JP5668891B2 - Three-dimensional object detection device - Google Patents

Description

The present invention relates to a three-dimensional object detection device.
This application claims priority based on Japanese Patent Application No. 2012-0466648 filed on Mar. 2, 2012. Regarding designated countries where incorporation by reference of documents is permitted, 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.

  Conventionally, a vehicle detection device that extracts an edge component from a captured image and detects another vehicle based on the extracted edge component is known (see Patent Document 1).

JP 2000-113201 A

  However, in the prior art, when a local light change occurs due to smear or flare, an edge component generated by the smear or flare may be erroneously detected as an edge component of another vehicle. In general, because the brightness of the areas corresponding to smears and flares is high, it is possible to eliminate the effects of light due to smears and flares by detecting solid objects except for areas with high brightness. When converting to an image and detecting a three-dimensional object based on the bird's-eye view image, the larger the rear distance from the host vehicle, the larger the area corresponding to smear or flare when converting the captured image to the bird's-eye view image. As a result, the brightness of the area corresponding to the smear or flare is lowered, and the smear or flare light image having such a low brightness may be erroneously detected as an adjacent vehicle.

  The problem to be solved by the present invention is to provide a three-dimensional object detection device that can appropriately detect other vehicles that are detection targets by eliminating the influence of light due to smear and flare.

  The present invention detects a high-luminance region whose luminance is equal to or greater than a predetermined threshold among detection regions, sets an area including the high-luminance region as a detection control region that is difficult to detect a three-dimensional object, and The longer the distance is, the wider the detection control area is set, and the three-dimensional object is detected in the detection area where the detection control area is set.

  According to the present invention, the larger the rear distance from the imaging means, the wider the detection control area that covers the high-luminance area, thereby supporting not only the high-luminance area corresponding to smear and flare but also smear and flare. Even in a region where the brightness is low, it is possible to eliminate the influence of light due to smears and flares, thereby appropriately detecting other vehicles as detection targets.

FIG. 1 is a schematic configuration diagram of a vehicle equipped with the three-dimensional object detection device according to the first embodiment. FIG. 2 is a plan view showing a traveling state of the vehicle of FIG. FIG. 3 is a block diagram showing details of the computer according to the first embodiment. FIGS. 4A and 4B are diagrams for explaining the outline of the processing of the alignment unit according to the first embodiment, in which FIG. 4A is a plan view showing the moving state of the vehicle, and FIG. 4B is an image showing the outline of alignment. It is. FIG. 5 is a schematic diagram illustrating how a differential waveform is generated by the three-dimensional object detection unit according to the first embodiment. FIG. 6 is a diagram illustrating a small region divided by the three-dimensional object detection unit according to the first embodiment. FIG. 7 is a diagram illustrating an example of a histogram obtained by the three-dimensional object detection unit according to the first embodiment. FIG. 8 is a diagram illustrating weighting by the three-dimensional object detection unit according to the first embodiment. FIG. 9 is a diagram illustrating another example of a histogram obtained by the three-dimensional object detection unit according to the first embodiment. FIG. 10 is a diagram for explaining a method of determining an adjacent vehicle existing in an adjacent lane. FIG. 11 is a diagram for explaining a detection control method by the detection control unit according to the first embodiment. FIG. 12 is a flowchart illustrating the adjacent vehicle detection method according to the first embodiment. FIG. 13 is a block diagram showing details of the computer according to the second embodiment. FIG. 14 is a diagram for explaining a detection control method by the detection control unit according to the second embodiment. FIG. 15 is a flowchart illustrating the adjacent vehicle detection method according to the second embodiment (part 1). FIG. 16 is a flowchart illustrating the adjacent vehicle detection method according to the second embodiment (part 2). FIG. 17 is a diagram for explaining the specific luminance region detection method according to the second embodiment. FIG. 18 is a diagram for explaining another example of the specific luminance region detection method according to the second embodiment. FIG. 19 is a block diagram illustrating details of the computer according to the third embodiment. 20A and 20B are diagrams illustrating a traveling state of the vehicle, in which FIG. 20A is a plan view illustrating the positional relationship of the detection region and the like, and FIG. 20B is a perspective view illustrating the positional relationship of the detection region and the like in real space. FIG. 21 is a diagram for explaining the operation of the luminance difference calculation unit according to the third embodiment. FIG. 21A is a diagram illustrating the positional relationship among the attention line, reference line, attention point, and reference point in the bird's-eye view image. (B) is a figure which shows the positional relationship of the attention line, reference line, attention point, and reference point in real space. 22A and 22B are diagrams for explaining the detailed operation of the luminance difference calculation unit according to the third embodiment. FIG. 22A is a diagram showing a detection area in a bird's-eye view image, and FIG. It is a figure which shows the positional relationship of a line, a reference line, an attention point, and a reference point. FIG. 23 is a diagram illustrating an example of an image for explaining the edge detection operation. 24A and 24B are diagrams showing edge lines and luminance distribution on the edge lines. FIG. 24A is a diagram showing the luminance distribution when a three-dimensional object (adjacent vehicle) is present in the detection area, and FIG. It is a figure which shows luminance distribution when a solid object does not exist in FIG. FIG. 25 is a flowchart illustrating an adjacent vehicle detection method according to the third embodiment. FIG. 26 is a graph showing an example of the threshold th in the mask area.

<< First Embodiment >>
FIG. 1 is a schematic configuration diagram of a vehicle equipped with a three-dimensional object detection device 1 according to the first embodiment. The three-dimensional object detection device 1 according to the present embodiment is intended to detect other vehicles (hereinafter also referred to as adjacent vehicles) existing in adjacent lanes 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 shown in order to clarify the connection relationship.

  As shown in FIG. 3, the computer 30 includes a viewpoint conversion unit 31, a positioning unit 32, a three-dimensional object detection unit 33, and a detection control unit 34. 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 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. By setting the pixel value of the difference image PD _t to “1” when the threshold value is equal to or greater than the threshold th, and setting the pixel value of the difference image PD _t to “0” when the absolute value is less than the predetermined threshold th, Data of the difference image PD _t as shown on the right side of FIG. 4B can be generated.

Returning to FIG. 3, the three-dimensional object detection unit 33 detects a three-dimensional object based on the data of the difference image PD _t shown in FIG. At this time, the three-dimensional object detection unit 33 also calculates the movement distance of the three-dimensional object in the real space. In detecting the three-dimensional object and calculating the movement distance, the three-dimensional object detection unit 33 first generates a differential waveform.

In generating the difference waveform, the three-dimensional object detection unit 33 sets a detection region in the difference image PD _t . The three-dimensional object detection device 1 of the present example is intended to calculate a movement distance for an adjacent vehicle 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, A2 are set on the rear side 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.

