential waveform DW _t, towards the headlight speed VELhl based on headlights of an adjacent vehicle V2 is in reliable trend. Therefore, in a scene in which the host vehicle V1 is overtaken by the adjacent vehicle V2, as shown in FIG. 15, the weight Whl of the headlight vehicle speed VELhl is increased relative to the weight Wsa of the differential vehicle speed VELsa, thereby making the relative of the adjacent vehicle V2 The vehicle speed (estimated vehicle speed VETest) can be calculated with higher accuracy. Since the differential vehicle speed VELsa and the headlight vehicle speed VELhl of the adjacent vehicle V2 are relative vehicle speeds of the adjacent vehicle V2 with respect to the host vehicle V1, the estimated vehicle speed calculation unit 38 determines whether the differential vehicle speed VELsa or the headlight vehicle speed VELhl of the adjacent vehicle V2 is positive. By determining whether the value is a negative value or a negative value, it is possible to determine whether the host vehicle V1 is a scene overtaken by the adjacent vehicle V2 or a scene where the host vehicle V1 is overtaken by the adjacent vehicle V2. it can.

Returning to FIG. 3, the detection determination distance calculation unit 39 performs the current time after the elapsed time T from the time when the adjacent vehicle V <b> 2 is detected based on the estimated vehicle speed VEEST calculated by the estimated vehicle speed calculation unit 38 according to the following formula 2. The relative movement distance of the adjacent vehicle V2 is calculated as the detection determination distance Dist.

  Here, FIG. 16 is a diagram for explaining the detection determination distance Dist. In the example shown in FIG. 16, the adjacent vehicle V2 is detected at a time t1 that is one hour before the time t2, which is the current time. The scene is illustrated. In this case, the detection determination distance calculation unit 39 is based on the estimated vehicle speed VErest calculated by the estimated vehicle speed calculation unit 38 during the time T from the time t1 when the adjacent vehicle V2 is detected to the current time t2. The relative movement distance that the adjacent vehicle V2 has moved is calculated as the detection determination distance Dist. Further, the detection determination distance calculation unit 39 repeatedly calculates the detection determination distance Dist, and outputs the calculated detection determination distance Dist to the threshold value changing unit 40.

  The calculation method of the detection determination distance Dist is not limited to the above method. For example, after detecting the adjacent vehicle V2, the detection determination distance Dist is integrated by integrating the estimated vehicle speed VEEST repeatedly calculated by the estimated vehicle speed calculation unit 38. It is good also as a structure which calculates.

  When the adjacent vehicle V2 is detected in the detection areas A1 and A2, the threshold changing unit 40 determines that the adjacent vehicle V2 exists in the detection areas A1 and A2 for a predetermined time after the adjacent vehicle V2 is detected. Thus, in order to continuously detect the adjacent vehicle V2 existing in the detection areas A1 and A2, the difference threshold th for detecting a three-dimensional object is changed.

  Specifically, the threshold value changing unit 40 changes the value of the difference threshold value th to a low value at the first timing (time t1) when the adjacent vehicle V2 is detected in the detection areas A1 and A2. Furthermore, the threshold value changing unit 40 repeatedly acquires the detection determination distance Dist from the detection determination distance calculation unit 39 after the first timing t1 when the adjacent vehicle V2 is detected, and the absolute value of the detection determination distance Dist and a predetermined reference distance are obtained. Compare Here, the reference distance Dstd is detected when the adjacent vehicle V2 detected in the detection areas A1 and A2 moves by the reference distance Dstd with respect to the host vehicle V1 and the adjacent vehicle V2 deviates from the detection areas A1 and A2. The distance can be determined that the adjacent vehicle V2 does not exist in the areas A1 and A2, and can be set based on, for example, the length of the detection areas A1 and A2 in the traveling direction and the total length of a general vehicle. The detection determination distance Dist calculated by the detection determination distance calculation unit 39 is a positive value when the adjacent vehicle V2 passes the own vehicle V1, and is negative when the own vehicle V1 passes the adjacent vehicle V2. However, since the reference distance Dstd is for comparison with the absolute value of the detection determination distance Dist, is the adjacent vehicle V2 overtaking the own vehicle V1 or the own vehicle V1 overtaking the adjacent vehicle V2? Regardless of, it is set to a positive value.

  When the absolute value of the detection determination distance Dist is less than the reference distance Dstd as a result of the comparison between the detection determination distance Dist and the predetermined reference distance Dstd, the threshold value changing unit 40 is adjacent to the adjacent vehicle in the detection areas A1, A2. It is determined that V2 exists, and the value of the difference threshold th changed at the first timing t1 is set to a low value. Thereby, even if foreign matter such as raindrops adheres to the lens of the camera 10 and it is difficult to continuously detect the adjacent vehicle V2 in the detection areas A1 and A2, the adjacent vehicle existing in the detection areas A1 and A2. V2 can be continuously detected.

  On the other hand, as a result of comparing the absolute value of the detection determination distance Dist with a predetermined reference distance Dstd, the threshold value changing unit 40 determines that the absolute value of the detection determination distance Dist is greater than or equal to the reference distance Dstd as shown at time t2 in FIG. In this case, at the second timing t2 when the detection determination distance Dist is equal to or greater than the reference distance Dstd, it is determined that the adjacent vehicle V2 does not exist in the detection areas A1 and A2, and the difference threshold value changed at the first timing t1 Return the value of th to the original value. As a result, when the adjacent vehicle V2 does not exist in the detection areas A1 and A2, a foreign object such as raindrops attached to the lens or a three-dimensional object other than the adjacent vehicle V2 existing in the adjacent lane is erroneously detected as the adjacent vehicle V2. This can be effectively prevented.

Next, the adjacent vehicle detection process according to the present embodiment will be described. FIG. 17 is a flowchart illustrating the adjacent vehicle detection process according to the first embodiment. As shown in FIG. 17, first, the computer 30 acquires captured image data from the camera 10 (step S101), and the viewpoint conversion unit 31 acquires the bird's-eye view image PB based on the acquired captured image data. Data of _t is generated (step S102).

Next, the alignment unit 32 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 before, and generates data of the difference image PD _t (step S103). . Specifically, the alignment unit 32 converts the difference between the pixel values of the bird's-eye view images PB _t and PB _t−1 to an absolute value, and when the absolute value is equal to or greater than a predetermined difference threshold th, the difference image PD _t Is set to “1”, and when the absolute value is less than the predetermined difference threshold th, the pixel value of the difference image PD _t is set to “0”. Note that the difference threshold th for detecting a three-dimensional object from the difference image PD _t may be changed in a threshold change process described later, and when the difference threshold th is changed, the changed difference threshold th is Used in step 103.

Thereafter, the differential waveform generating unit 33, from the data of the difference image PD _t, pixel value by counting the number of difference pixel DP "1", to generate a difference waveform DW _t (step S104). Then, the three-dimensional object detection unit 34 determines whether or not the peak of the differential waveform DW _t is greater than or _{equal to} a predetermined threshold value α (step S105). When the peak of the difference waveform DW _t is not equal to or greater than the threshold value α, that is, when there is almost no difference, it is considered that there is no three-dimensional object in the captured image. For this reason, when it is determined that the peak of the difference waveform DW _t is not equal to or greater than the threshold value α (step S105 = No), the three-dimensional object detection unit 34 determines that there is no three-dimensional object and there is no adjacent vehicle V2 ( Step S114). And it returns to step S101 and repeats the process shown in FIG.

On the other hand, if it is determined that the peak of the differential waveform DW _t is equal to or greater than the threshold value α (step S105 = Yes), the three-dimensional object detection unit 34 determines that a three-dimensional object exists in the adjacent lane, and proceeds to step S106. The differential vehicle speed calculation unit 35 divides the differential waveform DW _t into a plurality of small areas DW _{t1 to} DW _tn . Next, the differential vehicle speed calculation unit 35 performs weighting for each of the small areas DW _{t1 to} DW _tn (step S107), calculates an offset amount for each of the small areas DW _{t1 to} DW _tn (step S108), and adds the weight. A histogram is generated (step S109).

  Then, the difference vehicle speed calculation unit 35 calculates a relative movement distance that is a movement distance of the three-dimensional object with respect to the host vehicle V1 based on the histogram (step S110). Next, the differential vehicle speed calculation unit 35 calculates the absolute movement speed of the three-dimensional object from the relative movement distance (step S111). At this time, the differential vehicle speed calculation unit 35 calculates the relative movement speed by differentiating the relative movement distance with respect to time, and calculates the absolute movement speed by adding the own vehicle speed detected by the vehicle speed sensor 20.

  Thereafter, the three-dimensional object detection unit 34 determines whether or not 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 V1 is +60 km / h or less (step S112). . When both are satisfied (step S112 = Yes), the three-dimensional object detection unit 34 determines that the detected three-dimensional object is the adjacent vehicle V2 existing in the adjacent lane, and the adjacent vehicle V2 exists in the adjacent lane (step S113). ). Then, the process shown in FIG. 17 ends. On the other hand, when either one is not satisfied (step S112 = No), the three-dimensional object detection unit 34 determines that the adjacent vehicle V2 does not exist in the adjacent lane (step S114). And it returns to step S101 and repeats the process shown in FIG.

  In the present embodiment, the left and right rear sides of the host vehicle V1 are set as detection areas A1 and A2, and emphasis is placed on whether or not there is a possibility of contact when the host vehicle V1 changes lanes. For this reason, the process of step S112 is performed. That is, assuming that the system according to this embodiment is operated on a highway, when the speed of the adjacent vehicle V2 is less than 10 km / h, even when the adjacent vehicle V2 exists, when changing the lane, Since it is located far behind the host vehicle V1, there is little problem. Similarly, when the relative movement speed of the adjacent vehicle V2 with respect to the own vehicle V1 exceeds +60 km / h (that is, when the adjacent vehicle V2 moves at a speed higher than 60 km / h than the speed of the own vehicle V1), the lane When changing, it is less likely to cause a problem because the vehicle is moving in front of the host vehicle V1. For this reason, in step S112, it can be said that the adjacent vehicle V2 which becomes a problem at the time of lane change is judged.

