JP6591188B2 - Outside environment recognition device - Google Patents

Description

  The present invention relates to an outside environment recognition device that recognizes an environment outside the host vehicle, and more particularly to an outside environment recognition device that identifies a region to be controlled by the host vehicle.

  Conventionally, a specific object such as a vehicle positioned in front of the host vehicle is detected, and a collision with a preceding vehicle is avoided (collision avoidance control), or the distance between the preceding vehicle and the preceding vehicle is controlled to be a safe distance ( (Cruise Control) technology is known. And in order to identify a preceding vehicle, the technique using the vehicle-mounted stereo camera is known. Specifically, parallax information (corresponding to a relative distance between the host vehicle and the three-dimensional object) is derived for each block from two image data obtained by capturing the front of the host vehicle, and a distance image in which the parallax information is associated with the image data is obtained. Generate. A technique for dividing a distance image into a plurality of divided areas in the horizontal direction, generating a histogram (frequency distribution) of relative distances in the divided areas for each divided area, and identifying a preceding vehicle based on the histogram Is known (for example, Patent Document 1).

JP-A-10-283461

  In the technique of Patent Document 1 described above, first, when blocks that are close to each other are grouped, and when groups that are not so far apart are integrated, it is determined whether or not it is appropriate as a vehicle. If appropriate, the groups are integrated and specified as a preceding vehicle. Therefore, even when the vehicle is not integrally recognized and a plurality of parts are individually recognized, they can be integrated and appropriately controlled as a preceding vehicle.

  However, if two stereoscopic images corresponding to separate three-dimensional objects that are not far apart from each other are located side by side in the width direction of the image and the three-dimensional images are temporarily integrated, that is appropriate as a vehicle. If so, they are integrated and recognized as a preceding vehicle. If so, there is a risk that comfortable running may be hindered by collision avoidance control or cruise control.

  In view of such a problem, an object of the present invention is to provide an external environment recognition device that can appropriately specify a region to be controlled.

In order to solve the above problems, the environment outside the vehicle recognition system of the present invention, among the image captured by the imaging device, and converted multiple, three-dimensional position information represented blocks in sequence of a given pixel When the distance between the plurality of blocks is within the first distance range, the first grouping unit that groups the plurality of blocks to generate the first group, and the plurality of grouped by the first grouping unit When the first group is converted into the three-dimensional position information, the distance between the plurality of first groups is within a second distance range that is larger than the first distance range, and the plurality of first groups are arranged in the left and right directions in the width direction. when in the positional relationship is between the width direction between the plurality of first group, the image on the, in the region where the position of the plurality of first groups and the height direction overlaps, in front of the vehicle relative distance predetermined threshold Bro you are away or more Satisfies the integration condition click is less than the predetermined number, generating a second group by integrating a plurality of first group together, the distance between the plurality of first group in the second distance range, and a plurality even if the first group each other are in the positional relationship in the width direction right includes to be met integration condition, a second grouping unit that does not integrate the plurality of first group together, a.

The second grouping unit further generates a second group by integrating the plurality of first groups only when the size when the plurality of first groups are integrated is a reasonable size as a vehicle. May be.

  According to the present invention, it is possible to appropriately specify a region to be controlled.

It is the block diagram which showed the connection relation of the environment recognition system. It is the functional block diagram which showed the schematic function of the external environment recognition apparatus. It is a flowchart which shows the flow of a vehicle exterior environment recognition process. It is explanatory drawing for demonstrating a luminance image and a distance image. It is explanatory drawing for demonstrating the process of a histogram production | generation part. It is explanatory drawing for demonstrating the process of a 1st grouping part. It is explanatory drawing for demonstrating the process of a 2nd grouping part. It is explanatory drawing for demonstrating the process of a 2nd grouping part. It is explanatory drawing for demonstrating the process of a 2nd grouping part.

  Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The dimensions, materials, and other specific numerical values shown in the embodiment are merely examples for facilitating understanding of the invention, and do not limit the present invention unless otherwise specified. In the present specification and drawings, elements having substantially the same function and configuration are denoted by the same reference numerals, and redundant description is omitted, and elements not directly related to the present invention are not illustrated. To do.