  Further, as shown in FIG. 2, the three-dimensional object detection unit 33 recognizes the sides (sides along the traveling direction) of the set detection areas A1 and A2 on the own vehicle V1 side 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 three-dimensional object detection unit 33 generates a differential waveform. As shown in FIG. 5, the three-dimensional object detection unit 33 calculates a differential waveform from a portion corresponding to the detection areas A <b> 1 and A <b> 2 in the difference image PD _t (right diagram in FIG. 4B) calculated by the alignment unit 32. DW _t is generated. At this time, the three-dimensional object detection unit 33 generates a differential waveform DW _t along the direction in which the three-dimensional object falls by viewpoint conversion. 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 three-dimensional object detection unit 33 defines a line La on the direction the three-dimensional object collapses on data of the difference image PD _t. Then, the three-dimensional object detection 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 three-dimensional object detection unit 33 counts the number of difference pixels DP, and then obtains an intersection CP between the line La and the ground line L1. Then, the three-dimensional object detection unit 33 associates the intersection CP with the count number, determines the horizontal axis position based on the position of the intersection CP, that is, the position on the vertical axis in the right diagram of FIG. The axis position, that is, the position on the right and left axis in the right diagram of FIG.

Similarly, the three-dimensional object detection unit 33 defines lines Lb, Lc... In the direction in which the three-dimensional object falls, counts the number of difference pixels DP, and determines the horizontal axis position based on the position of each intersection CP. Then, the vertical axis position is determined from the count number (number of difference pixels DP) and plotted. The three-dimensional object detection unit 33 generates the differential waveform DW _t as shown in the right diagram of FIG.

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 the three-dimensional object detection unit 33 determines the vertical axis position from the count number of the difference pixels DP, the three-dimensional object detection unit 33 is normalized based on the distance at which the lines La and Lb in the direction in which the three-dimensional object falls and the detection area A1 overlap. Turn into. As a specific example, in the left diagram of FIG. 5, there are six difference pixels DP on the line La, and there are five difference pixels DP on the line Lb. For this reason, in determining the vertical axis position from the count number in FIG. 5, the three-dimensional object detection 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.

After the generation of the difference waveform DW _t , the three-dimensional object detection unit 33 detects the adjacent vehicle existing in the adjacent lane based on the generated difference waveform DW _t . Three-dimensional object detection unit 33 calculates the moving distance in comparison with the differential waveform DW _t-1 of the previous differential waveform DW _t and a time instant at the current time. That is, the three-dimensional object detection unit 33 calculates the movement distance from the time change of the difference waveforms DW _t and DW _t−1 .

More specifically, the three-dimensional object detection unit 33 divides the differential waveform DW _t into a plurality of small regions DW _{t1 to} DW _tn (n is an arbitrary integer equal to or greater than 2) as shown in FIG. FIG. 6 is a diagram illustrating the small areas DW _{t1 to} DW _tn divided by the three-dimensional object detection unit 33. The small regions 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 three-dimensional object detection unit 33 obtains an offset amount (amount of movement of the differential waveform in the horizontal axis direction (vertical direction in FIG. 6)) for each of the small regions 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). At this time, three-dimensional object detection unit 33, for each small area _DW t1 _{~DW tn,} when moving the differential waveform _{DW t1} before one unit time in the horizontal axis direction, the differential waveform DW _t at the current time The position where the error is minimized (the position in the horizontal axis direction) is determined, and the amount of movement in the horizontal axis between the original position of the differential waveform DW _t-1 and the position where the error is minimized is obtained as an offset amount. Then, the three-dimensional object detection unit 33 counts the offset amount obtained for each of the small areas DW _{t1 to} DW _tn and forms a histogram.

FIG. 7 is a diagram illustrating an example of a histogram obtained by the three-dimensional object detection unit 33. As shown in FIG. 7, the offset amount, which is the amount of movement that minimizes the error between each of the small areas DW _{t1 to} DW _tn and the differential waveform DW _t-1 one time before, has some variation. For this reason, the three-dimensional object detection unit 33 forms a histogram of offset amounts including variations, and calculates a movement distance from the histogram. At this time, the three-dimensional object detection unit 33 calculates the moving distance of the adjacent vehicle from the maximum value of the histogram. That is, in the example illustrated in FIG. 7, the three-dimensional object detection unit 33 calculates the offset amount indicating the maximum value of the histogram as the movement distance τ ^* . As described above, in the present 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 adjacent vehicle with respect to the own vehicle. For this reason, when calculating the absolute movement distance, the three-dimensional object detection unit 33 calculates the absolute movement distance based on the obtained movement distance τ ^* and the signal from the vehicle speed sensor 20.

Thus, in the present embodiment, a one-dimensional waveform is obtained by calculating the moving distance of the three-dimensional object 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. Thus, the movement distance is calculated from the offset amount of the information, 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 three-dimensional object detection unit 33 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. 8 is a diagram illustrating weighting by the three-dimensional object detection unit 33.

As shown in FIG. 8, the small region DW _m (m is an integer of 1 to n−1) is flat. That is, in the small area DW _m , the difference between the maximum value and the minimum value of the number of pixels indicating a predetermined difference is small. Three-dimensional object detection unit 33 to reduce the weight for such small area DW _m. This is because the flat small area DW _m has no characteristics and is likely to have a large error in calculating the offset amount.

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. Three-dimensional object detection unit 33 increases the weight for such small area DW _m. This is because the small region DW _{m + k} rich in undulations is characteristic and there is a high possibility that the offset amount can be accurately calculated. By weighting in this way, the calculation accuracy of the movement distance can be improved.

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 three-dimensional object detection unit 33 calculates the movement distance from the offset amount of the differential waveform DW _t when the error between the differential waveform DW _t and the differential waveform DW _t−1 is minimized. That is, the method for obtaining the offset amount of the difference waveform DW _t in the difference waveform DW _t-1 and the current time before one unit time is not limited to the contents.

  In the present embodiment, the three-dimensional object detection unit 33 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 three-dimensional object detection unit 33 ignores the offset amount corresponding to the stationary object among the maximum values of the histogram and calculates the moving distance of the adjacent vehicle.

  FIG. 9 is a diagram illustrating another example of a histogram obtained by the three-dimensional object detection unit 33. When there is a stationary object in addition to the adjacent vehicle 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 three-dimensional object detection unit 33 calculates the offset amount for the stationary object from the moving speed, ignores the maximum value corresponding to the offset amount, and calculates the moving distance of the three-dimensional object 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, when there are a plurality of maximum values, it is assumed that there are a plurality of adjacent vehicles within the angle of view of the camera 10. However, it is extremely rare that a plurality of adjacent vehicles exist in the detection areas A1 and A2. For this reason, the three-dimensional object detection unit 33 stops calculating 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.

  Furthermore, the three-dimensional object detection unit 33 calculates the relative movement speed of the three-dimensional object with respect to the host vehicle by differentiating the calculated relative movement distance of the three-dimensional object with respect to time, and the vehicle speed sensor The absolute moving speed of the three-dimensional object is calculated by adding the vehicle speed detected by the vehicle 20. The three-dimensional object detection unit 33 also calculates the relative movement speed of the host vehicle with respect to the three-dimensional object from the relative movement distance of the three-dimensional object.