  Moreover, the following effects are obtained by determining whether the absolute moving speed of the adjacent vehicle V2 is 10 km / h or more and the relative moving speed of the adjacent vehicle V2 with respect to the host vehicle V1 is +60 km / h or less in step S112. . For example, depending on the mounting error of the camera 10, 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 adjacent vehicle V2. Further, depending on the noise, the relative speed of the adjacent vehicle V2 with respect to the host vehicle V1 may be detected as 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.

  Furthermore, instead of the process of step S112, it may be determined that the absolute movement speed of the adjacent vehicle V2 is not negative or 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 V1 changes lanes, when the adjacent vehicle V2 is detected in step S113, 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.

  Next, the threshold value changing process according to the first embodiment will be described. FIG. 18 is a flowchart showing the threshold value changing process according to the first embodiment. The threshold change process described below is performed in parallel with the adjacent vehicle detection process shown in FIG. 17, and the difference threshold th set by this threshold change process is the difference threshold in the adjacent vehicle detection process shown in FIG. It will be applied as th.

  As shown in FIG. 18, first, in step S201, the threshold value changing unit 40 determines whether or not the adjacent vehicle V2 is detected by the adjacent vehicle detection process shown in FIG. When the adjacent vehicle V2 is detected, the process proceeds to step S202. On the other hand, when the adjacent vehicle V2 is not detected, the process waits at step S201 until the adjacent vehicle V2 is detected.

  Next, in step S202, the headlight detection unit 36 detects the headlight of the adjacent vehicle V2. Specifically, the headlight detection unit 36 selects an image area whose brightness difference from the surrounding area is greater than or equal to a predetermined value and has a size greater than or equal to a predetermined area as a candidate area corresponding to the headlight of the adjacent vehicle V2. Detect as. Further, the headlight detection unit 36 distinguishes between the headlight of the adjacent vehicle V2 and a light source such as a streetlight in the vehicle width direction from the host vehicle V1 to the candidate area, and the rear from the camera 10 to the candidate area. Based on the distance, the headlight of the adjacent vehicle V2 is detected by specifying an image region corresponding to the headlight of the adjacent vehicle V2 from the candidate regions.

  In step S203, the threshold value changing unit 40 determines whether or not the headlight of the adjacent vehicle V2 is detected in step S202. If the headlight of the adjacent vehicle V2 is detected, the process proceeds to step S204. If the headlight of the adjacent vehicle V2 is not detected, the process returns to step S201, and the detection of the adjacent vehicle V2 and the adjacent vehicle are performed again. The detection of the V2 headlight is repeated.

  In step S204, the headlight vehicle speed calculation unit 37 calculates the headlight vehicle speed of the adjacent vehicle V2. For example, the headlight vehicle speed calculation unit 37 calculates the movement distance of the headlight at a predetermined time as the movement distance of the adjacent vehicle V2 based on the change in the position of the headlight of the adjacent vehicle V2 detected in step S202. The relative vehicle speed of the adjacent vehicle V2 with respect to the host vehicle V1 is calculated as the headlight vehicle speed VELhl by differentiating the adjacent vehicle head moving distance with respect to time.

  In subsequent step S205, the estimated vehicle speed calculation unit 38 acquires the differential vehicle speed VELsa. For example, the estimated vehicle speed calculation unit 38 acquires the difference vehicle speed VELsa calculated in the adjacent vehicle detection process shown in FIG.

  In step S206, the estimated vehicle speed calculation unit 38 determines the adjacent vehicle V2 in consideration of adhesion of foreign matters such as raindrops on the lens based on the headlight vehicle speed calculated in step S204 and the differential vehicle speed acquired in step S205. The relative vehicle speed is calculated as the estimated vehicle speed VErest. Specifically, the estimated vehicle speed calculation unit 38 calculates the estimated vehicle speed VETest by obtaining a weighted average of the headlight vehicle speed and the differential vehicle speed according to the above-described Expression 1. In particular, in the present embodiment, when the estimated vehicle speed calculation unit 38 calculates the estimated vehicle speed VErest, as shown in FIG. 15, the greater the amount of foreign matter such as raindrops on the lens, the greater the weight Wsa of the difference vehicle speed VELsa. On the other hand, by increasing the weight Whl of the headlight vehicle speed VELhl, the relative vehicle speed of the adjacent vehicle V2 can be appropriately calculated as the estimated vehicle speed VEEST even when foreign matter such as raindrops adheres to the lens. Further, as shown in FIG. 15, the estimated vehicle speed calculation unit 38 has a difference vehicle speed VELsa in a scene where the host vehicle V1 is overtaking the adjacent vehicle V2 compared to a scene where the host vehicle V1 is overtaking the adjacent vehicle V2. By increasing the weight Whl of the headlight vehicle speed VELhl with respect to the weight Wsa, the relative vehicle speed (estimated vehicle speed VETest) of the adjacent vehicle V2 can be calculated with higher accuracy.

  In step S207, the detection determination distance calculation unit 39 calculates the relative movement distance that the adjacent vehicle V2 has moved after the detection of the adjacent vehicle V2 as the detection determination distance Dist. In step S208, the threshold value changing unit 40 changes the difference threshold value th in order to continuously detect the adjacent vehicle V2 existing in the detection areas A1 and A2. Specifically, the threshold value changing unit 40 can detect the adjacent vehicle V2 existing in the detection areas A1 and A2 even when foreign matter such as raindrops is attached to the lens of the camera 10. The difference threshold th is changed to a low value.

  In step S209, the threshold value changing unit 40 determines whether or not the absolute value of the detection determination distance Dist calculated in step S207 is greater than or equal to a predetermined reference value Dstd. Here, the reference distance Dstd is detected when the adjacent vehicle V2 detected in the detection areas A1 and A2 moves by the reference distance Dstd with respect to the host vehicle V1 and the adjacent vehicle V2 deviates from the detection areas A1 and A2. This is the distance at which it can be determined that the adjacent vehicle V2 does not exist in the areas A1 and A2. Therefore, when the absolute value of the detection determination distance Dist is less than the reference value Dstd, the threshold changing unit 40 determines that the adjacent vehicle V2 exists in the detection areas A1 and A2, and sets the difference threshold th to a low value. The process waits in step S209. On the other hand, when the absolute value of the detection determination distance Dist is greater than or equal to the reference value Dstd, the threshold value changing unit 40 determines that the adjacent vehicle V2 does not exist in the detection areas A1 and A2, and proceeds to step S210, and the difference threshold value Return th to the original value.

  For example, in the example shown in FIG. 16, first, at the first timing t1 (time t1), the adjacent vehicle V2 is detected and the difference threshold th is changed to a low value (step S208). Then, after the first timing t1, it is determined whether or not the absolute value of the detection determination distance Dist is greater than or equal to the reference value Dstd (step S209). While the absolute value of the detection determination distance Dist is less than the reference value Dstd (step S209 = No), it is determined that the adjacent vehicle V2 exists in the detection areas A1 and A2, and the difference threshold th remains low. Is set. Thus, after the first timing t1 when the adjacent vehicle V2 is detected, while the absolute value of the detection determination distance Dist is less than the reference value Dstd, the difference set to a low value in the adjacent vehicle detection process shown in FIG. The three-dimensional object is detected using the threshold value th, and as a result, it is possible to continuously detect the adjacent vehicle V2 existing in the detection areas A1 and A2.

  In the example shown in FIG. 16, after the first timing t1, at the second timing t2 (time t2), it is determined that the absolute value of the detection determination distance Dist is greater than or equal to the reference value Dstd (step S209 = Yes). The difference threshold th is returned to the original value (step S210). Thus, after the second timing t2 when it is determined that the adjacent vehicle V2 does not exist in the detection areas A1 and A2, in the adjacent vehicle detection process shown in FIG. Since objects are detected, it is possible to effectively prevent foreign objects such as water droplets adhering to the lens and three-dimensional objects other than the adjacent vehicle V2 existing in the adjacent lane from being erroneously detected as the adjacent vehicle V2. Can do.

In the present embodiment, in view of the fact that it is difficult to calculate the relative vehicle speed of the adjacent vehicle V2 with respect to the host vehicle V1 based on the differential waveform DW _t due to adhesion of foreign matters such as raindrops on the lens. The V2 headlight is detected, and the relative vehicle speed of the adjacent vehicle V2 is estimated based on the headlight of the adjacent vehicle V2. Therefore, the threshold value changing process shown in FIG. 18 can be configured to be performed only at night, for example, under the condition that the adjacent vehicle V2 lights the headlight. Thereby, the calculation load at the time of detecting the adjacent vehicle V2 can be reduced in the daytime. The threshold value changing unit 40 can determine that it is nighttime, for example, when the brightness of the entire captured image captured by the camera 10 is equal to or less than a predetermined value. Further, the threshold value changing unit 40 can also determine whether it is nighttime based on the illuminometer and the time.

  Further, the above-described threshold value changing process may be performed only during rainy weather when there is a high possibility that foreign matter such as raindrops will adhere to the lens. In this case, the threshold value changing unit 40 can determine whether or not it is raining based on the detection result of the raindrop sensor and the operation state of the wiper.

  Furthermore, the process of step S208 described above may be executed immediately after step S204 shown in FIG. 18, for example. In the threshold value changing process described above, it is not necessary to perform the process of changing the difference threshold value th at exactly the same timing as when the adjacent vehicle V2 is detected, and the adjacent vehicle V2 is detected as in this embodiment. It is possible to adopt a configuration in which the timing is slightly later than the set timing.

As described above, in the first embodiment, based on the difference waveform DW _t, it calculates the relative speed of the adjacent vehicle V2 as a differential speed VELsa, detects headlights of an adjacent vehicle V2, the adjacent vehicle V2 headlights Based on the above, the relative speed of the adjacent vehicle V2 is calculated as the headlight vehicle speed VELhl. Then, by weighting the differential vehicle speed VELsa and the headlight vehicle speed EVLhl according to the adhesion amount of foreign matters such as raindrops adhering to the lens, an appropriate adjacent vehicle V2 that takes into account the adhesion of foreign matters such as raindrops on the lens is taken into account. The relative speed is calculated as the estimated vehicle speed VErest. That is, as the amount of foreign matter such as raindrops adhering to the lens increases, the weighting Whl of the headlight vehicle speed VELhl is made larger than the weighting Wsa of the differential vehicle speed VELsa, and the amount of foreign matter such as raindrops adhering to the lens increases. The smaller the weight, the smaller the weight Whl of the headlight vehicle speed VELhl with respect to the weight Wsa of the differential vehicle speed VELsa. Thus, in the present embodiment, even when foreign matter such as raindrops adheres to the lens of the camera 10, the adjacent vehicle is determined based on the headlight vehicle speed VELhl where the influence of foreign matter such as raindrops is relatively small on the lens of the camera 10. The relative vehicle speed of V2 can be appropriately calculated as the estimated vehicle speed VEfest. In the case less adhesion of foreign materials such as raindrops on the lens, based on the difference waveform DW _t adjacent vehicle V2, calculates a relative speed of the adjacent vehicle V2 (difference speed VELsa), adjacent the vehicle from the vehicle V1 Even when the rear distance to V2 is short, the relative vehicle speed (differential vehicle speed VELsa) of the adjacent vehicle V2 can be appropriately calculated.