  In recent years, an in-vehicle camera mounted on a vehicle images a road environment ahead of the host vehicle, identifies a specific object such as a preceding vehicle based on color information and position information in the image, and Vehicles equipped with a so-called anti-collision function that avoids collisions and keeps the distance between the vehicle and the preceding vehicle at a safe distance (ACC: Adaptive Cruise Control) are becoming widespread.

  In a vehicle equipped with such an external environment recognition device that recognizes such an external environment, for example, a three-dimensional image on an image corresponding to a three-dimensional object located in front of the host vehicle is a specific object such as a vehicle (preceding vehicle). It is determined whether or not. If the stereoscopic image is a preceding vehicle, the preceding vehicle is set as a control target, and a collision is avoided or the inter-vehicle distance is controlled. In the present embodiment, an outside environment recognition device capable of appropriately specifying a specific object such as a preceding vehicle is provided.

(Environment recognition system 100)
FIG. 1 is a block diagram showing a connection relationship of the environment recognition system 100. The environment recognition system 100 includes an imaging device 110, a vehicle exterior environment recognition device 120, and a vehicle control device (ECU: Engine Control Unit) 130 provided in the host vehicle 1.

  The imaging device 110 includes an imaging element such as a CCD (Charge-Coupled Device) or a CMOS (Complementary Metal-Oxide Semiconductor), captures an environment corresponding to the front of the host vehicle 1, and displays a color image or a monochrome image. Can be generated. Here, the color value is a numerical group consisting of one luminance (Y) and two color differences (UV), or three hues (R (red), G (green), B (blue)). . Here, a color image or a monochrome image captured by the imaging device 110 is referred to as a luminance image, and is distinguished from a distance image described later.

  In addition, the imaging devices 110 are arranged in a substantially horizontal direction so that the optical axes of the two imaging devices 110 are substantially parallel on the traveling direction side of the host vehicle 1. The imaging device 110 continuously generates image data obtained by imaging a specific object existing in the detection area in front of the host vehicle 1, for example, every 1/60 second frame (60 fps). Here, specific objects to be recognized exist independently such as vehicles, people (pedestrians), traffic lights, guardrails, as well as taillights, blinkers, traffic lights, etc. Includes some of the things to do. Each functional unit in the following embodiment performs each process for each frame in response to such update of the image data.

  The vehicle exterior environment recognition device 120 acquires image data from each of the two imaging devices 110, derives parallax using so-called pattern matching, and associates the derived parallax information (corresponding to a relative distance described later) with the image data. Generate a distance image. The luminance image and the distance image will be described in detail later. Further, the vehicle environment recognition apparatus 120 uses a luminance (color value) based on the luminance image and a stereoscopic image displayed in the detection area in front of the host vehicle 1 using the relative distance from the host vehicle 1 based on the distance image. Specify whether it corresponds to a specific thing.

  When the stereoscopic image is specified as a specific object, for example, a preceding vehicle, the vehicle exterior environment recognition device 120 tracks the preceding vehicle and derives the relative speed of the preceding vehicle, and the preceding vehicle and the host vehicle 1 collide. It is determined whether or not there is a high possibility of being. Here, when it is determined that the possibility of a collision is high, the vehicle environment recognition device 120 displays a warning (notification) to the driver through the display 122 installed in front of the driver, and the vehicle control device. Information indicating that is output to 130.

  The vehicle control device 130 receives a driver's operation input through the steering wheel 132, the accelerator pedal 134, and the brake pedal 136, and controls the host vehicle 1 by transmitting it to the steering mechanism 142, the drive mechanism 144, and the brake mechanism 146. Further, the vehicle control device 130 controls the steering mechanism 142, the drive mechanism 144, and the braking mechanism 146 in accordance with instructions from the outside environment recognition device 120.

  Hereinafter, the configuration of the outside environment recognition device 120 will be described in detail. Here, a specific procedure for identifying a specific object such as a preceding vehicle located in front of the host vehicle 1 that is characteristic of the present embodiment will be described in detail, and description of a configuration unrelated to the characteristics of the present embodiment will be omitted.