After the generation of the difference waveform DW _t , the three-dimensional object detection unit 33 detects the adjacent vehicle existing in the adjacent lane based on the generated difference waveform DW _t . Here, FIG. 10 is a diagram for explaining a method of determining other vehicles existing in the adjacent lane, and shows an example of the difference waveform DW _t and a threshold value α for detecting the other vehicle existing in the adjacent lane. Yes. For example, as illustrated in FIG. 10, the three-dimensional object detection unit 33 determines whether or not the peak of the generated difference waveform DW _t is _equal to or greater than a predetermined threshold α, and the peak of the difference waveform DW _t is _{equal to} the predetermined threshold α. If it is above, the detected three-dimensional object is determined to be an adjacent vehicle existing in the adjacent lane, and when the peak of the differential waveform DW _t is not equal to or greater than the predetermined threshold value α, the detected three-dimensional object is in the adjacent lane. It determines with it not being the adjacent vehicle which exists.

The detection control unit 34 shown in FIG. 3 sets a mask area including areas corresponding to smears and flares in the detection areas A1 and A2 in order to eliminate the influence of smears and flares, and masks from the detection areas A1 and A2. In order to detect a three-dimensional object from the detection target area excluding the area, data generation of the difference image DP _t by the alignment unit 32 is controlled. Here, FIG. 11 is a diagram for explaining a detection control method by the detection control unit 34.

Specifically, the detection control unit 34, the bird's-eye view image PB _t, detects a luminance value at each position in the detection areas A1, A2, as shown in FIG. 11 right panel, among the detection areas A1, A2 A region having a predetermined luminance threshold value sb or more is detected as a specific luminance region corresponding to smear or flare. In the present embodiment, since the purpose is to eliminate the influence of smear and flare, the predetermined luminance threshold sb is set to a luminance value that can be determined as an area corresponding to smear or flare. For example, in the example shown in FIG. 11, since two smears occur in the detection area A1, the detection control unit 34 converts two areas having a luminance value equal to or higher than the luminance threshold sb in the detection area A1 to smear. Corresponding specific luminance regions Rb ₁ and Rb ₂ are detected.

Then, the detection control unit 34 sets a region including the specific luminance region as a mask region. Specifically, the detection control unit 34 sets the mask area including the specific luminance area in a wider range as the rear distance from the host vehicle V1 (camera 10) is larger. For example, in the example shown in FIG. 11, the specific luminance region Rb ₁ has a rear distance D ₁ from the host vehicle V ₁ (camera 10), and the specific luminance region Rb ₂ has a rear distance from the host vehicle V 1 (camera 10). D ₂ greater than D ₁ . Therefore, the detection control unit 34, than the mask region Rm ₁ the rear distance from the vehicle V1 (camera 10) comprises a specific luminance region Rb ₁ is _{D 1,} the rear distance from the vehicle V1 (camera 10) The mask region Rm ₂ including the specific luminance region Rb ₂ that is D ₂ is set in a wide range.

  For example, the detection control unit 34 may be configured to set a mask area including the specific luminance area in a wide range in proportion to the rear distance from the host vehicle V1 (camera 10), or the host vehicle V1. For each rear distance from (camera 10), an amount (pixel amount) for expanding the mask area is determined in a stepwise manner, and a predetermined amount (pixel amount) according to the rear distance from the host vehicle V1 (camera 10). ), The mask area may be widened.

  Next, the adjacent vehicle detection process according to the present embodiment will be described. FIG. 12 is a flowchart illustrating the adjacent vehicle detection process according to the first embodiment.

As shown in FIG. 12, 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 detection control unit 34 detects a region having a luminance value equal to or greater than the predetermined threshold sb in the detection region A1 as a specific luminance region (step S103), and sets a mask region including the detected specific luminance region ( Step S104).

Specifically, the detection control unit 34 sets the mask region in a wider range as the rear distance from the host vehicle V1 (camera 10) to the specific luminance region is larger. For example, the detection control unit 34, as shown in FIG. 11, the rear of the mask region Rm ₂ than the mask region Rm _1, is set to a range wider than the mask region Rm _1.

Then, 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 the data of the difference image PD _t ( Step S105). When generating the data of the difference image PD _t , the detection control unit 34 excludes the mask area set in step S104 from the generation target of the data of the difference image PD _t and removes the mask area from the detection area A1. in the detection target area to generate data of the difference image PD _t, controls the positioning unit 32. Thereby, for example, the alignment unit 32 uniformly sets the pixel values of the difference image PD _t to “0” in the mask region, while the absolute value is equal to or greater than the predetermined threshold th in the detection target region. In this case, the pixel value of the difference image PD _t is set to “1”, and the pixel value of the difference image PD _t is set to “0” when the absolute value is less than the predetermined threshold th. Thereby, the alignment unit 32 can generate data of the difference image PD _t in the detection target region excluding the mask region from the detection region A1.

Then, the three-dimensional object detection unit 33 counts the number of difference pixels DP having a pixel value “1”, and generates a difference waveform DW _t (step S106). In the present embodiment, since the pixel values of the difference image PD _t are uniformly set to “0” in the mask region, the three-dimensional object detection unit 33 detects the detection target region excluding the mask region in the detection region A1. The differential waveform DW _t is generated at.

Then, the three-dimensional object detection unit 33 determines whether or not the peak of the differential waveform DW _t is greater than or _{equal to} the threshold value α (step S107). 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 (detection target region). 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 S107 = No), the three-dimensional object detection unit 33 determines that there is no three-dimensional object and there is no adjacent vehicle (step). S116). And it returns to step S101 and repeats the process shown in FIG. Thus, in the present embodiment, the three-dimensional object detection unit 33 detects a three-dimensional object only in the detection target area excluding the mask area corresponding to smear and flare in the detection area A1.

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 S107 = Yes), the three-dimensional object detection unit 33 determines that a three-dimensional object exists in the adjacent lane, and proceeds to step S108. The three-dimensional object detection unit 33 divides the differential waveform DW _t into a plurality of small areas DW _{t1 to} DW _tn . Next, the three-dimensional object detection unit 33 performs weighting for each of the small areas DW _{t1 to} DW _tn (Step S109), calculates an offset amount for each of the small areas DW _{t1 to} DW _tn (Step S110), and adds the weight. A histogram is generated (step S111).

  Then, the three-dimensional object detection unit 33 calculates a relative movement distance that is a movement distance of the three-dimensional object with respect to the host vehicle V1 based on the histogram (step S112). Next, the three-dimensional object detection unit 33 calculates the absolute movement speed of the three-dimensional object from the relative movement distance (step S113). At this time, the three-dimensional object detection unit 33 calculates the relative movement speed by differentiating the relative movement distance with respect to time, and 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 33 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 is +60 km / h or less (step S114). When both are satisfied (step S114 = Yes), the three-dimensional object detection unit 33 determines that the detected three-dimensional object is an adjacent vehicle existing in the adjacent lane, and an adjacent vehicle exists in the adjacent lane (step S115). Then, the process shown in FIG. On the other hand, when either one is not satisfied (step S114 = No), the three-dimensional object detection unit 33 determines that there is no adjacent vehicle in the adjacent lane (step S116). And it returns to step S101 and repeats the process shown in FIG.