  In the present embodiment, the relative movement distance that the adjacent vehicle V2 has moved after the detection of the adjacent vehicle V2 is calculated as the detection determination distance Dist on the basis of the estimated vehicle speed VETest of the adjacent vehicle V2 calculated in this way. As shown, the adjacent vehicle V2 is detected from the first timing t1 at which the adjacent vehicle V2 is detected to the second timing t2 after the first timing t1 until the detection determination distance Dist is equal to or greater than the reference distance Dstd. , A2 is determined, and the difference threshold th is changed to a low value so that the adjacent vehicle V2 can be easily detected. Thereby, while the adjacent vehicle V2 exists in the detection areas A1 and A2, the adjacent vehicle V2 existing in the detection areas A1 and A2 becomes easy to detect, and foreign matters such as raindrops adhere to the lens. However, the adjacent vehicle V2 existing in the detection areas A1 and A2 can be continuously detected.

<< Second Embodiment >>
Next, the three-dimensional object detection device 1a according to the second embodiment will be described. As shown in FIG. 19, the three-dimensional object detection device 1 a according to the second embodiment includes a computer 30 a instead of the computer 30 of the first embodiment, except that it operates as described below. This is the same as in the first embodiment. Here, FIG. 19 is a block diagram showing details of the computer 30a according to the second embodiment.

  As shown in FIG. 19, the three-dimensional object detection device 1a according to the second embodiment includes a camera 10 and a computer 30a. The computer 30a includes a viewpoint conversion unit 31, a luminance difference calculation unit 41, and an edge line detection unit. 42, an edge waveform generation unit 43, an edge vehicle speed calculation unit 44, a three-dimensional object detection unit 34a, a headlight detection unit 36, a headlight vehicle speed calculation unit 37, an estimated vehicle speed calculation unit 38a, a detection determination distance calculation unit 39a, and a threshold value change unit 40a. Below, each structure of the solid-object detection apparatus 1a which concerns on 2nd Embodiment is demonstrated. Note that the viewpoint conversion unit 31, the headlight detection unit 36, and the headlight vehicle speed calculation unit 37 have the same configuration as that of the first embodiment, and thus description thereof is omitted.

  FIG. 20 is a diagram illustrating an imaging range and the like of the camera 10 of FIG. 19, FIG. 20A is a plan view, and FIG. 20B is a perspective view in real space on the rear side from the host vehicle V1. Show. As shown in FIG. 20A, the camera 10 has a predetermined angle of view a, and images the rear side from the host vehicle V1 included in the predetermined angle of view a. Similarly to the case shown in FIG. 2, 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 V1 travels.

Detection area A1, A2 of the present embodiment is in a plan view (a state of being bird's view) a trapezoidal shape, location of the detection areas A1, A2, size and shape, based on the distance d ₁ to d ₄ determines 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.

  Here, the distance d1 is a distance from the host vehicle V1 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 V1 travels contacts the ground. In the present embodiment, the object is to detect adjacent vehicles V2 and the like (including two-wheeled vehicles) traveling in the left and right lanes adjacent to the lane of the host vehicle V1 on the rear side of the host vehicle V1. For this reason, a distance d1 which is a position to be the ground lines L1 and L2 of the adjacent vehicle V2 from a distance d11 from the own vehicle V1 to the white line W and a distance d12 from the white line W to a position where the adjacent vehicle V2 is predicted to travel It can be determined substantially fixedly.

  Further, the distance d1 is not limited to being fixedly determined, and may be variable. In this case, the computer 30a recognizes the position of the white line W with respect to the host vehicle V1 by a technique such as white line recognition, and determines the distance d11 based on the recognized position of the white line W. Thereby, the distance d1 is variably set using the determined distance d11. In the following embodiment, since the position where the adjacent vehicle V2 travels (distance d12 from the white line W) and the position where the host vehicle V1 travels (distance d11 from the white line W) are roughly determined, the distance d1 is It shall be fixedly determined.

  The distance d2 is a distance extending in the vehicle traveling direction from the rear end portion of the host vehicle V1. 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. In particular, in the present embodiment, 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 adjacent vehicle V2 or the like, the distance d3 is set to a length including the adjacent vehicle V2.

  As shown in FIG. 20B, the distance d4 is a distance indicating a height that is set to include a tire such as the adjacent vehicle V2 in the real space. The distance d4 is a length shown in FIG. 20A in the bird's-eye view image. Note that the distance d4 may be a length that does not include a lane that is further adjacent to the left and right lanes in the bird's-eye view image (that is, the adjacent lane that is adjacent to two lanes). If the lane adjacent to the two lanes is included from the lane of the own vehicle V1, there is an adjacent vehicle V2 in the adjacent lane on the left and right of the own lane that is the lane in which the own vehicle V1 is traveling. This is because it becomes impossible to distinguish whether there is an adjacent vehicle on the lane.

  As described above, 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. Similarly, 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. Thus, the area surrounded by the sides b1 to b4 is set as the detection areas A1 and A2. As shown in FIG. 20B, the detection areas A1 and A2 are true squares (rectangles) in the real space behind the host vehicle V1.

  The luminance difference calculation unit 41 calculates a luminance difference with respect to the bird's-eye view image data subjected to the 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. The luminance difference calculation unit 41 calculates a luminance difference between two pixels in the vicinity of each position for each of a plurality of positions along the vertical imaginary line extending in the vertical direction in the real space. The luminance difference calculation unit 41 can calculate the luminance difference by either a method of setting only one vertical imaginary line extending in the vertical direction in the real space or a method of setting two vertical imaginary lines.

  Here, a specific method for setting two vertical virtual lines will be described. The luminance difference calculation unit 41 is different from the bird's eye view image that has undergone viewpoint conversion in the vertical direction in the real space, unlike the first vertical virtual line corresponding to the line segment extending in the vertical direction in the real space and the first vertical virtual line. A second vertical imaginary line corresponding to the extending line segment is set. The luminance difference calculation unit 41 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. Hereinafter, the operation of the luminance difference calculation unit 41 will be described in detail.

  As shown in FIG. 21A, the luminance difference calculation unit 41 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). Set). In addition, unlike the attention line La, the luminance difference calculation unit 41 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. Set. Here, the reference line Lr is set at a position separated from the attention line La by a predetermined distance in the real space. Note that 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 41 sets a point of interest Pa (a point on the first vertical imaginary line) on the line of interest La. Further, the luminance difference calculation unit 41 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. 21B in the real space. As is clear from FIG. 21B, the attention line La and the reference line Lr are lines extending in the vertical direction on the real space, and the attention point Pa and the reference point Pr are substantially the same height in the real space. This is the point that is set. Note that the attention point Pa and the reference point Pr do not necessarily have the same height, and an error that allows the attention point Pa and the reference point Pr to be regarded as the same height is allowed.

  The luminance difference calculation unit 41 calculates the 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. In particular, in the second embodiment, in order to detect a three-dimensional object existing in the detection areas A1 and A2, a vertical virtual line is set as a line segment extending in the vertical direction in the real space with respect to the bird's-eye view image, 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. For this reason, the edge line detection unit 42 shown in FIG. 19 detects an edge line based on the luminance difference between the attention point Pa and the reference point Pr.

  This point will be described in more detail. FIG. 22 is a diagram illustrating a detailed operation of the luminance difference calculation unit 41, FIG. 22 (a) shows a bird's-eye view image in a bird's-eye view state, and FIG. 22 (b) is shown in FIG. 22 (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. 22, the luminance difference is calculated in the same procedure for the detection area A2.

  When the adjacent vehicle V2 is reflected in the captured image captured by the camera 10, the adjacent vehicle V2 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 region B1 in FIG. 22A in FIG. 22B, it is assumed that the attention line La is set on the rubber part of the tire of the adjacent vehicle V2 on the bird's-eye view image. In this state, the luminance difference calculation unit 41 first sets a reference line Lr. The reference line Lr is set along the vertical direction at a position away from the attention line La by a predetermined distance in the real space. Specifically, in the three-dimensional object detection device 1a according to the present embodiment, the reference line Lr is set at a position separated from the attention line La by 10 cm in the real space. Thereby, the reference line Lr is set on the wheel of the tire of the adjacent vehicle V2, which is separated from the rubber of the tire of the adjacent vehicle V2, for example, by 10 cm, on the bird's eye view image.

  Next, the luminance difference calculation unit 41 sets a plurality of attention points Pa1 to PaN on the attention line La. In FIG. 22B, for the convenience of explanation, six attention points Pa1 to Pa6 (hereinafter simply referred to as attention points Pai when showing arbitrary points) are set. Note that the number of attention points Pa set on the attention line La may be arbitrary. In the following description, it is assumed that N attention points Pa are set on the attention line La.

  Next, the luminance difference calculation unit 41 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 41 calculates the luminance difference between the attention point Pa and the reference point Pr having the same height. Thereby, the brightness | luminance difference calculation part 41 calculates the brightness | luminance difference of two pixels for every some position (1-N) along the vertical virtual line extended in the perpendicular direction in real space. For example, the luminance difference calculation unit 41 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. Thereby, the luminance difference calculation unit 41 continuously calculates the luminance difference along the attention line La and the reference line Lr. That is, the luminance difference calculation unit 41 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 41 repeatedly executes the above-described processing of 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 41 repeatedly executes the above process while changing the position of the attention line La and the reference line Lr by the same distance in the extending direction of the ground line L1 in the real space. For example, the luminance difference calculation unit 41 sets the line that has been the reference line Lr in the previous process as the attention line La, sets the reference line Lr for the attention line La, and sequentially obtains the luminance difference. It will be.