(Vehicle environment recognition device 120)
FIG. 2 is a functional block diagram showing a schematic function of the outside environment recognition device 120. As shown in FIG. 2, the vehicle exterior environment recognition device 120 includes an I / F unit 150, a data holding unit 152, and a central control unit 154.

  The I / F unit 150 is an interface for performing bidirectional information exchange with the imaging device 110 and the vehicle control device 130. The data holding unit 152 includes a RAM, a flash memory, an HDD, and the like. The data holding unit 152 holds various pieces of information necessary for the processing of each function unit described below, and temporarily holds image data received from the imaging device 110. To do.

  The central control unit 154 is configured by a semiconductor integrated circuit including a central processing unit (CPU), a ROM storing a program, a RAM as a work area, and the like, and through the system bus 156, an I / F unit 150, a data holding unit 152 and the like are controlled. In the present embodiment, the central control unit 154 includes the image processing unit 160, the three-dimensional position information generation unit 162, the histogram generation unit 164, the first grouping unit 166, the second grouping unit 168, and the specific object specifying unit 170. Also functions as the vehicle control unit 172.

(External vehicle environment recognition processing)
FIG. 3 is a flowchart showing the flow of the external environment recognition process. In the environment recognition process outside the vehicle, the image processing unit 160 processes the image acquired from the imaging device 110 (S200), the histogram generation unit 164 generates a histogram (S202), and the first grouping unit 166 performs the three-dimensional operation. The first group grouped based on the position is generated (S204), and the second grouping unit 168 further integrates the first groups according to the appearance of the first group to generate the second group. Then, the specified object specifying unit 170 specifies the specified object (S208), and the vehicle control unit 172 controls the host vehicle 1 (S210). Hereinafter, each process is explained in full detail.

(Image processing S200)
The image processing unit 160 acquires image data from each of the two imaging devices 110, and selects a block corresponding to a block arbitrarily extracted from one image data (for example, an array of 4 horizontal pixels × 4 vertical pixels) as the other image. The parallax is derived using so-called pattern matching, which is retrieved from the data. Here, “horizontal” indicates the horizontal direction of the captured luminance image, and “vertical” indicates the vertical direction of the captured luminance image.

  As this pattern matching, it is conceivable to compare the luminance (Y color difference signal) in units of blocks indicating an arbitrary image position between two pieces of image data. For example, SAD (Sum of Absolute Difference) that takes the difference in luminance, SSD (Sum of Squared Intensity Difference) that uses the difference squared, or NCC that takes the similarity of the variance value obtained by subtracting the average value from the luminance of each pixel There are methods such as (Normalized Cross Correlation). The image processing unit 160 performs such a block-unit parallax derivation process for all blocks displayed in the detection area (for example, horizontal 600 pixels × vertical 180 pixels). Here, the block is assumed to be horizontal 4 pixels × vertical 4 pixels, but the number of pixels in the block can be arbitrarily set.

  However, the image processing unit 160 can derive the parallax for each block, which is a unit of detection resolution, but cannot recognize what part of the stereoscopic image the block is. Accordingly, the parallax information is derived independently in units of blocks in the detection area, not in units of stereoscopic images. An image in which disparity information derived in this way (corresponding to a relative distance described later) is associated with each block of image data is referred to as a distance image.

  FIG. 4 is an explanatory diagram for explaining the luminance image 210 and the distance image 212. For example, it is assumed that a luminance image (image data) 210 as illustrated in FIG. 4A is generated for the detection region 214 through the two imaging devices 110. However, only one of the two luminance images 210 is schematically shown here for easy understanding. In the present embodiment, the image processing unit 160 obtains the parallax for each block from the luminance image 210 and forms a distance image 212 as shown in FIG. Each block in the distance image 212 is associated with the parallax of the block. Here, for convenience of description, blocks from which parallax is derived are represented by black dots.

  Returning to FIG. 2, the three-dimensional position information generation unit 162 uses the so-called stereo method to calculate disparity information for each block in the detection region 214 based on the distance image 212 generated by the image processing unit 160. Convert into 3D position information including horizontal distance, height and relative distance. Here, the stereo method is a method of deriving a relative distance of the block with respect to the imaging device 110 from the parallax of the block by using a triangulation method. At this time, the three-dimensional position information generation unit 162 determines from the road surface of the block based on the relative distance of the block and the distance on the distance image 212 from the point on the road surface at the same relative distance to the block to the block. The height of is derived. Regarding the conversion to the three-dimensional position information, since existing techniques such as JP2013-109391A can be referred to, detailed description thereof is omitted here.