  In the present embodiment, the rear side of the host vehicle is set as the detection areas A1 and A2, and emphasis is placed on whether or not there is a possibility of contact when the host vehicle changes lanes. For this reason, the process of step S114 is performed. That is, assuming that the system according to the present embodiment is operated on a highway, if the speed of the adjacent vehicle is less than 10 km / h, even if the adjacent vehicle exists, the host vehicle is required to change the lane. Because it is located far behind, there are few problems. Similarly, when the relative moving speed of the adjacent vehicle to the own vehicle exceeds +60 km / h (that is, when the adjacent vehicle is moving at a speed higher than 60 km / h than the speed of the own vehicle), when changing the lane Is less likely to be a problem because it is moving in front of the host vehicle. For this reason, it can be said that the adjacent vehicle which becomes a problem at the time of lane change is judged in step S114.

  In step S114, it is determined whether or not the absolute movement speed of the adjacent vehicle is 10 km / h or more and the relative movement speed of the adjacent vehicle to the host vehicle is +60 km / h or less. 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 that the stationary object is determined to be an adjacent vehicle. Further, depending on the noise, the relative speed of the adjacent vehicle to the host vehicle 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 S114, it may be determined that the absolute moving speed of the adjacent vehicle is not negative or not 0 km / h. Further, in the present embodiment, since an emphasis is placed on whether there is a possibility of contact when the host vehicle changes lanes, a warning sound is sent to the driver of the host vehicle when an adjacent vehicle is detected in step S115. Or a display corresponding to a warning may be performed by a predetermined display device.

As described above, in the first embodiment, two captured images at different times are converted into bird's-eye view images, the difference image PD _t is generated based on the difference between the two bird's-eye view images, and the difference image PD _t By generating the differential waveform DW _t from the upper difference data, the adjacent vehicle existing in the adjacent lane is detected based on the generated differential waveform DW _t . In the first embodiment, when the difference image PD _t is generated based on the difference between the two bird's-eye view images, the area having the luminance of a predetermined value or higher in the detection areas A1 and A2 is set to smear or flare. The mask area including the specific luminance area is set to a wider range as the backward distance from the camera 10 is detected as the corresponding specific luminance area. Then, in the detection areas A1, A2 only the detection target area excluding the mask region, and detects a difference of the two bird's-eye view image to generate a difference image PD _t corresponding only to the detection target area. As a result, in this embodiment, not only a high-luminance area corresponding to smear or flare, but also a low-luminance area generated by stretching the area corresponding to smear or flare when the captured image is converted into a bird's-eye view image. In addition, since the three-dimensional object can be excluded from the detection target area, it is possible to appropriately detect the three-dimensional object by eliminating the influence of smear and flare.

  That is, in general, when a captured image in which smear or flare occurs is converted into a bird's-eye view image, the region corresponding to smear or flare is smaller in bird's eye view as the rear distance from the vehicle V1 to the position where smear or flare occurs is smaller. Appear clearly in the visual image. On the other hand, when a captured image in which smear or flare occurs is converted into a bird's-eye view image, the region corresponding to the smear or flare is stretched as the rear distance from the vehicle V1 to the position where the smear or flare occurs is increased. , The area corresponding to smear and flare spreads. In the region corresponding to the smear or flare stretched in this way, the luminance decreases as the distance from the center position of the smear or flare increases. Therefore, for example, even if a solid object is detected except for a high-luminance area that can be determined as smear or flare, in areas corresponding to smear or flare that are far from the center position of smear or flare and have low brightness, In some cases, an image of light due to smear or flare is erroneously detected as an adjacent vehicle.

  In contrast, in the present embodiment, the larger the rear distance from the host vehicle V1 (camera 10) to the specific luminance area, the wider the mask area including the specific luminance area, and the mask area in the detection area A1. By detecting a three-dimensional object in the detection target area excluding, it is possible to eliminate the influence of light due to smear or flare even at a position where the brightness is far from the center position of smear or flare. It is possible to effectively prevent the image from being erroneously detected as an adjacent vehicle.

<< Second Embodiment >>
Next, the three-dimensional object detection device 1a according to the second embodiment will be described. As shown in FIG. 13, the three-dimensional object detection device 1 a according to the second embodiment includes a detection control unit 34 a and a storage unit 35, and is the same as the first embodiment except that it operates as described below. is there. Here, FIG. 13 is a block diagram showing details of the computer 30a according to the second embodiment.

In the second embodiment, as shown in FIG. 14, the detection control unit 34a shown in FIG. 13 detects the specific luminance region as the rear distance from the host vehicle V1 (camera 10) to the specific luminance region increases. The brightness threshold sb is set low, and an area that is equal to or greater than the set brightness threshold sb is detected as a specific brightness area. Then, the detection control unit 34a, the detection target region excluding the specific luminance area from the detection region A1, A2, so as to generate image data of the difference image PD _t, controls the positioning unit 32.

  In addition, for example, even when the sun shines in clouds and the brightness value of the area corresponding to smear or flare is less than the brightness threshold sb, the area corresponding to such smear or flare is detected as the specific brightness area. Even when the specific luminance region having a luminance value equal to or higher than the luminance threshold sb cannot be detected at the time of the current processing, the control unit 34a exists around the specific luminance region detected at the previous processing and has a predetermined luminance value. A region having a peak is detected as a specific luminance region corresponding to a smear or flare having a low luminance, and this is set as a mask region. Thereby, in 2nd Embodiment, it can prevent effectively that the image of the light of the smear and flare which the sun hit with the cloud, for example, and the brightness | luminance fell is detected as an adjacent vehicle.

  The storage unit 35 is a storage medium such as a ROM or a RAM, and stores the detection position of the specific luminance area detected by the detection control unit 34a. The position information of the specific luminance area stored in the storage unit 35 is appropriately referred to by the above-described detection control unit 34a.

  Next, the adjacent vehicle detection process according to the second embodiment will be described. 15 and 16 are flowcharts showing the adjacent vehicle detection process of the second embodiment.

Step S201, in S202, similarly to steps S101, S102 of the first embodiment, acquisition of the data of the captured image is performed (step S201), on the basis of the data of the acquired captured image data of the bird's-eye view image PB _t Is generated (step S202).

  Next, in step S203, the detection control unit 34a detects an area having a luminance value equal to or greater than the predetermined threshold value sb among the detection areas A1 and A2 as a specific luminance area. In the second embodiment, as shown in FIG. 14, as the rear distance from the host vehicle V1 (camera 10) to the specific luminance area is larger, the luminance threshold sb for detecting the specific luminance area is set lower. The detection control unit 34a detects an area that is equal to or higher than the brightness threshold sb set in this way as a specific brightness area.

  In step S204, the detection control unit 34a determines whether or not the specific luminance area is detected in step S203. When the specific luminance area is detected, the process proceeds to step S205, and the detection control unit 34a sets the specific luminance area detected in step S203 as a mask area. Then, the process proceeds to step S206. On the other hand, if the specific luminance area is not detected, the process proceeds to step S206 without performing the process of step S205.