  As described above, in the second embodiment, the edge extending in the vertical direction is obtained by calculating the luminance difference from the attention point Pa on the attention line La and the reference point Pr on the reference line Lr that are substantially the same height in the real space. It is possible to clearly detect a luminance difference in the case where there is. Also, in order to compare the brightness of vertical virtual lines extending in the vertical direction in real space, even if the three-dimensional object is stretched according to the height from the road surface by converting to a bird's-eye view image, The detection process is not affected, and the detection accuracy of the three-dimensional object can be improved.

  Returning to FIG. 19, the edge line detection unit 42 detects an edge line from the continuous luminance difference calculated by the luminance difference calculation unit 41. For example, in the case illustrated in FIG. 22B, the first attention point Pa1 and the first reference point Pr1 are located in the same tire portion, and thus the luminance difference is small. On the other hand, the second to sixth attention points Pa2 to Pa6 are located in the rubber part of the tire, and the second to sixth reference points Pr2 to Pr6 are located in the wheel part of the tire. Therefore, the luminance difference between the second to sixth attention points Pa2 to Pa6 and the second to sixth reference points Pr2 to Pr6 increases. For this reason, the edge line detection unit 42 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.

Specifically, in detecting the edge line, the edge line detection unit 42 firstly follows the following equation 1 to determine the i-th attention point Pai (coordinates (xi, yi)) and the i-th reference point Pri (coordinates (xi). ', Yi')), the i th attention point Pai is attributed.
[Formula 1]
When I (xi, yi)> I (xi ′, yi ′) + t s (xi, yi) = 1
When I (xi, yi) <I (xi ′, yi ′) − t s (xi, yi) = − 1
Otherwise s (xi, yi) = 0

  In Equation 1, t represents an edge threshold, I (xi, yi) represents the luminance value of the i-th attention point Pai, and I (xi ′, yi ′) represents the luminance value of the i-th reference point Pri. Show. According to the above equation 1, when the luminance value of the attention point Pai is higher than the luminance value obtained by adding the edge threshold t to the reference point Pri, the attribute s (xi, yi) of the attention point Pai is “1”. It becomes. On the other hand, when the luminance value of the attention point Pai is lower than the luminance value obtained by subtracting the edge threshold t from the reference point Pri, the attribute s (xi, yi) of the attention point Pai is “−1”. When the luminance value of the attention point Pai and the luminance value of the reference point Pri are in other relationships, the attribute s (xi, yi) of the attention point Pai is “0”. In the present embodiment, the edge threshold t may be changed by a threshold changing unit 40a described later in order to promote detection of a three-dimensional object, and when the edge threshold t is changed by the threshold changing unit 40a. , The attribute s (xi, yi) of the attention point Pai is detected using the edge threshold t changed by the threshold changing unit 40a.

Next, the edge line detection unit 42 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 the following formula 2.
[Formula 2]
When s (xi, yi) = s (xi + 1, yi + 1) (and excluding 0 = 0),
c (xi, yi) = 1
Other than the above
c (xi, yi) = 0

  When the attribute s (xi, yi) of the attention point Pai and the attribute s (xi + 1, yi + 1) of the adjacent attention point Pai + 1 are the same, the continuity c (xi, yi) is ‘1’. When 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”.

  Next, the edge line detection part 42 calculates | requires the sum total about the continuity c of all the attention points Pa on attention line La. The edge line detection unit 42 normalizes the continuity c by dividing the obtained sum of the continuity c by the number N of points of interest Pa. Then, the edge line detection unit 42 determines that the attention line La is an edge line when the normalized value exceeds the threshold θ. The threshold value θ is a value set in advance through experiments or the like.

That is, the edge line detection unit 42 determines whether or not the attention line La is an edge line based on the following Equation 3. Then, the edge line detection unit 42 determines whether or not all of the attention lines La drawn on the detection area A1 are edge lines.
[Formula 3]
Σc (xi, yi) / N> θ

  As described above, in the second embodiment, the attention point Pa is attributed based on the luminance difference between the attention point Pa on the attention line La and the reference point Pr on the reference line Lr, and the attribute along the attention line La is attributed. Since it is determined whether the attention line La is an edge line based on the continuity c of the image, the boundary between the high luminance area and the low luminance area is detected as an edge line, and an edge in line with a natural human sense Detection can be performed. This effect will be described in detail. FIG. 23 is a diagram illustrating an image example for explaining the processing of the edge line detection unit 42. In this image example, a first striped pattern 101 showing a striped pattern in which a high brightness area and a low brightness area are repeated, and a second striped pattern showing a striped pattern in which a low brightness area and a high brightness area are repeated. 102 is an adjacent image. Further, in this image example, 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.

  On the other hand, since the low luminance region and the high luminance region are adjacent to each other, if the edge is detected only by the luminance difference, the part 103 is recognized as an edge. However, since the edge line detection unit 42 determines the part 103 as an edge line only when the attribute of the luminance difference has continuity in addition to the luminance difference in the part 103, the edge line detection unit 42 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.

  Returning to FIG. 19, the three-dimensional object detection unit 34 a detects a three-dimensional object based on the amount of edge lines detected by the edge line detection unit 42. As described above, the three-dimensional object detection device 1a according to the present embodiment 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 34 a detects a three-dimensional object based on the amount of edge lines detected by the edge line detection unit 42. Specifically, the three-dimensional object detection unit 34a determines whether or not the amount of edge lines detected by the edge line detection unit 42 is equal to or greater than a predetermined threshold value β, and the amount of edge lines is determined to be a predetermined threshold value β. In the above case, the edge line detected by the edge line detection unit 42 is determined to be an edge line of a three-dimensional object.

  Furthermore, prior to detecting the three-dimensional object, the three-dimensional object detection unit 34a determines whether or not the edge line detected by the edge line detection unit 42 is correct. The three-dimensional object detection unit 34a determines whether or not the luminance change along the edge line of the bird's-eye view image on the edge line is equal to or greater than a predetermined threshold value tb. When the brightness change of the bird's-eye view image on the edge line is equal to or greater than the threshold value tb, it is determined that the edge line has been detected by erroneous determination. On the other hand, when the luminance change of the bird's-eye view image on the edge line is less than the threshold value tb, it is determined that the edge line is correct. The threshold value tb is a value set in advance by experiments or the like.

  FIG. 24 is a diagram showing the luminance distribution of the edge line, and FIG. 24A shows the edge line and luminance distribution when the adjacent vehicle V2 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.

  As shown in FIG. 24A, it is assumed that the attention line La set in the tire rubber portion of the adjacent vehicle V2 is determined to be an edge line in the bird's-eye view image. In this case, the luminance change of the bird's-eye view image on the attention line La is gentle. This is because the tire of the adjacent vehicle is extended in the bird's-eye view image by converting the image captured by the camera 10 into the bird's-eye view image. On the other hand, as shown in FIG. 24B, it is assumed that the attention line La set in the white character portion “50” drawn on the road surface in the bird's-eye view image is erroneously determined as an edge line. In this case, 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.

  Based on the difference in luminance distribution on the attention line La as described above, the three-dimensional object detection unit 34a determines whether or not the edge line is detected by erroneous determination. For example, when a 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. As described above, when the tire of the adjacent vehicle V2 is stretched, one portion of the tire is stretched, so that the luminance change of the bird's eye view image in the stretched direction tends to be small. On the other hand, when a character or the like drawn on the road surface is erroneously determined as an edge line, 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. In this case, the brightness change in the stretched direction tends to increase in the bird's-eye view image. Therefore, when the luminance change along the edge line is equal to or greater than the predetermined threshold value tb, the three-dimensional object detection unit 34a detects the edge line by erroneous determination. Judge that it is not caused. 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. On the other hand, when the change in luminance along the edge line is less than the predetermined threshold value tb, the three-dimensional object detection unit 34a determines that the edge line is an edge line of the three-dimensional object, and the three-dimensional object exists. Judge.

Specifically, the three-dimensional object detection unit 34a calculates the luminance change of the edge line according to any of the following 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 below 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 below 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). To do.
[Formula 4]
Evaluation value in the vertical equivalent direction = Σ [{I (xi, yi) −I (xi + 1, yi + 1)} ² ]
[Formula 5]
Evaluation value in the vertical equivalent direction = Σ | I (xi, yi) −I (xi + 1, yi + 1) |

Not only the above formula 5, but also the attribute b of the adjacent luminance value is binarized using the threshold value t2 as in the following formula 6, and the binarized attribute b is summed for all the attention points Pa. May be.
[Formula 6]
Evaluation value in the vertical equivalent direction = Σb (xi, yi)
However, when | I (xi, yi) −I (xi + 1, yi + 1) |> t2,
b (xi, yi) = 1
Other than the above
b (xi, yi) = 0

  When the absolute value of the luminance difference between the luminance value of the attention point Pai and the luminance value of the reference point Pri is larger than the threshold value t2, 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 34a sums the attributes b for all the attention points Pa on the attention line La and obtains an evaluation value in the vertical equivalent direction, whereby the edge line is caused by the three-dimensional object. It is determined whether or not a three-dimensional object exists.

Further, the edge waveform generation unit 43 shown in FIG. 19 generates a one-dimensional edge waveform EW _t based on the edge lines detected from the portions corresponding to the detection areas A1 and A2. For example, similarly to the generation of the differential waveform DW _t in the first embodiment, the edge waveform generation unit 43 counts the number of pixels corresponding to the edge line along the direction in which the three-dimensional object falls due to the viewpoint conversion to generate the frequency distribution. By doing so, a one-dimensional edge waveform ED _t can be generated.

Edge speed calculating unit 44 shown in FIG. 19, similarly to the difference speed calculation unit 35 of the first embodiment, based on the edge waveform EW _t and one unit time before edge waveform EW _t-1 at the current time, three-dimensional The moving speed of the object (the relative vehicle speed of the adjacent vehicle V2 with respect to the host vehicle V1) is calculated as the edge vehicle speed. That is, the edge vehicle speed calculation unit 44 calculates the movement distance of the object at the predetermined three-dimensional time from the time change of the edge waveforms EW _t and EW _t−1 and differentiates the calculated movement distance of the three-dimensional object with time. The relative moving speed of the three-dimensional object with respect to the vehicle V1 (the relative vehicle speed of the adjacent vehicle V2 with respect to the host vehicle V1) is calculated as the edge vehicle speed.