(Histogram generation process S202)
Subsequently, the histogram generation unit 164 divides the distance image 212 into a plurality of divided regions, and for each divided region, the relative distances of the plurality of blocks in the divided region are divided into a plurality of classes (relative distances divided by equal distances). A histogram (frequency distribution) is generated in which the categories are sorted in the shortest order). Hereinafter, specific processing of the histogram generation unit 164 will be described.

  FIG. 5 is an explanatory diagram for explaining the processing of the histogram generation unit 164. The histogram generation unit 164 first divides the distance image 212 into a plurality of divided regions 216 in the horizontal direction. Then, the divided region 216 has a strip shape extending in the vertical direction as shown in FIG. Such a strip-shaped divided region 216 is originally composed of, for example, 150 columns each having a horizontal width of 4 pixels, but here, for convenience of explanation, the detection region 214 is divided into 16 parts.

  Subsequently, for each divided region 216, the histogram generation unit 164 has a plurality of relative distances for all blocks that are considered to be located above the road surface in the divided region 216 based on the three-dimensional position information. It is determined which class is included, and the relative distances are assigned to the corresponding classes to generate a histogram (indicated by a horizontally long square (bar) in FIG. 5B). Then, as shown in FIG. 5B, a distance distribution 218 based on a histogram for each divided region 216 is obtained. Here, the vertical direction indicates a class obtained by dividing the relative distance into equal distances, and the horizontal direction indicates the number of blocks (frequency) allocated to the class. However, FIG. 5B is a virtual screen for calculation, and actually does not involve generation of a visual screen.

(First grouping process S204)
FIG. 6 is an explanatory diagram for explaining the processing of the first grouping unit 166. The first grouping unit 166 first refers to the distance distribution 218 for each divided region 216, and if there are consecutive classes having effective frequencies in the same divided region 216, the first grouping unit 166 groups the consecutive classes. As shown in FIG. 6A, a divided stereoscopic image candidate 220 that is a candidate for a three-dimensional object is generated for each divided region 216. Then, the first grouping unit 166 sets the largest frequency (indicated by a black square in FIG. 6) in the divided stereoscopic image candidate 220 as the representative distance 222.

  Subsequently, the first grouping unit 166 compares the adjacent divided regions 216 with each other, groups the divided regions 216 whose representative distances 222 are close to each other (for example, located at 1 m or less), and FIG. As shown in FIG. 5, a divided region group 240 is generated. At this time, even when the representative distance 222 is close in three or more divided areas 216, all the continuous divided areas 216 are collected as a divided area group 240. By such grouping, it is possible to specify the size of the stereoscopic image located above the road surface in the horizontal width direction.

  Subsequently, the first grouping unit 166 uses the block whose relative distance z corresponds to the representative distance 222 in the divided region group 240 as a base point, the difference between the block, the horizontal distance x, the height y difference, and the relative Blocks having a difference in distance z within a predetermined first distance range (for example, 0.1 m) are grouped on the assumption that they correspond to the same specific object. Thus, the first group 242 that is a virtual block group is generated. The above range is represented by a distance in real space, and can be set to an arbitrary value by a manufacturer or a passenger. In addition, the first grouping unit 166 also uses the block as a base point for the newly added block, and the difference in the horizontal distance x, the difference in the height y, and the difference in the relative distance z are the first distance range. The blocks inside are further grouped. As a result, all the blocks that can be assumed to be the same specific object are grouped.

Also, here, the horizontal distance x difference, the height y difference, and the relative distance z difference are determined independently, and only when they are all included in the first distance range, they are in the same group. It can also be calculated. For example, the root mean square of the difference in horizontal distance x, the difference in height y, and the difference in relative distance z ((difference in horizontal distance x) ² + (difference in height y) ² + (difference in relative distance z) ² ) Are included in the first distance range, the same group may be used. With this calculation, an accurate distance between blocks in real space can be derived, so that the grouping accuracy can be improved. The first group 242 generated by such grouping and the second group to be described later include all the grouped blocks, and are treated as a rectangular stereoscopic image whose outline is composed of a horizontal line and a vertical line.