  In step S206, the storage control unit 34a refers to the storage unit 35 and reads information on the specific luminance area detected in the previous process. In step S207, based on the information on the specific luminance area read in step S206, the specific luminance area detected in step S203 is placed around the specific luminance area detected in the previous process by the detection control unit 34a. A determination is made whether or not it exists.

  For example, the detection control unit 34a has the peak value of the luminance value in the specific luminance area detected in step S203 within a predetermined pixel range from the peak position of the luminance value in the specific luminance area detected during the previous process. In this case, it can be determined that the specific luminance area detected in step S203 exists around the specific luminance area detected in the previous process. If it is determined that the specific brightness area detected in step S203 exists around the specific brightness area detected in the previous process, the process proceeds to step S208, while the specific brightness area detected in the previous process is detected. If the specific brightness area is not detected in the current process around the position of the area, the process proceeds to step S210.

  In step S208, the detection control unit 34a performs processing for detecting a region having a luminance value equal to or greater than the luminance threshold sb 'as the specific luminance region at the time of the current process around the specific luminance region detected in step S203. Here, FIG. 17 is a diagram for explaining a method of detecting a specific luminance region according to the second embodiment. For example, as shown in FIG. 17, when the detection control unit 34a detects a region having a luminance equal to or higher than the luminance threshold sb at the time of the current processing (a region indicated by a solid line in FIG. 17), the detection control unit 34a is detected at the previous processing. A region that exists around the specific luminance region and has a luminance equal to or greater than the luminance threshold sb ′ that is smaller than the luminance threshold sb is determined as an area corresponding to, for example, a smear or flare in which the sun is hit by a cloud and the luminance is decreased. Then, it is detected as the specific luminance region Rb at the time of the current processing. Thereby, the area corresponding to smear or flare at the time of the current process can be appropriately excluded from the detection target area. In step S209, the detection control unit 34a sets the specific luminance area detected in step S208 as a mask area.

  Moreover, in 2nd Embodiment, it is good also as a structure which replaces with the process of step S207-S209 and performs the process of step S211-S214. Specifically, first, in step S211, based on the information on the specific luminance area at the time of the previous process read out by step S206 by the detection control unit 34a, a predetermined predetermined area around the specific luminance area Rb ′ at the time of the previous process is set. It is determined whether or not there is a region having a luminance value peak. For example, as shown in FIG. 18, the detection control unit 34a has a higher luminance value in the vicinity of the specific luminance region Rb ′ at the time of the previous process than the surroundings (it may not be a luminance value equal to or higher than the luminance threshold sb). When there is a region having a peak where the gradient of the luminance value is equal to or greater than the predetermined gradient, it is determined that there is a region having a peak of the predetermined luminance value. As a result, the detection control unit 34a can detect a region having a luminance value equal to or higher than a predetermined luminance threshold value sb because the sun is clouded and the luminance of smear or flare is low as shown in FIG. Thus, an area corresponding to such a low-luminance smear or flare can be detected as the specific luminance area. FIG. 18 is a diagram for explaining another example of the specific luminance region detection method according to the second embodiment.

  If it is determined in step S211 that there is a region having a peak of a predetermined luminance value around the specific luminance region at the time of the previous processing, the process proceeds to step S212, while the specific luminance region at the time of the previous processing is performed. When it is determined that there is no region having a peak of a predetermined luminance value in the vicinity of, the process proceeds to step S210.

  In step S212, the detection control unit 34a performs a process of shifting the specific luminance area at the time of the previous process to the position of the area having the peak of the predetermined luminance value detected in step S211. Specifically, the detection control unit 34a matches the peak position of the brightness value in the area having the peak of the predetermined brightness value detected in step S211 with the center position of the specific brightness area at the previous processing. The specific brightness area at the time of the previous process is shifted. In step S213, the detection control unit 34a detects the area corresponding to the specific luminance area in the previous process shifted in step S212 as the specific luminance area in the current process. In step S214, the specific luminance area detected in step S213 is set as a mask area by the detection control unit 34a. As a result, as shown in FIG. 18, even when there is no region having a luminance value equal to or higher than the predetermined luminance threshold sb, the specific luminance region can be detected around the specific luminance region at the time of the previous process.

  In step S210, the position of the specific luminance area detected in the current process is stored in the storage unit 35 by the detection control unit 34a. Note that the position of the specific luminance area stored in step S210 is used as the specific luminance area in the previous process in step S206 in the next process.

Then, proceeding to FIG. 16, in step S215, the alignment unit 32 performs alignment between 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 the difference image PD Data for _t is generated. In the second embodiment, when generating the data of the difference image PD _t , the alignment unit 32 uses the data of the difference image PD _t in the detection target area excluding the mask area set in Step S205 and Step S210. Is generated. Then, the three-dimensional object detection unit 33 generates a differential waveform DW _t from the differential image PD _t corresponding to the detection target area excluding the mask area (step S216). Note that the processing after step S217 shown in FIG. 16 is the same as the processing after step S107 of the first embodiment, and thus description thereof is omitted.

  As described above, in the second embodiment, as shown in FIG. 14, the luminance threshold value sb for detecting the specific luminance region is lowered as the rear distance from the host vehicle V1 (camera 10) to the specific luminance region is larger. An area that is greater than or equal to the set brightness threshold value sb is detected as a specific brightness area. Thereby, also in the second embodiment, by converting the captured image into a bird's eye view image, the area corresponding to the smear or flare is stretched, and in the area corresponding to the stretched smear or flare, the smear or flare Even when the brightness at a position away from the center position of the area corresponding to the area becomes low, it is possible to detect the area corresponding to such low brightness smear or flare as a specific brightness area and exclude it from the detection target area. Therefore, it is possible to effectively prevent erroneous detection of an image of light due to smear or flare as an adjacent vehicle.

  In the second embodiment, in addition to the specific luminance region having a luminance value equal to or higher than the luminance threshold sb at the time of the current processing, even when the luminance value not higher than the luminance threshold sb at the time of the current processing is detected at the previous processing. An area that exists around the specified luminance area and has a predetermined luminance value peak is detected as a specific luminance area corresponding to a smear or flare having a low luminance. Thereby, for example, even when the sun is shaded by clouds and the brightness value of the area corresponding to smear or flare is less than the brightness threshold sb, the area corresponding to such smear or flare can be detected as the specific brightness area. It is possible to effectively prevent such low-brightness smear and flare light images from being erroneously detected as adjacent vehicles.

  In addition to the above configuration, in the second embodiment, it is determined whether it is nighttime or daytime, and when it is determined that it is nighttime, the brightness threshold is compared with the case where it is determined that it is daytime. It is good also as a structure which sets sb high. As a result, the detection target area is easily set at night when smear and flare are unlikely to occur, and therefore it is easy to detect adjacent vehicles at night.