なお、上記の数式３において、Ｗｅｄはエッジ車速ＶＥＬｅｄに対する重み付けである。The estimated vehicle speed calculation unit 38a shown in FIG. 19 attaches foreign matter such as raindrops on the lens based on the headlight vehicle speed calculated by the headlight vehicle speed calculation unit 37 and the edge vehicle speed calculated by the edge vehicle speed calculation unit 44. The relative vehicle speed of the adjacent vehicle V2 in consideration of the above is calculated as the estimated vehicle speed. Specifically, the estimated vehicle speed calculation unit 38a calculates the edge vehicle speed VELed calculated by the edge vehicle speed calculation unit 44, and the headlight vehicle speed VELhl calculated by the headlight vehicle speed calculation unit 37, as shown in Equation 3 below. On the other hand, weighting according to the adhesion amount of foreign matters such as raindrops on the lens is performed, and weighted average of the weighted edge vehicle speed VELed and the headlight vehicle speed VELhl is taken into consideration, and the adhesion of foreign matters such as raindrops on the lens is taken into consideration. The relative vehicle speed of the adjacent vehicle V2 is calculated as the estimated vehicle speed VETest.

In Equation 3 above, Wed is a weight for the edge vehicle speed VELed.

  Here, when foreign matter such as raindrops adheres to the lens, it is difficult to detect an edge caused by the adjacent vehicle V2 because the image of the adjacent vehicle V2 is distorted or blurred by foreign matter such as raindrops. On the other hand, an edge caused by a foreign substance such as a raindrop may be detected. Therefore, when foreign matter such as raindrops adheres to the lens, an error occurs between the actual relative vehicle speed of the adjacent vehicle V2 and the edge vehicle speed VELed based on the edge, like the differential vehicle speed VELsa of the first embodiment. May end up. Therefore, in the second embodiment, as in the first embodiment, when the estimated vehicle speed VETest is calculated, the amount of foreign matter such as raindrops attached to the lens or the host vehicle V1 is overtaken by the adjacent vehicle V2. Or the weight Wed of the headlight vehicle speed VELhl and the weight Wed of the edge vehicle speed VELed are set according to the determination result of whether the host vehicle V1 overtakes the adjacent vehicle. That is, the estimated vehicle speed calculation unit 38a increases the weight Whl of the headlight vehicle speed VELhl with respect to the weight Wed of the edge vehicle speed VELed as the adhesion amount of foreign matters such as raindrops attached to the lens increases, and the host vehicle V1. When the vehicle is overtaken by the adjacent vehicle V2, the weight Whl of the headlight vehicle speed VELhl is increased with respect to the weighted Wed of the edge vehicle speed VELed compared to the case where the host vehicle V1 overtakes the adjacent vehicle.

  Based on the estimated vehicle speed VETest of the adjacent vehicle V2 calculated by the estimated vehicle speed calculation unit 38a, the detection determination distance calculation unit 39a uses the relative movement distance that the adjacent vehicle V2 has moved after the detection of the adjacent vehicle V2 as the detection determination distance Dist. calculate.

  As shown in FIG. 16, the threshold value changing unit 40a changes the edge threshold value t for detecting the three-dimensional object (adjacent vehicle V2) to a low value at the first timing t1 (time t1) when the adjacent vehicle V2 is detected. Then, after the first timing t1 when the adjacent vehicle V2 is detected, the changed edge threshold t is returned to the original value at the second timing t2 (time t2) when the detection determination distance Dist is equal to or greater than the predetermined reference distance Dstd. return. This facilitates detection of the adjacent vehicle V2 while it can be determined that the adjacent vehicle V2 exists in the detection areas A1 and A2 when the adjacent vehicle V2 is detected in the detection areas A1 and A2. This makes it possible to continuously detect the adjacent vehicle V2 existing in the detection areas A1 and A2 even when foreign matter such as raindrops adheres to the lens.

  Next, an adjacent vehicle detection method according to the second embodiment will be described. FIG. 25 is a flowchart showing details of the adjacent vehicle detection method according to the second embodiment. In FIG. 25, for convenience, processing for the detection area A1 will be described, but the same processing is executed for the detection area A2.

  In step S301, the camera 10 captures a predetermined area specified by the angle of view a and the attachment position, and the computer 30a acquires image data of the captured image P captured by the camera 10. Next, in step S302, the viewpoint conversion unit 31 performs viewpoint conversion on the acquired image data to generate bird's-eye view image data.

  Next, the brightness | luminance difference calculation part 41 sets attention line La on detection area | region A1 in step S303. At this time, the luminance difference calculation unit 41 sets a line corresponding to a line extending in the vertical direction in the real space as the attention line La. Next, the brightness | luminance difference calculation part 41 sets the reference line Lr on detection area | region A1 in step S304. At this time, the luminance difference calculation unit 41 sets a reference line Lr that corresponds to a line segment extending in the vertical direction in the real space and is separated from the attention line La by a predetermined distance in the real space.

  Next, the brightness | luminance difference calculation part 41 sets several attention point Pa on attention line La in step S305. At this time, the luminance difference calculation unit 41 sets a number of attention points Pa that are not problematic when the edge detection by the edge line detection unit 42 is performed. In step S306, the luminance difference calculation unit 41 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.

  Next, in step S307, the luminance difference calculation unit 41 calculates the luminance difference between the attention point Pa and the reference point Pr that have the same height in the real space. Then, the edge line detection unit 42 calculates the attribute s of each attention point Pa based on the luminance difference calculated by the luminance difference calculation unit 41 according to the above formula 1. In the present embodiment, the attribute s of each attention point Pa is calculated using the edge threshold t for detecting the edge of the three-dimensional object. The edge threshold value t may be changed in a threshold value changing process to be described later to promote detection of a three-dimensional object. When the edge threshold value t is changed, the changed edge threshold value t is changed to this step. 307 will be used.

  Next, in step S308, the edge line detection unit 42 calculates the continuity c of the attribute s of each attention point Pa according to the above equation 2. In step S309, the edge line detection unit 42 determines whether or not the value obtained by normalizing the sum of the continuity c is greater than the threshold value θ according to the above equation 3. When it is determined that the normalized value is larger than the threshold θ (step S309 = Yes), the edge line detection unit 42 detects the attention line La as an edge line in step S310. Then, the process proceeds to step S311. When it is determined that the normalized value is not larger than the threshold θ (step S309 = No), the edge line detection unit 42 does not detect the attention line La as an edge line, and the process proceeds to step S311.

  In step S311, the computer 30a determines whether or not the processing in steps S303 to S310 has been executed for all the attention lines La that can be set on the detection area A1. When it is determined that the above processing has not been performed for all the attention lines La (step S311 = No), the processing returns to step S303, a new attention line La is set, and the processing up to step S311 is repeated. On the other hand, if it is determined that the above process has been performed for all the attention lines La (step S311 = Yes), the process proceeds to step S312.

  In step S312, the three-dimensional object detection unit 34a calculates a luminance change along the edge line for each edge line detected in step S310. The three-dimensional object detection unit 34a calculates the luminance change of the edge line according to any one of the above formulas 4, 5, and 6. Next, in step S313, the three-dimensional object detection unit 34a excludes edge lines whose luminance change is equal to or greater than a predetermined threshold value tb from among 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 tb is a value set based on a luminance change generated by characters on the road surface, weeds on the road shoulder, or the like, which is obtained in advance through experiments or the like. On the other hand, the three-dimensional object detection unit 34a determines an edge line whose luminance change is less than the predetermined threshold value tb among the edge lines as an edge line of the three-dimensional object, and thereby detects a three-dimensional object present in the adjacent vehicle. .

  Next, in step S314, the three-dimensional object detection unit 34a determines whether or not the amount of the edge line is equal to or greater than a predetermined threshold value β. Here, the threshold value β is a value set in advance by experiments or the like. For example, when a four-wheeled vehicle is set as a three-dimensional object to be detected, the threshold value β is determined in advance by an experiment or the like. It is set based on the number of edge lines of the four-wheeled vehicle that appeared in A1. When it is determined that the amount of the edge line is equal to or larger than the threshold value β (step S314 = Yes), the three-dimensional object detection unit 34a determines that a three-dimensional object exists in the detection area A1, and proceeds to step S315. It is determined that a vehicle exists. On the other hand, when it is determined that the amount of the edge line is not equal to or larger than the threshold β (step S314 = No), the three-dimensional object detection unit 34a determines that there is no three-dimensional object in the detection area A1, and proceeds to step S316. It is determined that there is no adjacent vehicle in the detection area A1.

  Subsequently, the threshold value changing process according to the second embodiment will be described with reference to FIG. Note that the threshold value changing process according to the second embodiment is also performed in parallel with the adjacent vehicle detection process shown in FIG. 25, as in the first embodiment. In addition, the threshold value changing process according to the second embodiment is a three-dimensional object (adjacent vehicle V2) so that the adjacent vehicle V2 can be detected properly even when foreign matter such as raindrops adheres to the lens of the camera 10. The edge threshold value t for detecting the edge of) is changed. Therefore, the edge threshold t changed in this threshold value changing process is used when detecting the edge of the adjacent vehicle V2 in the adjacent vehicle detection process shown in FIG.

  In steps S401 to S404, as in steps S201 to S204 of the first embodiment, it is determined whether or not the adjacent vehicle V2 is detected in the adjacent vehicle detection process shown in FIG. 25 (step S401). When V2 is detected (step S401 = Yes), the headlight of the adjacent vehicle V2 is detected (step S402). If the headlight of the adjacent vehicle V2 is detected (step S403 = Yes), the headlight vehicle speed of the adjacent vehicle V2 is detected and calculated (step S404). On the other hand, when the adjacent vehicle V2 is not detected (step S401 = No), or when the headlight of the adjacent vehicle V2 is not detected (step S403 = No), the process returns to step S401, and the detection of the adjacent vehicle V2 and the adjacent The detection of the headlight of the vehicle V2 is repeated.

