JP2003172780A - Recognition device and recognition method of preceding vehicle - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a recognition device and a recognition method capable of recognizing accurately a preceding vehicle, even when the preceding vehicle shows up on only a part of a detection range of a laser radar. <P>SOLUTION: Reflection lines RL are formed by elongating and projecting each reflecting point by a laser radar module two-dimensionally in the height direction equivalently to the vehicle height, and the dispersion of the lengths on the positions corresponding to a rectangular region S acquired by an image processing of each formed reflection line RL and the heights of the rectangular region S on the positions of the reflection lines RL is evaluated. The reflection lines RL by which the dispersion becomes below a prescribed value determined beforehand are selected as a vehicle candidate group, and the reflection lines RL of the selected vehicle candidate group are collated with the rectangular region S, to thereby acquire a recognition result having higher accuracy. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a front vehicle recognizing device and a recognizing method for recognizing a vehicle traveling in front of an own vehicle.

[0002]

2. Description of the Related Art In recent years, a vehicle equipped with a more advanced and more comfortable driving support system, such as a follow-up running function and a steering assist function on a highway, has been proposed. There is a recognition device that recognizes the vehicle.

In a conventional recognition device using this kind of scan laser radar, the distance to the reflection point can be detected by measuring the time from the irradiation of the laser beam to the observation of the reflected light, and the scanning mechanism is provided. By providing 10
If the vehicle has a horizontal field of view of several degrees and is a long-distance vehicle,
As shown in Figure 2, two reflections from reflectors (reflectors) installed at both ends of the vehicle rear end face can be observed, and many reflections from the vehicle body can be observed at medium and short distances.
The number of reflection points is as large as three or more. FIG. 6 (a) shows how laser light is emitted from the laser radar mounted on the vehicle, and ● in FIG. 6 (b) indicates a reflection point, and ZR in the figure indicates the traveling direction of the vehicle. XR is the direction orthogonal to this.

However, in this case, there is no constant reflection from the same part of the vehicle body, and the direction, shape,
The reflection position changes every moment due to the positional relationship and the distribution is not uniform.

Therefore, there has been proposed a method of recognizing a preceding vehicle by clustering the obtained reflection point group by a fuzzy method or the like. As a specific example thereof, Preprints 931 No. 93017
19, pp53-56 (1993-5) ("Development of preceding vehicle recognition algorithm by laser radar"), or Japanese Patent Application Laid-Open No. 6-30
There is a method described in Japanese Patent No. 9600.

[0006]

However, these conventional methods have almost no problem when the distance between vehicles or the distance between vehicles and a roadside structure is wide like an expressway. If you try to expand to, the following problems will occur. That is, as the first problem, the reflection from the traveling vehicle or the parked vehicle in the vicinity of the front vehicle is included in the reflection from the front vehicle and processed, and an error occurs in the distance measurement value of the front vehicle. The problem is that the reflection from the roadside object is included in the reflection from the vehicle in front and processed.
As a third problem that an error occurs in the distance measurement value of the vehicle ahead, there is a problem that detection of an interrupting vehicle or the like at a short distance is delayed because the horizontal field of view of the radar is generally narrow.

Further, in the case of a laser radar, when no vehicle is present, reflection from a roadside structure such as a reflector of a guardrail or a signboard is also observed, and these are erroneously recognized as a parked vehicle or a forward vehicle, or they are adjacent to each other. It may be determined that the vehicle in front of the lane is a vehicle traveling in the same lane as the observation vehicle, or the laser light may be attenuated by the water in front of the road splashing by the vehicle in front, making it impossible to recognize the vehicle in front. Is a problem peculiar to a laser radar or another problem requiring a very high level of recognition processing, and is not a problem to be solved by the present invention this time.

[0008] Therefore, in order to solve the above-mentioned first to third problems, a preprint 95 of an academic conference of the Society of Automotive Engineers of Japan
2, pp239-242 (1995) ("Examination of a traveling environment recognition method by fusion of image processing and laser radar"), when the vehicle recognition is performed using the laser radar, the image is processed by the image pickup means. It has been conventionally considered that by combining the results, it is possible to improve the recognition accuracy of the front vehicle by eliminating reflections from vehicles other than the front vehicle, roadside objects, and the like.