(Second grouping process S206)
7 to 9 are explanatory diagrams for explaining the processing of the second grouping unit 168. FIG. As shown in FIG. 7A, when a preceding vehicle appears in the distance image 212, a block whose distance is not clear by pattern matching may occur depending on the luminance of the image data. Originally, the first grouping unit 166 should group all the preceding vehicle regions 250 having a substantially equal relative distance z, but actually, in all blocks of the preceding vehicle, as shown in FIG. In some cases, the relative distance z cannot be obtained, and a plurality of parts individually form the first group 242.

  Therefore, the second grouping unit 168 determines an integration condition (distance condition, vehicle property), which will be described later, according to the appearance mode of the first group 242 grouped by the first grouping unit 166 (the positional relationship between the first groups 242). The first group 242 is further integrated with each other in accordance with the condition and the continuity condition) to generate the second group.

(Distance condition)
First, as shown in FIG. 7, the second grouping unit 168 has a distance between the first groups 242 (end points of the first group 242) within a second distance range (for example, 1 m) that is larger than the first distance range. For example, the first groups 242 are temporarily integrated to form the second group 254 as shown in FIG.

(Vehicle condition)
Next, the second grouping unit 168 determines that the size of the second group 254 obtained by temporarily integrating the first groups 242 according to the distance condition is an appropriate size as a vehicle, for example, 1.5 m to 2. If it is included in the range of 5 m and 0.5 m to 3.8 m in the vertical direction, the second group 254 is newly made a stereoscopic image as a candidate for a specific object, and 1.5 m to 2.5 m in the horizontal direction. If it is not included in the range of 0.5 m to 3.8 m in the vertical direction, the first group 242 indicates a separate stereoscopic image, and the second group 254 is not generated.

  Here, the validity of the size of the vehicle is determined as the likelihood of the vehicle, but the present invention is not limited to this, and the likelihood of the vehicle may be determined using other characteristics of the vehicle. For example, using the feature that the rear part of the vehicle is represented by one surface, the intersection line between the surface formed by each of the first groups 242 and the horizontal surface is almost in a straight line (the inclination is equal), which seems to be a vehicle. May be determined.

  By generating the second group 254 that satisfies the distance condition and the vehicle property in this way, even when the preceding vehicle is not integrally recognized as the region 250 but is recognized as a plurality of parts, FIG. As described above, a stereoscopic image (second group 254) can be formed with an appropriate size. However, the following problems may occur only under such conditions.

  Here, as shown in FIG. 8A, separate three-dimensional objects 260 that are not far apart, for example, two first groups 242 corresponding to a signboard and a vehicle are arranged side by side in the width direction of the image. Suppose you are. At this time, the distance between the first groups 242 is within the second distance range (the distance condition is satisfied), and the size of the second group 254 that integrates the first groups 242 is as shown in FIG. 8B. It is assumed that the vehicle has a reasonable size (a vehicle condition is satisfied). Then, since the 2nd grouping part 168 recognizes the 2nd group 254 which unified 1st group 242 as a solid thing which becomes a candidate of a specific thing, comfortable run on the contrary is obstructed by collision avoidance control and cruise control. There is a risk of being.

  Here, when FIG. 7 is compared with FIG. 8, it is between the width directions of the first groups 242 indicated by a one-dot chain line in FIG. The relative distance z of the blocks existing in the overlapping area (therefore, the width is the distance between the first groups 242 and the height is the same as the first group 242) 262 is approximately equal to the relative distance z of the first group 242. On the other hand, the relative distance z of the blocks (poles) existing in the region 262 between the first groups 242 in the width direction, which is indicated by a one-dot chain line in FIG. 8B, is farther from the first group 242. The point is different. Here, the maximum value in the height direction of the two first groups 242 is taken as the target of the region where the positions in the height direction overlap. That is, the height from the maximum value of the height of the first group 242 whose upper side is higher among the two first groups 242 to the minimum value of the height of the first group 242 whose lower side is lower among the two first groups 242. It is an area where the position of the direction overlaps. However, the target of the region of the present embodiment is not limited to this case, and it is sufficient if it is determined regularly. For example, the minimum value in the height direction of the two first groups 242, that is, the two first groups The maximum height of the first group 242 having the lower upper side of the 242 may be set to the minimum value of the height of the first group 242 having the higher lower side of the two first groups 242. In addition, one of the two first groups 242 may be the target, for example, the one with the longer height in the height direction, the one with the shorter length in the height direction, or the left side of the image. You can select the person who wants to be on the right side of the image.