In step S405, the edge waveform generation unit 43 generates the edge waveform EW _t , and then the edge vehicle speed calculation unit 44 generates the edge waveforms EW _t and EW _t−1 based on the generated edge waveforms EW _t and EW _t−1. The relative vehicle speed of the adjacent vehicle V2 with respect to the host vehicle V1 is calculated as the edge vehicle speed VELed.

  In step S406, the estimated vehicle speed calculation unit 38a adheres to the lens of the camera 10 according to the above Equation 3 based on the headlight vehicle speed VELhl calculated in step S404 and the edge vehicle speed VELed calculated in step S405. The relative speed of the adjacent vehicle V2 in consideration of foreign matters such as raindrops is calculated as the estimated vehicle speed VETest. The estimated vehicle speed calculation unit 38a calculates the estimated vehicle speed VErest by calculating a weighted average of the headlight vehicle speed VELhl and the edge vehicle speed VELeed. At this time, as in the first embodiment, raindrops on the lens, etc. The weight Whl of the headlight vehicle speed VELhl and the weight Wed of the edge vehicle speed VELed are changed based on the amount of foreign matter attached and the determination result of whether or not the host vehicle V1 is a scene overtaken by the adjacent vehicle V2.

  In step S407, the detection determination distance calculation unit 39a detects the relative movement distance in which the adjacent vehicle V2 has moved after the detection of the adjacent vehicle V2 based on the estimated vehicle speed VETest of the adjacent vehicle V2 calculated in step S406. Calculated as the distance Dist.

  In step S408, the threshold value changing unit 40a sets an edge threshold value t for detecting the edge of the three-dimensional object (adjacent vehicle V2) in order to continuously detect the adjacent vehicle V2 existing in the detection areas A1 and A2. Be changed. Specifically, the threshold value changing unit 40 can detect the adjacent vehicle V2 existing in the detection areas A1 and A2 even when foreign matter such as raindrops is attached to the lens of the camera 10. The edge threshold value t is changed to a low value.

  In step S409, the threshold changing unit 40a determines whether or not the absolute value of the detection determination distance Dist calculated in step S407 is equal to or greater than a predetermined reference value Dstd. When the absolute value of the detection determination distance Dist is less than the reference value Dstd (step S409 = No), it is determined that the adjacent vehicle V2 exists in the detection areas A1 and A2, and the edge threshold value t is set to a low value. In step S409, the process waits. Thereby, also in 2nd Embodiment, it becomes possible to continue detecting the adjacent vehicle V2 which exists in detection area | region A1, A2. On the other hand, if the absolute value of the detection determination distance Dist is greater than or equal to the reference value Dstd (step S409 = Yes), it is determined that the adjacent vehicle V2 does not exist in the detection areas A1, A2, and the process proceeds to step S410 to change the threshold value. The edge threshold t is returned to the original value by the unit 40a.

  As described above, in the second embodiment, the edge of the adjacent vehicle V2 is detected from the image, and the relative vehicle speed of the adjacent vehicle V2 is calculated as the edge vehicle speed based on the detected edge. When a large amount of foreign matter such as raindrops is attached to the lens, the weight Whl of the headlight vehicle speed VELhl that is less affected by the foreign matter such as raindrops is increased, and when the foreign matter such as raindrops is little attached to the lens. Then, the weight Wed of the edge vehicle speed VELed is increased, and the relative vehicle speed of the adjacent vehicle V2 is calculated as the estimated vehicle speed VErest. Accordingly, the relative vehicle speed of the adjacent vehicle V2 can be appropriately calculated as the estimated vehicle speed VEEST regardless of whether or not foreign matters such as raindrops are attached to the lens.

  Then, based on the calculated estimated vehicle speed VEEST of the adjacent vehicle V2, the relative movement distance moved by the adjacent vehicle V2 after the detection of the adjacent vehicle V2 is calculated as the detection determination distance Dist, and the detection determination distance Dist is less than the reference distance Dstd. In the meantime, the edge threshold t for detecting the edge of the three-dimensional object (adjacent vehicle V2) is changed to a low value. As a result, in the second embodiment, it is possible to easily detect the adjacent vehicle V2 while it can be determined that the adjacent vehicle V2 exists in the detection areas A1 and A2, and therefore foreign matter such as raindrops adheres to the lens. Even when the vehicle is present, it is possible to continuously detect the adjacent vehicle V2 existing in the detection areas A1 and A2.

<< Third Embodiment >>
Next, the three-dimensional object detection device 1b according to the third embodiment will be described. As shown in FIG. 27, the three-dimensional object detection device 1b according to the third embodiment includes a computer 30b instead of the computer 30 of the first embodiment, and operates as described below. This is the same as in the first embodiment. Here, FIG. 27 is a block diagram showing details of the computer 30b according to the third embodiment.

  As shown in FIG. 27, the three-dimensional object detection device 1b according to the third embodiment includes a camera 10, a vehicle speed sensor 20, and a computer 30b. The computer 30b includes a viewpoint conversion unit 31, a positioning unit 32, and the like. The differential waveform generation unit 33, the three-dimensional object detection unit 34, the differential vehicle speed calculation unit 35, the headlight detection unit 36, the headlight vehicle speed calculation unit 37, the estimated vehicle speed calculation unit 38b, and the detection determination distance calculation unit 39 And a threshold value changing unit 40. In the following, an estimated vehicle speed calculation unit 38b having a configuration different from that of the first embodiment will be described, and the other configurations are the same as those of the first embodiment, and thus description thereof will be omitted.

  The estimated vehicle speed calculation unit 38b according to the third embodiment compares the headlight vehicle speed VELhl and the differential vehicle speed VELsa, and calculates the estimated vehicle speed VETest based on the comparison result. Specifically, the estimated vehicle speed calculation unit 38b, when the headlight vehicle speed VELhl is a positive value (that is, when the host vehicle V1 is overtaken by the adjacent vehicle V2), the difference between the headlight vehicle speed VELhl and the difference vehicle speed. The faster vehicle speed of VELsa is calculated as the estimated vehicle speed VETest. That is, when the headlight vehicle speed VELhl is a positive value, the estimated vehicle speed calculation unit 38b determines that the value obtained by subtracting the differential vehicle speed VELsa from the headlight vehicle speed VELhl is greater than 0 (VELhl−VELsa> 0), or When the value obtained by dividing the headlight vehicle speed VELhl by the differential vehicle speed VELsa is larger than 1 (VELhl / VELsa> 1), it is determined that the headlight vehicle speed VELhl is faster than the differential vehicle speed VELsa, and the headlight vehicle speed VELhl is set. Calculated as the estimated vehicle speed VETest. On the other hand, when the value obtained by subtracting the differential vehicle speed VELsa from the headlight vehicle speed VELhl is 0 or less (VELhl−VELsa ≦ 0), or the value obtained by dividing the headlight vehicle speed VELhl by the differential vehicle speed VELsa is 1 or less (VELhl). For / VELsa ≦ 1), the differential vehicle speed VELsa is calculated as the estimated vehicle speed VErest. When the headlight vehicle speed VELhl is a positive value and the headlight vehicle speed VELhl is compared with the differential vehicle speed VELsa, if the differential vehicle speed VELsa is a negative value, the differential vehicle speed VELsa is set to 0 (or (A positive value approximating 0) (that is, the lower limit value of the differential vehicle speed VELsa is set to 0).

  Further, the estimated vehicle speed calculation unit 38b is slower of the headlight vehicle speed VELhl and the differential vehicle speed VELsa when the headlight vehicle speed VELhl is a negative value (that is, when the host vehicle V1 overtakes the adjacent vehicle V2). The other vehicle speed is calculated as the estimated vehicle speed VETest. That is, when the headlight vehicle speed VELhl is a negative value, the estimated vehicle speed calculation unit 38b determines that the value obtained by subtracting the differential vehicle speed VELsa from the headlight vehicle speed VELhl is smaller than 0 (VELhl−VELsa <0), or When the value obtained by dividing the headlight vehicle speed VELhl by the differential vehicle speed VELsa is greater than 1 (VELhl / VELsa> 1), it is determined that the headlight vehicle speed VELhl is slower than the differential vehicle speed VELsa, and the headlight vehicle speed VELhl is estimated. Calculated as vehicle speed VErest. On the other hand, when the value obtained by subtracting the differential vehicle speed VELsa from the headlight vehicle speed VELhl is 0 or more (VELhl−VELsa ≧ 0), or the value obtained by dividing the headlight vehicle speed VELhl by the differential vehicle speed VELsa is 1 or less (VELhl). For / VELsa ≦ 1), the differential vehicle speed VELsa is calculated as the estimated vehicle speed VErest. When the headlight vehicle speed VELhl is a negative value and the headlight vehicle speed VELhl is compared with the differential vehicle speed VELsa, if the differential vehicle speed VELsa is a positive value, the differential vehicle speed VELsa is set to 0 (or (A negative value approximating 0) (that is, the upper limit value of the differential vehicle speed VELsa is set to 0).

  In addition, when the sign of the numerical value is reversed between the headlight vehicle speed VELhl and the differential vehicle speed VELsa, the differential vehicle speed VELsa may be calculated as the estimated vehicle speed VELest by giving priority to the differential vehicle speed VELsa.

  Then, the estimated vehicle speed VErest calculated by the estimated vehicle speed calculation unit 38 b is output to the detection determination distance calculation unit 39. Thereby, the detection determination distance calculation part 39 can calculate the relative movement distance of the adjacent vehicle V2 as the detection determination distance Dist by time-integrating the estimated vehicle speed VEEST acquired from the estimated vehicle speed calculation part 38b.

  As described above, in the third embodiment, when the estimated vehicle speed VELest is calculated, the headlight vehicle speed VELhl is compared with the differential vehicle speed VELsa. If the headlight vehicle speed VELhl is a positive value, the headlight vehicle speed VELhl is calculated. And the difference vehicle speed VELsa, the faster vehicle speed is calculated as the estimated vehicle speed VELest, and if the headlight vehicle speed VELhl is a negative value, the slower vehicle speed of the headlight vehicle speed VELhl and the difference vehicle speed VELsa is estimated. Calculated as vehicle speed VErest. Accordingly, in the third embodiment, when a foreign matter such as a water droplet is attached to the lens, as shown in FIG. 12C, the difference waveform is caused by the influence of the differential waveform caused by the water droplet attached to the lens. Even if the difference vehicle speed VELsa calculated based on the vehicle speed becomes closer to the moving speed of the own vehicle V1 than the actual moving speed of the adjacent vehicle V2 (the relative moving speed approaches 0), The estimated vehicle speed VETest of the vehicle V2 can be calculated appropriately.