However, in the case of such fusion, in particular, as shown in FIG. 7, in the situation where the front vehicle is included in only a part of the detection range L of the laser radar, the image captured by the image pickup means is used to detect the rear vehicle. When a predetermined rectangular area including the end face image is extracted, the center of the rectangular area does not coincide with the center of the detection range L of the laser radar, and it is determined that the area detected by the laser radar is not a vehicle. However, the rectangular area obtained from the image of the image pickup means may not be recognized as a vehicle, and in such a situation, there is a problem that even if the laser radar and the image pickup means are collated, the forward vehicle cannot be accurately detected. It was

The problem to be solved by the present invention is to provide a recognition device and a recognition method capable of accurately recognizing a front vehicle that is only within a part of the detection range of a laser radar. The purpose is to do.

[0011]

In order to achieve the above object, a front vehicle recognition device according to a first aspect of the invention is a front vehicle recognition device for recognizing a vehicle traveling in front of the own vehicle. In the above, a laser radar that irradiates the front of the own vehicle while scanning the laser beam in the horizontal direction and receives the reflected light from the reflection point to identify the positions of the plurality of reflection points, and an imaging unit that images the front of the own vehicle An image processing unit for extracting a predetermined rectangular area including a rear end face image of a front vehicle from an image picked up by the image pickup unit, and the respective reflection points specified by the laser radar in a height direction corresponding to a vehicle height. Forming portions for two-dimensionally stretching and projecting to form reflection lines corresponding to the respective reflection points, and lengths of the respective reflection lines formed by the forming portions at positions corresponding to the rectangular regions. The height of the rectangular area It is characterized in that it comprises a recognition unit for recognizing a vehicle ahead based on and.

According to this structure, each reflection point specified by the laser radar is two-dimensionally extended and projected in the height direction corresponding to the vehicle height, and the reflection line corresponding to each reflection point is formed. Is formed, and whether or not the vehicle is a front vehicle is determined based on the length at the position corresponding to the rectangular area obtained by the image processing of these reflection lines and the height of the rectangular area.

At this time, when each reflection point is two-dimensionally expanded in the height direction by the amount corresponding to the vehicle height and projected to form a reflection line, each reflection point is formed at a position corresponding to a rectangular area obtained by image processing. Since the length of each reflection line is proportional to the distance to each reflection point, the length of each reflection line at the position corresponding to the rectangular area deviates significantly from the height of the rectangular area. It is possible to determine that the reflection line that does not correspond to the reflection point from the vehicle and that approximates the height of the rectangular region corresponds to the reflection point from the vehicle in front.

Therefore, only the reflection points corresponding to the reflection lines in which the length of each reflection line at the position corresponding to the rectangular area approximates the height of the rectangular area are selected, and the reflection point group by these selected reflection points is the vehicle. Since it can be judged as a candidate group, when merging the result of image processing by the imaging unit with the vehicle recognition using the laser radar, it is possible to accurately recognize the preceding vehicle that is only within the detection range of the laser radar. You can

Further, in the recognizing device for a front vehicle according to a second aspect of the present invention, the recognizing unit has a length of the reflecting line at a position corresponding to the rectangular area and a position of the reflecting line. The height of the rectangular area is compared to evaluate the variation, and when the variation is less than or equal to a predetermined value, it is determined that the rectangular area is a forward vehicle.

According to this structure, when each reflection point is two-dimensionally expanded and projected in the height direction by an amount corresponding to the vehicle height to form a reflection line, it corresponds to a rectangular area obtained by image processing. The length of each reflection line at the position corresponding to the rectangular area is greatly deviated from the height of the rectangular area because the length of each reflection line at the position It can be determined that the line does not correspond to the reflection point from the front vehicle, and the reflection line that approximates the height of the rectangular area corresponds to the reflection point from the front vehicle.