  Therefore, the second grouping unit 168 obtains a block (relative distance z) that exists between the first groups 242 in the width direction and exists in a region 262 where the position of the first group 242 and the height direction overlaps on the image. The continuity between the first groups 242 is determined according to the relative distance z of the blocks).

(Continuity condition)
Specifically, the second grouping unit 168 is located between the first groups 242 in the width direction when the first groups 242 are in the left-right positional relationship with each other. In the region 262 where the positions in the height direction overlap, the number of blocks located farther than a predetermined threshold (for example, 5 m) (the relative distance z to the first group 242 is more than the threshold) is less than a predetermined number (for example, 10). If there is, the first groups 242 form the second group 254 by formally integrating the first groups 242 with each other indicating the same stereoscopic image as a candidate for the specific object. The first group 242 indicates a separate stereoscopic image, and the second group 254 is not generated. Note that by setting the predetermined number to 1, it is possible to make a condition whether or not there is a block itself located farther than a predetermined threshold.

  Here, continuity is determined according to the number of blocks located far away from a predetermined threshold (for example, 5 m). However, the present invention is not limited to this, and the number of divided stereoscopic image candidates 220 (number of divided regions 216). The continuity may be determined according to

  By doing so, the preceding vehicle shown in FIG. 7 satisfies the integration condition (all of the distance condition, the vehicle property condition, and the continuity condition), so that the entire region 250 of the preceding vehicle can be extracted as the second group 254. On the other hand, even if the separate three-dimensional object 260 shown in FIG. 8 satisfies the distance condition and the vehicle property condition, it does not satisfy the continuity condition (because the integration condition is not satisfied), so that the second group 254 is generated. Each of the first groups 242 before being integrated becomes a stereoscopic image that is a candidate for a specific object.

  In addition, by setting only the region 262 where the position in the height direction on the image overlaps the first group 242, the width is between the first groups 242 and the first Even if another stereoscopic image exists vertically above or vertically below the group 242, there is no influence on each other.

  For example, as shown in the distance image 212 of FIG. 9A, it is assumed that there is a fence below the side (near side) where the relative distance z is short and the three-dimensional object 260 exists on the far side (back side). Here, depending on the situation, the first groups 242 indicating the same fence may be generated apart from each other. Moreover, a three-dimensional object 260 also exists between the width directions. However, since only the first group 242 and the region 262 where the position in the height direction overlaps on the image are targeted for the continuity condition, it is possible to appropriately specify the specific object.

  Similarly, as shown in the distance image 212 of FIG. 9B, the road information indicator is above the side where the relative distance z is near (front side), and the three-dimensional object 260 is present on the far side (back side). Suppose that Here, the first groups 242 indicating the same road information display may be generated apart from each other. Moreover, a three-dimensional object 260 also exists between the width directions. However, since only the region 262 where the position in the height direction on the image overlaps with the first group 242 is the target of the continuity condition, it is possible to appropriately specify the specific object as in FIG. 9A. Become.

(Specific object identification process S208)
The specific object specifying unit 170 sets the second group 254 grouped by the second grouping unit 168 and the first group 242 not grouped by the second grouping unit 168 as a plurality of specific object conditions. If it is compared and the condition is satisfied, it is specified as a specific object. For example, in the specific object specifying unit 170, the width of the second group 254 grouped by the second grouping unit 168 is 2.0 m or more, and the height of the second group 254 is 1.0 m or more. If the height of the group 254 from the road surface is 2.0 m or less and the horizontal distance from the traveling locus of the host vehicle 1 is 5.0 m or less, the first group 242 is identified as the preceding vehicle. With the above configuration, the preceding vehicle located on the road can be extracted efficiently and appropriately.