  Furthermore, in 2nd Embodiment, it is good also as a structure which sets the brightness | luminance threshold value sb low, for example, when the positional information on the sun is acquired and it is judged that the sun is located in the west. This makes it easier to detect areas corresponding to smears and flares as specific brightness areas in situations where the sun is likely to generate smears and flares, thus more appropriately eliminating the effects of light due to smears and flares. be able to. The method for acquiring the position information of the sun is not particularly limited. For example, the detection control unit 34a may select an area having a luminance value greater than or equal to a predetermined value in the captured image as an area corresponding to the sun. By detecting as, it is possible to acquire the position information of the sun.

<< Third Embodiment >>
Next, the three-dimensional object detection device 1b according to the third embodiment will be described. As shown in FIG. 19, the three-dimensional object detection device 1 b according to the third embodiment includes a computer 30 b 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 30b according to the third embodiment.

  As shown in FIG. 19, the three-dimensional object detection device 1b according to the third embodiment includes a camera 10 and a computer 30b. The computer 30b includes a viewpoint conversion unit 31, a luminance difference calculation unit 36, and an edge line detection unit. 37, a three-dimensional object detection unit 33a, and a detection control unit 34b. Below, each structure of the solid-object detection apparatus 1b which concerns on 3rd Embodiment is demonstrated.

  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, L2 of the adjacent vehicle V2 is determined 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.

  Returning to FIG. 19, the viewpoint conversion unit 31 inputs captured image data of a predetermined area obtained by imaging with the camera 10. The viewpoint conversion unit 31 performs viewpoint conversion processing on the input captured image data to the bird's-eye image data in a bird's-eye view state. The bird's-eye view is a state seen from the viewpoint of a virtual camera looking down from above, for example, vertically downward (or slightly obliquely downward). This viewpoint conversion process can be realized by a technique described in, for example, Japanese Patent Application Laid-Open No. 2008-219063.

  The luminance difference calculation unit 36 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. For each of a plurality of positions along a vertical imaginary line extending in the vertical direction in the real space, the brightness difference calculation unit 36 calculates a brightness difference between two pixels in the vicinity of each position. The luminance difference calculation unit 36 can calculate the luminance difference by either a method of setting only one vertical virtual line extending in the vertical direction in the real space or a method of setting two vertical virtual lines.

  Here, a specific method for setting two vertical virtual lines will be described. The brightness difference calculating unit 36 applies a first vertical imaginary line corresponding to a line segment extending in the vertical direction in the real space and a vertical direction in the real space different from the first vertical imaginary line with respect to the bird's eye view image that has undergone viewpoint conversion. A second vertical imaginary line corresponding to the extending line segment is set. The luminance difference calculation unit 36 continuously obtains the luminance difference between the point on the first vertical imaginary line and the point on the second vertical imaginary line along the first vertical imaginary line and the second vertical imaginary line. Hereinafter, the operation of the luminance difference calculation unit 36 will be described in detail.

  As shown in FIG. 21A, the luminance difference calculation unit 36 corresponds to a line segment extending in the vertical direction in real space and passes through the detection area A1 (hereinafter, attention line La). Set). In addition, unlike the attention line La, the luminance difference calculation unit 36 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 36 sets a point of interest Pa (a point on the first vertical imaginary line) on the line of interest La. In addition, the luminance difference calculation unit 36 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 36 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 third 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 37 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 36, 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 36 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 1b according to the present embodiment, the reference line Lr is set at a position 10 cm away from the attention line La in real space. Thereby, the reference line Lr is set on the wheel of the tire of the 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 36 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 36 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 36 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 36 calculates the brightness | luminance difference of two pixels for every some position (1-N) along the vertical imaginary line extended in the perpendicular direction in real space. The luminance difference calculation unit 36 calculates, for example, a luminance difference between the first attention point Pa1 and the first reference point Pr1, and a luminance difference between the second attention point Pa2 and the second reference point Pr2. Will be calculated. Thereby, the luminance difference calculation unit 36 continuously obtains the luminance difference along the attention line La and the reference line Lr. That is, the luminance difference calculation unit 36 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 36 repeatedly executes the processing such as setting the reference line Lr, setting the attention point Pa and the reference point Pr, and calculating the luminance difference while shifting the attention line La in the detection area A1. That is, the luminance difference calculation unit 36 repeatedly executes the above processing while changing the positions 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 36 sets a 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 third 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 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 37 detects an edge line from the continuous luminance difference calculated by the luminance difference calculation unit 36. 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 37 can 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, when detecting the edge line, the edge line detection unit 37 firstly follows the following Equation 1 to determine the i-th attention point Pai (coordinate (xi, yi)) and the i-th reference point Pri (coordinate ( xi ′, yi ′)) and the i th attention point Pai are attributed.
[Equation 1]
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 a predetermined 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. Indicates. According to Equation 1, when the luminance value of the attention point Pai is higher than the luminance value obtained by adding the threshold value t to the reference point Pri, the attribute s (xi, yi) of the attention point Pai is “1”. Become. On the other hand, when the luminance value of the attention point Pai is lower than the luminance value obtained by subtracting the luminance 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”.

Next, the edge line detection unit 37 determines whether or not the attention line La is an edge line from the continuity c (xi, yi) of the attribute s along the attention line La based on Equation 2 below.
[Equation 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 37 calculates | requires the sum total about the continuity c of all the attention points Pa on attention line La. The edge line detection unit 37 normalizes the continuity c by dividing the obtained sum of continuity c by the number N of points of interest Pa. Then, the edge line detection unit 37 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 37 determines whether or not the attention line La is an edge line based on Equation 3 below. Then, the edge line detection unit 37 determines whether or not all the attention lines La drawn on the detection area A1 are edge lines.
[Equation 3]
Σc (xi, yi) / N> θ

  As described above, in the third 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 example of an image for explaining the processing of the edge line detection unit 37. 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, the edge line detection unit 37 determines the part 103 as an edge line only when the luminance difference attribute has continuity in addition to the luminance difference in the part 103. 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 sense can be performed.

  Returning to FIG. 19, the three-dimensional object detection unit 33 a detects a three-dimensional object based on the amount of edge lines detected by the edge line detection unit 37. As described above, the three-dimensional object detection device 1b 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 33a detects a three-dimensional object based on the amount of edge lines detected by the edge line detection unit 37. Specifically, the three-dimensional object detection unit 33a determines whether the amount of edge lines detected by the edge line detection unit 37 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 case described above, the edge line detected by the edge line detection unit 37 is determined to be an edge line of a three-dimensional object, thereby detecting the three-dimensional object based on the edge line as the adjacent vehicle V2.

  Further, prior to detecting the three-dimensional object, the three-dimensional object detection unit 33a determines whether or not the edge line detected by the edge line detection unit 37 is correct. The three-dimensional object detection unit 33a 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 V2 is extended in the bird's-eye view image by converting the image captured by the camera 10 into a bird's-eye view image. 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 33a determines whether or not the edge line is detected by erroneous determination. 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 33a has detected the edge line by erroneous determination, and the edge line is caused by the three-dimensional object. Judge that it is not. 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 33a 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 33a calculates the luminance change of the edge line according to any one of the following mathematical formulas 4 and 5. The luminance change of the edge line corresponds to the evaluation value in the vertical direction in the real space. Equation 4 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). . Also, the following Equation 5 represents the luminance distribution according to the sum of 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 evaluate.
[Equation 4]
Evaluation value in the vertical equivalent direction = Σ [{I (xi, yi) −I (xi + 1, yi + 1)} ² ]
[Equation 5]
Evaluation value in the vertical equivalent direction = Σ | I (xi, yi) −I (xi + 1, yi + 1) |

In addition, not only Formula 5 but also Formula 6 below, the threshold value t2 is used to binarize the attribute b of the adjacent luminance value, and the binarized attribute b is summed for all the attention points Pa. Also good.
[Equation 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 33a 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.