Therefore, the variation of the length of each reflection line at the position corresponding to the rectangular area and the height of the rectangular area at the position of the reflection line are evaluated, and the variation is equal to or less than a predetermined value. Even if the vehicle ahead is only part of the detection range of the laser radar, the reflected line corresponding to the reflection point from the vehicle ahead can be selected as a vehicle candidate by selecting You can

Further, in the recognizing device for a front vehicle according to a third aspect of the present invention, the recognizing unit has a length of the reflecting line at a position corresponding to the rectangular area and a position of the reflecting line. In the above, the reflection line in which the variation in height of the rectangular area is less than or equal to a specified value is a vehicle candidate group, and the vehicle candidate group is subjected to coordinate conversion into a coordinate system for image processing and a collating unit that collates with the rectangular area. When the vehicle candidate group after the coordinate conversion substantially coincides with at least a part of the rectangular area, the vehicle candidate group and the rectangular area are determined to be forward vehicles.

According to this structure, the collation unit
The length at the position corresponding to the rectangular area of each reflection line, and the reflection line in which the variation in the height of the rectangular area at the position of the reflection line is a predetermined value or less is selected as the vehicle candidate group,
Even when the front vehicle is only within a part of the detection range of the laser radar, only the reflection line corresponding to the reflection point from the front vehicle can be selected as the vehicle candidate group.

Further, the collating unit transforms the vehicle candidate group into the coordinate system of the image sensor and collates it with the rectangular area, and the judging section transforms the coordinate-converted vehicle candidate point group into at least a part of the rectangular area. If they substantially match, the vehicle candidate group and the rectangular area are determined to be the front vehicle, so that the front vehicle can be accurately detected under any circumstances.

Further, in the front vehicle recognition device according to the invention described in claim 4, the image processing unit sets a predetermined gazing area for an image picked up by the image sensor, and determines each pixel in the gazing area. The rectangular area as a vehicle candidate is extracted by computing the product of the edge histogram in the X direction from the grayscale, the edge histogram in the Y direction orthogonal to this, and the edge histogram in both directions to derive the maximum point. It is characterized by that.

With such a configuration, when a rectangular area as a vehicle candidate is extracted from the edge histogram,
Other than the vehicle can be excluded, and the rectangular area as a vehicle candidate can be accurately extracted.

According to a fifth aspect of the present invention, there is provided a method for recognizing a front vehicle, in which a laser radar irradiates a front side of the vehicle with laser light while scanning the same in a horizontal direction and receives reflected light from a reflection point. A distance measuring step of detecting the distance to a plurality of the reflection points and specifying the position of each of the reflection points;
An image pickup step of picking up an image of the front of the vehicle by the image pickup section, an extraction step of image-processing the image picked up by the image pickup step to extract a predetermined rectangular area including the rear end face image of the front vehicle, and the laser radar. A forming step of two-dimensionally projecting each of the reflection points in a height direction corresponding to a vehicle height to form a reflection line corresponding to each of the reflection points, and each of the reflection lines formed by the forming step. The recognition step of recognizing the preceding vehicle based on the length at the position corresponding to the rectangular area and the height of the rectangular area.

According to this structure, when each reflection point is two-dimensionally expanded in the height direction by the amount corresponding to the vehicle height and projected to form a reflection line, it corresponds to a rectangular area obtained by image processing. The length of each reflection line at the position corresponding to the rectangular area is largely deviated from the height of the rectangular area because the length of each reflection line at the position corresponding to the rectangular area is proportional to the distance to each reflection point. It can be determined that the reflection line does not correspond to the reflection point from the front vehicle, and the reflection line approximate to the height of the rectangular area corresponds to the reflection point from the front vehicle.