<< 4th Embodiment >>
Next, the three-dimensional object detection device 1c according to the fourth embodiment will be described. As shown in FIG. 28, the three-dimensional object detection device 1c according to the fourth embodiment includes a computer 30c instead of the computer 30 of the first embodiment, and operates as described below. This is the same as in the first embodiment. Here, FIG. 28 is a block diagram showing details of the computer 30c according to the fourth embodiment.

  As shown in FIG. 28, the three-dimensional object detection device 1c according to the fourth embodiment includes a camera 10, a vehicle speed sensor 20, and a computer 30c. The computer 30c includes a viewpoint conversion unit 31, a positioning unit 32, The difference waveform generation unit 33, the three-dimensional object detection unit 34, the difference vehicle speed calculation unit 35, the headlight detection unit 36, the headlight vehicle speed calculation unit 37, the detection determination distance calculation unit 39b, and the threshold value change unit 40 It is composed of In the following, the detection determination distance calculation unit 39b having a configuration different from that of the first embodiment will be described, and the other configurations are the same as those of the first embodiment, and thus description thereof will be omitted.

  The detection determination distance calculation unit 39b acquires the differential vehicle speed VELsa from the differential vehicle speed calculation unit 35, acquires the headlight vehicle speed VELhl from the headlight vehicle speed calculation unit 37, and calculates the differential movement distance Dsa and the headlight movement distance Dhl. Then, the detection determination distance Dist is calculated by comparing the calculated difference moving distance Dsa and the headlight moving distance Dhl.

  Specifically, the detection determination distance calculation unit 39b calculates the difference moving distance Dsa by time-integrating the difference vehicle speed VELsa after detection of the adjacent vehicle V2, and the headlight vehicle speed VELhl after detection of the adjacent vehicle V2. Is integrated over time to calculate the headlight movement distance Dhl. Then, when the headlight vehicle speed VELhl is a positive value (that is, when the host vehicle V1 has been overtaken by the adjacent vehicle V2), the detection determination distance calculation unit 39b and the difference travel distance Dsa and the headlight travel distance The larger distance among Dhl is calculated as the detection determination distance Dist. That is, when the headlight vehicle speed VELhl is a positive value, the detection determination distance calculation unit 39b has a value obtained by subtracting the differential movement distance Dsa from the headlight movement distance Dhl is greater than 0 (Dhl−Dsa> 0). Is determined that the headlight movement distance Dhl is greater than the differential movement distance Dsa, and the headlight movement distance Dhl is calculated as the detection determination distance Dist. On the other hand, when the value obtained by subtracting the difference movement distance Dsa from the headlight movement distance Dhl is 0 or less (Dhl−Dsa ≦ 0), the difference movement distance Dsa is calculated as the detection determination distance Dist.

  Further, the detection determination distance calculation unit 39b, when the headlight vehicle speed VELhl is a negative value (that is, when the host vehicle V1 has overtaken the adjacent vehicle V2), the difference movement distance Dsa and the headlight movement distance Dhl. The smaller distance is calculated as the detection determination distance Dist. That is, when the headlight vehicle speed VELhl is a negative value, the detection determination distance calculation unit 39b subtracts the difference movement distance Dsa from the headlight movement distance Dhl is smaller than 0 (Dhl−Dsa <0). Is determined that the headlight movement distance Dhl is smaller than the differential movement distance Dsa, and the headlight movement distance Dhl is calculated as the detection determination distance Dist. Further, when the value obtained by subtracting the difference movement distance Dsa from the headlight movement distance Dhl is 0 or more (Dhl−Dsa ≧ 0), the difference movement distance Dsa is calculated as the detection determination distance Dist.

  In addition, when the sign value of the headlight vehicle speed VELhl is switched, the detection determination distance calculation unit 39b holds the detection determination distance Dist before the switch of the sign value of the headlight vehicle speed VELhl as the previous value Dpre. After clearing the judgment distance Dist, the differential vehicle speed VELsa after the positive / negative of the numerical value of the headlight vehicle speed VELhl is integrated over time to calculate the differential moving distance Dsa and the positive / negative of the numerical value of the headlight vehicle speed VELhl is switched. The headlight moving distance Dhl is calculated by time-integrating the headlight vehicle speed VELhl after that. Then, the detection determination distance calculation unit 39b calculates the detection determination distance Dist by adding the previous value Dpre to the comparison result obtained by comparing the differential movement distance Dsa and the headlight movement distance Dhl as described above.

  As described above, in the fourth embodiment, when the detection determination distance Dist is calculated, the differential vehicle speed VELsa after detection of the adjacent vehicle V2 is time-integrated to calculate the differential movement distance Dsa and the adjacent vehicle V2 of the adjacent vehicle V2. The headlight moving distance Dhl is calculated by time integration of the detected headlight vehicle speed VELhl. Then, the headlight moving distance Dhl is compared with the differential moving distance Dsa, and when the headlight vehicle speed VELhl is a positive value, the larger one of the differential moving distance Dsa and the headlight moving distance Dhl is detected. When the determination distance Dist is calculated and the headlight vehicle speed VELhl is a negative value, the smaller one of the differential movement distance Dsa and the headlight movement distance Dhl is calculated as the detection determination distance Dist. Accordingly, in the fourth embodiment, as in the third embodiment, when a foreign matter such as a water droplet is attached to the lens, as shown in FIG. 12C, the fourth embodiment is caused by the water droplet attached to the lens. Due to the influence of the difference waveform, the difference vehicle speed VELsa calculated based on the difference waveform is close to the movement speed of the own vehicle V1 as compared to the actual movement speed of the adjacent vehicle V2 (the relative movement speed becomes 0). Even in the case of approaching, the relative movement distance that the adjacent vehicle V2 has moved can be appropriately calculated as the detection determination distance Dist.

  The embodiment described above is described for facilitating the understanding of the present invention, and is not described for limiting the present invention. Therefore, each element disclosed in the above embodiment is intended to include all design changes and equivalents belonging to the technical scope of the present invention.

  For example, in the above-described embodiment, the configuration in which the difference threshold th or the edge threshold t is set to a low value when the adjacent vehicle V2 is detected in the detection areas A1 and A2 is exemplified. Instead of the difference threshold value th and the edge threshold value t, or in addition to the difference threshold value th and the edge threshold value t, the threshold value α and the threshold value β for detecting the three-dimensional object may be set to low values. May be changed to a low value. Thereby, even when foreign matter such as raindrops adheres to the lens, the adjacent vehicle V2 existing in the detection areas A1 and A2 can be continuously detected. Alternatively, the pixel value (or luminance value) output from the camera 10 may be increased when the adjacent vehicle V2 is detected in the detection areas A1 and A2. In this case, even if the difference threshold th and the edge threshold t are not changed, the difference pixel DP and the edge are easily detected, and the three-dimensional object (adjacent vehicle V2) is easily detected, and therefore exists in the detection areas A1 and A2. The adjacent vehicle V2 can be continuously detected. In this case, the pixel value (or luminance value) output from the camera 10 is returned to the original output value at the second timing t2 when the detection determination distance Dist is equal to or greater than the reference distance Dstd.

  Further, in the above-described embodiment, the configuration in which the three-dimensional object is detected as the adjacent vehicle V2 when the moving speed of the three-dimensional object satisfies the predetermined condition is exemplified. For example, the adjacent vehicle V2 is detected in the detection areas A1 and A2. In the case of detection, the above condition may be relaxed to facilitate detection of the adjacent vehicle V2. For example, in the above-described embodiment, when 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 host vehicle V1 is +60 km / h or less, the three-dimensional object is determined as the adjacent vehicle V2. However, when the adjacent vehicle V2 is detected in the detection areas A1 and A2, for example, the absolute moving speed of the three-dimensional object is 5 km / h or more and the relative moving speed of the three-dimensional object with respect to the host vehicle V1 is +70 km / h. When it is h or less, it can be set as the structure set as the structure which judges that a solid object is the adjacent vehicle V2. In this case, the above condition is returned to the original condition at the second timing t2 when the detection determination distance Dist becomes equal to or greater than the reference distance Dstd.

  Further, in the above-described embodiment, when calculating the estimated vehicle speed VEEST of the adjacent vehicle V2, as shown in FIG. 15, the difference from the weight Whl of the headlight vehicle speed VELhl according to the adhesion amount of foreign matters such as raindrops on the lens Although the configuration for setting the weight Wsa of the vehicle speed VELsa is illustrated, in this case, when no foreign matter such as raindrops is detected in the lens, the differential vehicle speed VELsa is calculated as the estimated vehicle speed VErest of the adjacent vehicle V2, and conversely, the raindrops When a foreign object such as the above is detected, the headlight vehicle speed VELhl may be calculated as the estimated vehicle speed VELest of the adjacent vehicle V2. That is, when foreign matter such as raindrops is not detected, the weight Wh1 of the headlight vehicle speed VELhl is set to 0, the estimated vehicle speed VErest of the adjacent vehicle V2 is calculated, and when foreign matter such as raindrops is detected, A configuration may be adopted in which the estimated vehicle speed VETest of the adjacent vehicle V2 is calculated by setting the weight Ws a of the differential vehicle speed VELsa to 0.

  Note that the camera 10 of the above-described embodiment corresponds to the imaging unit of the present invention, the viewpoint conversion unit 31 corresponds to the image conversion unit of the present invention, and the alignment unit 32, the difference waveform generation unit 33, and the luminance difference calculation unit 41. The edge line detection unit 42, the three-dimensional object detection units 34 and 34a, the difference vehicle speed calculation unit 35, the edge waveform generation unit 43, and the edge vehicle speed calculation unit 44 correspond to the three-dimensional object detection unit of the present invention, and are a headlight detection unit. 36 corresponds to the light source detection means of the present invention, the headlight vehicle speed calculation unit 37 corresponds to the second movement speed calculation means of the present invention, and the estimated vehicle speed calculation units 38 and 38a correspond to the estimated movement speed calculation means, foreign matter of the present invention. The detection determination distance calculating units 39 and 39a correspond to the detection unit and the determination unit, the detection distance calculation units 39 and 39a correspond to the detection distance calculation unit of the present invention, and the threshold value changing units 40 and 40a correspond to the control unit and night determination unit of the present invention.