  As in the first embodiment, the detected object control unit 35b detects, as the specific luminance area, an area having a luminance value equal to or higher than a predetermined value from the detection areas A1 and A2, as shown in FIG. The larger the backward distance, the wider the mask area including the detected specific luminance area. Then, the detection control unit 35b controls the luminance difference calculation unit 36 so as to detect an edge line in the detection target region excluding the mask region from the detection regions A1 and A2.

  Next, an adjacent vehicle detection method according to the third embodiment will be described. FIG. 25 is a flowchart showing details of the adjacent vehicle detection method according to the present 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.

  First, in step S301, the camera 10 captures a predetermined area specified by the angle of view a and the attachment position, and the computer 30b acquires image data of a captured image 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.

  In steps S303 and S304, as in steps S103 and 104 of the first embodiment, an area having a luminance value equal to or greater than the predetermined threshold value sb in the detection area A1 is detected as a specific luminance area, and a mask including the detected specific luminance area. The area is set. Also in the third embodiment, the detection control unit 34b sets the mask region in a wider range as the rear distance from the host vehicle V1 (camera 10) to the specific luminance region is larger.

  Next, in step S305, the luminance difference calculator 36 sets the attention line La and the reference line Lr on the detection area A1. At this time, the luminance difference calculation unit 36 sets a line corresponding to a line extending in the vertical direction in the real space as the attention line La, corresponds to a line segment extending in the vertical direction in the real space, and the attention line A line separated from La by a predetermined distance in the real space is set as the reference line Lr.

  Next, in step S306, the luminance difference calculation unit 36 sets a plurality of attention points Pa on the attention line La, and the attention point Pa and the reference point Pr have substantially the same height in the real space. A reference point Pr is set. 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. Note that the luminance difference calculation unit 36 sets a number of attention points Pa that do not cause a problem when an edge is detected by the edge line detection unit 37.

  Next, in step S307, the luminance difference calculation unit 36 calculates the luminance difference between the attention point Pa and the reference point Pr that have the same height in the real space. In the third embodiment, the luminance difference calculation unit 36 calculates the luminance difference in the detection target area excluding the mask area set in step S304 from the detection area A1. Then, the edge line detection unit 37 calculates the attribute s of each attention point Pa in accordance with Equation 1 above. Next, in step S308, the edge line detection unit 37 calculates the continuity c of the attribute s of each attention point Pa according to the above mathematical formula 2. In step S309, the edge line detection unit 37 determines whether the value obtained by normalizing the total sum of continuity c is greater than the threshold value θ according to the above formula 3. When it is determined that the normalized value is larger than the threshold θ (step S309 = Yes), the edge line detection unit 37 detects the attention line La as an edge line in step S310. Then, the process proceeds to step S311. If it is determined that the normalized value is not greater than the threshold θ (step S309 = No), the edge line detection unit 37 does not detect the attention line La as an edge line, and the process proceeds to step S311.

  In step S311, the computer 30b determines whether or not the processing in steps S305 to S311 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 S305, 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 33a calculates a luminance change along the edge line for each edge line detected in step S310. The three-dimensional object detection unit 33a 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 33a 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 33a 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 existing in the adjacent vehicle. .

  In step S314, the three-dimensional object detection unit 33a determines whether the amount of edge lines is equal to or greater than a predetermined threshold value β. 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 33a determines in step S315 that there is an adjacent vehicle in the detection area A1. On the other hand, when it is determined that the amount of the edge line is not equal to or larger than the threshold value β (step S314 = No), the three-dimensional object detection unit 33a determines in step S316 that there is no adjacent vehicle in the detection area A1. Then, the process shown in FIG. 25 is complete | finished.

  As described above, in the third embodiment, a captured image is converted into a bird's-eye view image, and edge information of a three-dimensional object is detected from the converted bird's-eye view image, thereby detecting an adjacent vehicle existing in the adjacent lane. And when detecting the edge information of a three-dimensional object from a bird's-eye view image, an area having a luminance equal to or higher than a predetermined value is detected as a specific luminance area in the detection areas A1 and A2, and as the rear distance from the camera 10 increases, The mask area including the specific luminance area is set to a wide range, and edge information is extracted in the detection target area excluding the mask area from the detection areas A1 and A2. As a result, in the third embodiment, even when a three-dimensional object is detected based on edge information, a region corresponding to smear or flare is expanded by converting the captured image into a bird's-eye view image, so that smear or flare is supported. Even if the brightness of the area far from the center position of the area corresponding to smear or flare is low, the effect of light due to such low brightness smear or flare can be eliminated. It is possible to effectively prevent a light image from being erroneously detected as an adjacent vehicle.

  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 region having the luminance equal to or higher than the predetermined luminance threshold sb is detected as the specific luminance region corresponding to the smear or flare, but is not limited to this configuration. In the case of a general CCD (Charge-Coupled Device) camera, smear is generated only from the light source in the lower direction of the image. It is also possible to search for a continuous region and detect this as a specific luminance region corresponding to smear.

In the first embodiment and the second embodiment described above, the three-dimensional object is detected in the detection target area excluding the mask area by generating the data of the difference image PD _t in the detection target area excluding the mask area. Although the configuration to be performed is illustrated, the configuration is not limited to this configuration. For example, the data of the difference image PD _t is generated in the entire detection areas A1 and A2, and the data corresponding to the detection target area is included in the data of the difference image PD _t. by generating a differential waveform DW _t, it may be configured to detect the three-dimensional object in the detection target area excluding the mask region. Alternatively, to generate a difference waveform DW _t in the detection areas A1, A2 entire region by determining whether a threshold value or more α in the corresponding portion to the detection target region of the differential waveform DW _t, excluding the mask region Alternatively, a configuration may be used in which a three-dimensional object is detected in the detection target region. In the third embodiment described above, the luminance difference calculation unit 36 calculates the luminance difference in the detection target area excluding the mask area, thereby detecting the three-dimensional object in the detection target area excluding the mask area. However, the present invention is not limited to this configuration. For example, in the detection target area excluding the mask area, the edge line is detected by the edge line detection unit 37, so that the three-dimensional object is detected in the detection target area excluding the mask area. It is good also as a structure which detects this.

Furthermore, instead of the embodiment described above, detection control by the detection control unit 34 may be performed with the following configuration. For example, in the first embodiment, as the rear distance to the vehicle V1 (camera 10) is large, so it is difficult to detect the difference data of the difference image DP _t, changes the threshold value th for detecting difference data structure It is good. Here, FIG. 26A is a graph showing an example of the threshold value th in the front mask region Rm ₁ shown in FIG. 11, and FIG. 26B shows the threshold value in the rear mask region Rm ₂ shown in FIG. It is a graph which shows an example of th.