Therefore, each reflection point specified by the laser radar is two-dimensionally extended in the height direction corresponding to the vehicle height,
Corresponding to a rectangular area based on the height of the rectangular area and the length at a position corresponding to the rectangular area obtained by image processing of each of these reflective lines The length of each reflection line at the position to be selected is only the reflection points corresponding to the reflection line that approximates the height of the rectangular area, and these selected reflection points can be judged as a vehicle candidate group. When merging the results of image processing by the imaging unit with recognition, even in the situation where the vehicle in front is only within the detection range of the laser radar,
The vehicle in front can be recognized accurately.

Further, in the method for recognizing a front vehicle according to a sixth aspect of the present invention, in the recognizing step, the length of each of the reflection lines at a position corresponding to the rectangular area and the position of the reflection line. In the above step, the height of the rectangular area is collated, the variation is evaluated, and when the variation is equal to or less than a predetermined value, it is determined that the rectangular area is a forward vehicle.

According to such a configuration, when each reflection point is two-dimensionally expanded in the height direction by an amount corresponding to the vehicle height and projected to form a reflection line, it corresponds to a rectangular area obtained by image processing. The length of each reflection line at the position corresponding to the rectangular area is greatly deviated from the height of the rectangular area because the length of each reflection line at the position It can be determined that the line does not correspond to the reflection point from the front vehicle, and the reflection line that approximates the height of the rectangular area corresponds to the reflection point from the front vehicle.

Therefore, the variation in the length of each reflection line at the position corresponding to the rectangular region and the height of the rectangular region at the position of the reflection line is evaluated, and the variation is determined to be a predetermined value or less. By selecting such a reflection line, even if the front vehicle is only within a part of the detection range of the laser radar, only the reflection line corresponding to the reflection point from the front vehicle is selected as the vehicle candidate group. be able to.

According to a seventh aspect of the present invention, in the method for recognizing a front vehicle, the recognizing step includes the length of each of the reflection lines at a position corresponding to the rectangular area, and the position of the reflection line. In the collation step, in which the reflection line in which the variation in the height of the rectangular area is equal to or less than a specified value is a vehicle candidate group, and the vehicle candidate group is coordinate-converted into a coordinate system of image processing to collate with the rectangular area, When the vehicle candidate group after the coordinate conversion substantially matches at least a part of the rectangular area, the vehicle candidate group and the rectangular area are judged to be forward vehicles.

With such a configuration, the length of each reflection line at the position corresponding to the rectangular area and the variation in the height of the rectangular area at the position of the reflection line are less than a predetermined value. By selecting the reflection point corresponding to the vehicle candidate point group as a vehicle candidate point group, only the reflection line corresponding to the reflection point from the front vehicle is detected even if the front vehicle is only within a part of the detection range of the laser radar. Can be selected as a vehicle candidate group, and the selected vehicle candidate group is coordinate-converted into the coordinate system for image processing and collated with a rectangular area, so that the vehicle candidate group after coordinate conversion substantially matches at least a part of the rectangular area. At this time, the vehicle candidate group and the rectangular area can be determined to be the forward vehicle, so that the forward vehicle can be accurately detected under any circumstances.

[0031]

BEST MODE FOR CARRYING OUT THE INVENTION An embodiment of the present invention will be described with reference to FIGS. However, FIG. 1 is a block diagram, and FIGS. 2 to 5 are operation explanatory diagrams.

As shown in FIG. 1, a laser radar module 1 composed of a scan laser radar, its scanning mechanism and a light receiver, and a CCD camera module 2 as an image processing unit composed of a monocular CCD camera as an image pickup unit are provided in a vehicle. The laser radar module 1 irradiates the front of the vehicle with laser light while scanning the same in the horizontal direction, receives reflected light from a reflection point, and measures the distances to a plurality of reflection points. The position is identified, the front of the vehicle is imaged by the camera module 2, the reflection point data identified by the laser radar module 1, and the captured image obtained by the camera module 2 are CP.
It is stored in the memory 4 composed of RAM or the like by U3.
Note that another memory may be provided, and the data from the laser radar module 1 and the data from the camera module 2 may be stored in different memories.