DESCRIPTION OF SYMBOLS 1, 1a ... Three-dimensional object detection apparatus 10 ... Camera 20 ... Vehicle speed sensor 30, 30a ... Calculator 31 ... Viewpoint conversion part 32 ... Position alignment part 33 ... Difference waveform generation part 34, 34a ... Three-dimensional object detection part 35 ... Difference vehicle speed calculation part 36 ... Headlight detection unit 37 ... Headlight vehicle speed calculation unit 38, 38a ... Estimated vehicle speed calculation unit 39, 39a ... Detection determination distance calculation unit 40, 40a ... Threshold change unit 41 ... Luminance difference calculation unit 42 ... Edge line detection unit 43 ... edge waveform generating unit 44 ... edge speed calculating unit a ... angle A1, A2 ... detection area CP ... intersection DP ... differential pixel _{DW t, DW} t _'... differential waveform _{DW t1 ~DW m, DW m +} k ~DW tn ... small regions L1, L2 ... ground line La, Lb ... line P ... captured image on the direction in which the three-dimensional object collapses PB t _... bird's-eye view image PD t _... difference image V1 ... vehicle V2 ... adjacent vehicle

Claims (13)

An imaging means equipped with a lens mounted on the vehicle and forming an image of the rear of the host vehicle;
Three-dimensional object detection means for detecting a three-dimensional object behind the host vehicle based on a captured image obtained by the imaging means, and calculating a movement speed of the detected three-dimensional object as a first movement speed;
Light source detection means for detecting a light source present behind the host vehicle based on the captured image obtained by the imaging means;
Second moving speed calculating means for calculating a moving speed of the three-dimensional object as a second moving speed based on a time change of the light source detected by the light source detecting means;
An estimated movement speed calculating means for calculating, as an estimated movement speed, a relative movement speed of the three-dimensional object in consideration of adhesion of foreign matter on the lens based on the first movement speed and the second movement speed;
A detection determination distance calculation unit that calculates, as a detection determination distance, a relative movement distance that the three-dimensional object has moved after the detection of the three-dimensional object, based on the estimated movement speed calculated by the estimated movement speed calculation unit;
At the first timing when the three-dimensional object is detected, the detection of the three-dimensional object is promoted, and after the first timing, at the second timing when the absolute value of the detection determination distance is equal to or greater than a predetermined reference distance. And a control means for suppressing the detection of the three-dimensional object. The three-dimensional object detection device according to claim 1,
The three-dimensional object detection means includes:
Image conversion means for converting the captured image obtained by the imaging means into a bird's-eye view image;
The position of the bird's-eye view image at different times obtained by the image conversion means is aligned on the bird's-eye view, and the number of pixels indicating a predetermined difference is counted on the difference image of the aligned bird's-eye view image. Differential waveform information is generated by distribution, the three-dimensional object is detected based on the differential waveform information, and the first movement speed is calculated based on a temporal change in the waveform of the differential waveform information. A three-dimensional object detection device. The three-dimensional object detection device according to claim 2,
The three-dimensional object detection means generates the difference waveform information by counting the number of pixels indicating a difference equal to or greater than a predetermined first threshold on the difference image and performing frequency distribution, and the difference waveform information is determined to be a predetermined first value. When the threshold is 2 or more, the solid object is detected based on the difference waveform information,
The control means promotes detection of the three-dimensional object by changing the first threshold value or the second threshold value to a low value at the first timing, and the first threshold value at the second timing. Alternatively, the three-dimensional object detection device is configured to suppress the detection of the promoted three-dimensional object by changing the second threshold value to a value higher than the value changed at the first timing. The three-dimensional object detection device according to claim 2 ,
The three-dimensional object detection means generates the difference waveform information by counting the number of pixels indicating a difference equal to or greater than a predetermined first threshold on the difference image and performing frequency distribution, and the difference waveform information is determined to be a predetermined first value. When the threshold is 2 or more, the solid object is detected based on the difference waveform information,
The control means increases the pixel value of the difference image at the first timing , or counts the number of pixels indicating a difference equal to or greater than the first threshold on the difference image to the three-dimensional object detection means. By increasing the frequency-distributed difference value, the detection of the three-dimensional object is promoted, and at the second timing, the pixel value of the difference image is lowered, or the three-dimensional object detection means A three-dimensional object detection device that suppresses detection of the promoted three-dimensional object by lowering the output of the difference value changed at the first timing. The three-dimensional object detection device according to claim 1,
The three-dimensional object detection means includes:
Image conversion means for converting the captured image obtained by the imaging means into a bird's-eye view image;
Edge information is detected from the bird's-eye view image obtained by the image conversion means, the solid object is detected based on the edge information, and the first moving speed is determined based on the time change of the edge information. A three-dimensional object detection device characterized by calculating. The three-dimensional object detection device according to claim 5,
The three-dimensional object detection means detects, from the bird's eye view image, an edge component whose luminance difference between adjacent pixel areas is a predetermined first threshold value or more, and the edge information based on the edge component is a predetermined second threshold value or more. The solid object is detected based on the edge information,
The control means promotes detection of the three-dimensional object by changing the first threshold value or the second threshold value to a low value at the first timing, and the first threshold value at the second timing. Alternatively, the three-dimensional object detection device is configured to suppress the detection of the promoted three-dimensional object by changing the second threshold value to a value higher than the value changed at the first timing. The three-dimensional object detection device according to claim 5 ,
The three-dimensional object detection means detects, from the bird's eye view image, an edge component whose luminance difference between adjacent pixel areas is a predetermined first threshold value or more, and the edge information based on the edge component is a predetermined second threshold value or more. The solid object is detected based on the edge information,
The control means detects the solid object at the first timing by increasing the luminance value of the pixel region or causing the solid object detection means to output the edge information at a high value. Promoted by lowering the luminance value of the pixel area at the second timing , or causing the solid object detection means to output the edge information changed at the first timing at a lower value. A three-dimensional object detection apparatus, wherein the detection of the three-dimensional object is suppressed. The three-dimensional object detection device according to any one of claims 1 to 7,
Further comprising a foreign matter detection means for detecting foreign matter adhering to the lens based on the captured image;
The estimated moving speed calculating means weights each of the first moving speed and the second moving speed based on the amount of foreign matter attached to the lens, and weighted the first moving speed and the second moving speed. A three-dimensional object detection device, wherein a weighted average value with a speed is calculated as the estimated moving speed. The three-dimensional object detection device according to claim 8,
The estimated moving speed calculation means relatively decreases the weight of the first moving speed and relatively increases the weight of the second moving speed as the amount of foreign matter attached to the lens increases. A three-dimensional object detection device. The three-dimensional object detection device according to claim 8 or 9,
Based on the first moving speed or the second moving speed, further comprising a judging means for judging whether or not the host vehicle is overtaken by another vehicle;
The estimated moving speed calculating means relatively weights the first moving speed when the own vehicle is overtaking another vehicle by the determining means compared to when the own vehicle is overtaking the other vehicle. The three-dimensional object detection apparatus is characterized in that the weight of the second movement speed is relatively increased. The three-dimensional object detection device according to any one of claims 1 to 10,
It further includes a night determination means for determining whether it is night,
The control means promotes the detection of the three-dimensional object at the first timing and promotes the three-dimensional object at the second timing only when the night determination means determines that it is nighttime. 3D object detection apparatus characterized by suppressing detection of A captured image obtained by imaging the rear of the host vehicle is converted into a bird's-eye view image, the position of the bird's-eye view image at a different time is aligned on the bird's-eye view, and a predetermined image is displayed on the difference image of the aligned bird's-eye view image. The differential waveform information is generated by counting the number of pixels indicating the difference and frequency distribution, and detecting the three-dimensional object based on the difference waveform information, and from the time change of the waveform of the difference waveform information, A three-dimensional object detection method for calculating a movement speed as a first movement speed and determining whether the three-dimensional object is another vehicle based on the first movement speed of the three-dimensional object,
A light source existing behind the host vehicle is detected based on the captured image, a moving speed of the three-dimensional object is calculated as a second moving speed based on a temporal change of the light source, and the first moving speed and the second moving speed are calculated. The relative movement speed of the three-dimensional object in consideration of adhesion of foreign matter on the lens is calculated as an estimated movement speed based on the speed, and the relative movement in which the three-dimensional object has moved after the detection of the three-dimensional object based on the estimated movement speed By calculating the distance as the detection determination distance, at the first timing when the solid object is detected, the solid object is detected based on the difference waveform information, or the solid object is determined as the other vehicle. After the first timing, the detected three-dimensional object or the three-dimensional object is accelerated at a second timing at which the absolute value of the detection determination distance is equal to or greater than a predetermined reference distance. Three-dimensional object detection method characterized by suppressing determine that the serial other vehicles. A captured image obtained by imaging the rear of the host vehicle is converted into a bird's-eye view image, edge information is detected from the bird's-eye view image, a solid object is detected based on the edge information, and the solid object is detected based on the edge information. Is a three-dimensional object detection method for determining whether or not the vehicle is another vehicle,
The moving speed of the three-dimensional object is calculated as a first moving speed from the time change of the edge information, a light source existing behind the host vehicle is detected based on the captured image, and the three-dimensional object is detected based on the time change of the light source. It calculates the moving velocity of the object as the second moving speed, on the basis of the a first moving speed and said second moving speed, a relative movement speed of the three-dimensional object in consideration of the adhesion of foreign substances in lenses as the estimated movement speed And calculating the relative movement distance that the three-dimensional object has moved after detection of the three-dimensional object as a detection determination distance based on the estimated movement speed, and at the first timing when the three-dimensional object is detected, the edge The detection of the three-dimensional object based on the information or the determination of the three-dimensional object as the other vehicle is promoted, and after the first timing, the absolute value of the detection determination distance is a predetermined reference value. In the second timing to be the distance or more, three-dimensional object detection method characterized by inhibiting the detection or the three-dimensional object of the three-dimensional object was facilitated by determining that the another vehicle.

Images