For example, as shown in FIG. 26A, for the front mask region Rm ₁ , a threshold pattern that sets the threshold th to th ₁ when the overall luminance value of the bird's-eye view image is br ₁ is used. In contrast, as shown in FIG. 26B, for the rear mask region Rm ₂ , when the overall luminance value of the bird's-eye view image is br ₁ , the threshold value th is less than th _1. applying a threshold pattern for setting a higher th _2. Thus, in the rear mask region Rm ₂ , the difference between the difference images DP _t is such that it is difficult to detect the adjacent vehicle even in a region where the brightness of the bird's eye view image is relatively low compared to the front mask region Rm _1. By setting the threshold value th for detecting data high, in the rear mask region Rm ₂ , an area having a relatively low brightness compared to the front mask region Rm ₁ is excluded from the vehicle detection target. Therefore, when the captured image is converted to a bird's-eye view image, the area corresponding to smear or flare is stretched, and even if the brightness at a position far from the center position of the smear or flare becomes low, such low smear And the influence of light due to flare can be eliminated, and it is possible to effectively prevent erroneous detection of a light image due to smear or flare with low brightness as an adjacent vehicle. Note that, as shown in FIGS. 26A and 26B, the threshold value th has a high luminance value in the detection areas A1 and A2 in addition to the rear distance from the host vehicle V1 (camera 10) to the specific luminance area. The region can be set to a higher value.

Further, in addition to the configuration in which the threshold th for detecting difference data is changed so that the difference data of the difference image DP _t is difficult to detect as the rear distance to the own vehicle V1 (camera 10) increases, the own vehicle V1. A configuration may be adopted in which the threshold value α for determining the adjacent vehicle is changed so that the adjacent vehicle is difficult to detect as the rear distance to (camera 10) increases. Similarly, in the third embodiment, the threshold value t and the threshold value θ for detecting the edge line are changed so that the edge line is difficult to detect as the rear distance to the host vehicle V1 (camera 10) increases. In addition, as the rear distance to the host vehicle V1 (camera 10) is larger, the edge line equal to or greater than the threshold tb for excluding the edge line is changed according to the luminance change so that the edge line is difficult to detect. Also good. In addition, in 3rd Embodiment, it is good also as a structure which changes the threshold value (beta) for determining an adjacent vehicle so that it is hard to detect an adjacent vehicle, so that the back distance to the own vehicle V1 (camera 10) is large.

  Furthermore, in 1st Embodiment and 2nd Embodiment which were mentioned above, although the vehicle speed of the own vehicle V1 is judged based on the signal from the speed sensor 20, it is not restricted to this, A speed is calculated from the several image at different time. It is good also as a structure to estimate. In this case, the vehicle speed sensor 20 is not necessary, and the configuration can be simplified.

  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 includes a positioning unit 32, a three-dimensional object detection unit 33, a detection control unit 34, The luminance difference calculation unit 36 and the edge line detection unit 37 correspond to the three-dimensional object detection unit of the present invention, and the detection control unit 34 corresponds to the luminance detection unit, day / night determination unit, and sun position acquisition unit of the present invention, and stores them. The unit 35 corresponds to the storage means of the present invention.

DESCRIPTION OF SYMBOLS 1, 1a, 1b ... Three-dimensional object detection apparatus 10 ... Camera 20 ... Vehicle speed sensor 30, 30a, 30b ... Computer 31 ... Viewpoint conversion part 32 ... Position alignment part 33, 33a ... Three-dimensional object detection part 34, 34a, 34b, ... Detection Control unit 35 ... storage unit 36 ... luminance difference calculation unit 37 ... edge line detection unit a ... angle of view A1, A2 ... detection region CP ... intersection point DP ... difference pixel DW _t , DW _t '... difference waveform DW _{t1 to} DW _m , DW _{m + k to} DW _tn ... small areas L1, L2 ... ground lines La and Lb ... line PB _{t in the} direction in which the three-dimensional object collapses ... bird's eye view image PD _t ... difference image V1 ... own vehicle V2 ... adjacent vehicle

Claims (7)

Imaging means for imaging the rear of the vehicle;
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. Three-dimensional object detection means for generating difference waveform information by frequency distribution and detecting a three-dimensional object in a detection region set at the rear of the vehicle based on the difference waveform information;
Brightness detection means for detecting the brightness of the pixels in the detection area,
The three-dimensional object detection means detects, as a high-brightness area, an area having a luminance equal to or higher than a predetermined threshold among the detection areas, and selects at least a predetermined range of the detection area that covers the high-luminance area as the three-dimensional object. Is set as a detection control region that is difficult to detect, and the detection control region is set wider as the rear distance from the imaging unit is larger, and the difference waveform information is generated in the detection region where the detection control region is set. A three-dimensional object detection device. Imaging means for imaging the rear of the vehicle;
Image conversion means for converting the captured image obtained by the imaging means into a bird's eye view image;
Three-dimensional object detection means for detecting edge information from the bird's-eye view image obtained by the image conversion means, and detecting a three-dimensional object existing in a predetermined detection area based on the edge information;
Brightness detection means for detecting the brightness of the pixels in the detection area,
The three-dimensional object detection means detects, as a high-brightness area, an area having a luminance equal to or higher than a predetermined threshold among the detection areas, and selects at least a predetermined range of the detection area that covers the high-luminance area as the three-dimensional object. Is set as a detection control region that is difficult to detect, and the detection control region is set wider as the rear distance from the imaging unit is larger, and the edge information is detected in the detection region where the detection control region is set. A three-dimensional object detection device. The three-dimensional object detection device according to claim 1 or 2,
The three-dimensional object detection device detects the three-dimensional object only in a detection target area excluding the detection control area in the detection area. The three-dimensional object detection device according to any one of claims 1 to 3,
The three-dimensional object detection device, wherein the three-dimensional object detection unit sets the predetermined threshold value for detecting the high-luminance region to be lower as the rear distance from the imaging unit is larger. The three-dimensional object detection device according to any one of claims 1 to 4,
It further comprises day / night determination means for determining whether it is daytime or nighttime,
The three-dimensional object detection device according to claim 1, wherein the three-dimensional object detection unit sets the predetermined threshold value for detecting the high luminance region higher at night than at daytime. The three-dimensional object detection device according to any one of claims 1 to 5,
Solar position acquisition means for acquiring solar position information;
The three-dimensional object detection means sets the predetermined threshold value for detecting the high-intensity region low when it is determined that the position of the sun exists in the west based on the position information of the sun. 3D object detection device. The three-dimensional object detection device according to any one of claims 1 to 6,
Storage means for storing the position of the high-luminance region in the detection region;
The three-dimensional object detection means, based on the position of the high luminance area detected at the time of the previous processing, when the high luminance area cannot be detected at the position of the high luminance area detected at the time of the previous processing. The three-dimensional object detection apparatus, wherein the detection control area is set.

Images