At this time, the relationship between the coordinate systems of the laser radar module 1 and the camera module 2 is set as shown in FIG. 2, for example. That is, as shown in FIG. 2, the camera coordinate system takes the camera optical axis as the Z axis with the lens center as the origin, and takes the X axis and the Y axis parallel to the x axis and the y axis on the image plane. Here, the focal length f is known.

In the laser radar coordinate system, the light receiver is the origin, the laser optical axis is the ZR axis, and the YR axis is set in the vertical direction and the XR axis is set in the horizontal direction. XR YR ZR X from coordinate system
A YZ coordinate system can be converted by a composite matrix RT of a rotation vector R and a translation vector T, and as described later,
In the present invention, the coordinates of the reflection point specified by the laser radar module 1 are converted into camera coordinates for verification. However,
The composite matrix RT has been calibrated in advance,
It is known.

By the way, the laser radar module 1 is
Laser light is emitted in front of the vehicle, and the scanning mechanism scans the laser light horizontally at a predetermined angle (for example, 0.1 °), and the reflected light from the object in front of the vehicle is received by the light receiver. The distance between the irradiation of the laser light and the reception of the reflected light is detected from the distance between the vehicle and the preceding vehicle traveling in the same lane. The time required for such a single inter-vehicle distance detection process is about 100.
This is a short time of about ms, and this detection operation is repeated at regular intervals.

When a plurality of reflection points on the detection target are specified by the laser radar module 1 by such an operation, the CPU 3 determines each reflection point to be equivalent to the vehicle height (about 2).
The reflection line is formed by two-dimensionally extending and projecting in the height direction by m). Such a forming process by the CPU 3 corresponds to a forming unit.

On the other hand, the image of the front of the vehicle captured by the camera module 2 is processed by the CPU 3, and as shown in FIG. The density of the gazing area V is projected in the vertical direction to extract a vertical line segment, and a set of maximum points showing symmetry is selected from the vertical line segments, which are set as both end candidates of the vehicle. Further, a horizontal gazing area H is set at the coordinate located at the center of the set of local maximum points, a horizontal line segment is extracted in the same manner, and if a large number of observations are made, it becomes a rectangular area as a vehicle candidate.

Then, the CPU 3 varies the lengths of the respective reflection lines formed as described above at the positions corresponding to the rectangular regions by the image processing and the heights of the rectangular regions at the positions of the reflection lines. Is evaluated, and a reflection line whose variation is equal to or less than a predetermined value is selected as a vehicle candidate group.

At this time, when each reflection point is two-dimensionally expanded in the height direction by an amount corresponding to the vehicle height and projected to form a reflection line, each reflection point is formed at a position corresponding to a rectangular area obtained by image processing. Since the length of the reflection line is proportional to the distance to each reflection point, the length of each reflection line at the position corresponding to the rectangular area greatly deviates from the height of the rectangular area. It is possible to judge that the reflection line that does not correspond to the reflection point of the vehicle and that approximates the height of the rectangular area corresponds to the reflection point from the vehicle in front, and the reflection line and the rectangular area of the selected vehicle candidate group. By collating with, it is possible to obtain a more accurate recognition result. Such recognition processing by the CPU 3 corresponds to a recognition unit.

Specifically, when a rectangular area S is obtained by image processing as shown in FIG. 4A, only the reflection line RL shown in FIG. 4B, which approximates the height of the rectangular area S, is obtained. Is selected as the vehicle candidate group corresponding to the reflection point from the vehicle ahead. Then, as shown in FIG. 5, the rectangular region S is collated with the reflection line RL as the selected vehicle candidate group. Here, the height of the rectangular area S is Hi, the length of the reflection line RL of the vehicle candidate group is Hl, and n is the number of data, and Val =
Σ {min (Hi, Hl) / max (Hi, Hl)} / n
The fusion result can be evaluated by the evaluation function Val expressed as (1), and the closer the value of this evaluation function is to the predetermined value 1, the more coincident the rectangular area S and each selected reflection line RL are. The degree of accuracy is high and the probability of being a vehicle ahead is high.
Here, the evaluation function Val of the expression (1) represents an average value of cumulative values of the ratio of the smaller one (min) and the larger one (max) of Hi and Hl.