(Vehicle control processing S210)
When the specific object specifying unit 170 specifies the preceding vehicle, the vehicle control unit 172 derives the relative speed or the like of the preceding vehicle while tracking the preceding vehicle, and there is a high possibility that the preceding vehicle and the host vehicle 1 collide with each other. And the result is output to the vehicle control device 130. Thus, collision avoidance control and cruise control are executed.

  As described above, in the outside environment recognition device 120 of the present embodiment, even when the distance of a separate three-dimensional object is short, an area to be controlled, for example, a preceding vehicle can be appropriately specified. Therefore, stable collision avoidance control and cruise control can be realized.

  Further, in addition to the above-described vehicle environment recognition device 120, a program that causes a computer to function as the vehicle environment recognition device 120, a computer-readable flexible disk, magneto-optical disk, ROM, CD, DVD, BD, or the like that records the program. A storage medium is also provided. Here, the program refers to data processing means described in an arbitrary language or description method.

  As mentioned above, although preferred embodiment of this invention was described referring an accompanying drawing, it cannot be overemphasized that this invention is not limited to this embodiment. It will be apparent to those skilled in the art that various changes and modifications can be made within the scope of the claims, and these are naturally within the technical scope of the present invention. Is done.

  For example, in the above-described embodiment, when the second grouping unit 168 satisfies all the three conditions of the distance condition, the vehicle condition, and the continuity condition as the integration conditions, the first groups 242 are integrated. However, the present invention is not limited to such a case, and the second group 254 may be generated if at least two conditions of the distance condition and the continuity condition are satisfied as the integration condition. it can.

  In the above-described embodiment, the application example to a pair of frame images (stereo images) captured at the same time has been described. However, the present invention is not limited to this, and a pair of frames having relevance to each other. Widely applicable to the area. As another example of such a frame region, there is a pair of frame images captured at different times, which are targets of so-called optical flow processing. In this case, a monocular camera is used instead of the imaging device 110 described above, and frame images are output in time series. Further, such a frame region is not limited to an image (luminance distribution) defined by luminance, but information other than luminance (for example, heat distribution obtained from a far-infrared camera, laser radar or millimeter wave radar) It may be defined by the obtained reflection intensity distribution or the like.

  It should be noted that each step of the vehicle environment recognition processing in the present specification does not necessarily have to be processed in time series in the order described in the flowchart, and may include processing in parallel or by a subroutine.

  The present invention relates to a vehicle exterior environment recognition device that recognizes an environment outside the host vehicle, and can be used particularly for a vehicle exterior environment recognition device that identifies a region to be controlled by the host vehicle.

120 Outside-vehicle environment recognition device 166 First grouping unit 168 Second grouping unit 242 First group 254 Second group

Claims (2)

Of the image captured by the imaging device, the plurality, the distance between the plurality of blocks in the case of converting the block represented by sequence of a given pixel in the 3-dimensional position information is within the first distance range A first grouping unit that groups the plurality of blocks to generate a first group;
Within the plurality of distances between the first group is the first distance range is greater than the second distance range when the first grouping unit has converted a plurality of said first group of grouped three-dimensional position information There, and in the case where the plurality of first group with each other in a positional relationship in the width direction left is between the width direction between the plurality of first group, the image on the first group and the height of the plurality in the region where the direction of the position overlap satisfies the integrated conditional block relative distance of the vehicle ahead is away more than a predetermined threshold value is less than the predetermined number, the second group by integrating together said plurality of first group Generate
Wherein a plurality of the distance said second distance range between the first group, and, even when the plurality of first group with each other in a positional relationship in the width direction right, to meet the integrated condition a second grouping unit that does not integrate with each other the plurality of first group,
A vehicle exterior environment recognition device. The second grouping unit is further only if the size of the case of the integration of the first group among the plurality is a reasonably large as the vehicle, the integrated with each other the plurality of first group third The outside environment recognition device according to claim 1, wherein two groups are generated.

Images