Therefore, as shown in FIG. 7, the reflection line RL corresponding to the reflection point from the front vehicle is set even when there is no front vehicle in the detection range L of the laser radar module 1. By selecting and matching the selected reflection line RL with the rectangular area S by image processing, it is possible to determine whether the vehicle is a front vehicle.

Therefore, according to the above-described embodiment, each reflection point specified by the laser radar module 1 is two-dimensionally extended and projected in the height direction corresponding to the vehicle height to correspond to each reflection point. The length of each reflection line at the position corresponding to the rectangular area is formed based on the length at the position corresponding to the rectangular area obtained by image processing of these reflection lines and the height of the rectangular area. If only the reflection lines that are close to the height of the rectangular area are selected, it is possible to judge that the selected reflection lines are the vehicle candidate group. Therefore, in the vehicle recognition using the laser radar module 1, the image processing by the CCD camera module 2 is performed. When the results are combined and collated, even a forward vehicle that is only within a part of the detection range of the laser radar module 1 can be accurately recognized.

Further, the laser radar module 1 is excellent in distance measurement, and the CCD camera module 2 can accurately distinguish the vehicle from the others, so that the CCD camera module 2
By combining the vehicle recognition by the laser radar module 1 with the vehicle recognition by the laser radar module 1, it is possible to prevent the reflection from the vehicle other than the front vehicle or the roadside object from being included in the reflection from the front vehicle as in the conventional case. Of course.

In the above embodiment, the evaluation function V
The case where the fusion result is evaluated by using al has been described, but the fusion result evaluation method is not limited to such an evaluation function. For example, the CPU 3 performs coordinate conversion of the reflection lines (or the reflection points corresponding to these) of the selected vehicle candidate group into the coordinate system in the image processing of the CCD camera module 2 and processes the imaged image by the CCD camera module 2. The obtained rectangular area may be collated, and when the coordinate-converted vehicle candidate group substantially coincides with at least a part of the rectangular area, the vehicle candidate group and the rectangular area may be determined as a forward vehicle. In this case, the matching process by the CPU 3 corresponds to the matching unit, and the determination process corresponds to the determination unit.

Further, in the above-mentioned embodiment, the case where the monocular CCD camera is used as the imaging means has been described, but it goes without saying that the imaging means is not limited to the monocular CCD camera described above.

Further, the present invention is not limited to the above-described embodiment, and various modifications other than those described above can be made without departing from the spirit of the present invention.

[0047]

As described above, according to the first and fifth aspects of the invention, the laser radar is excellent in distance measurement, and the image sensor can accurately distinguish between the vehicle and the other parts. Can be prevented from being included in the reflection from the front vehicle, which is the reflection from a vehicle other than the front vehicle, a roadside object, etc., as in the related art.

Further, each reflection point specified by the laser radar is two-dimensionally extended and projected in the height direction corresponding to the vehicle height to form a reflection line corresponding to each reflection point, and each of these reflection points is formed. Reflection in which the length of each reflection line at the position corresponding to the rectangular area approximates the height of the rectangular area based on the length of the reflection area at the position corresponding to the rectangular area and the height of the rectangular area. Since only the lines are selected and it is possible to determine that the selected reflected lines are the vehicle candidate group, when merging the results of the image processing by the imaging unit with the vehicle recognition using the laser radar, the detection range of the laser radar is It is possible to accurately recognize a vehicle ahead that is only part of it, and to provide a more advanced and more comfortable driving support system.

According to the second and sixth aspects of the present invention, when the reflection points are formed by two-dimensionally extending and projecting each reflection point in the height direction by an amount corresponding to the vehicle height, image processing is performed. Since the length of each reflection line at the position corresponding to the rectangular area obtained by is proportional to the distance to each reflection point, the length of each reflection line at the position corresponding to the rectangular area is It can be determined that the reflection line that largely deviates from the above does not correspond to the reflection point from the front vehicle, and the reflection line that approximates the height of the rectangular area corresponds to the reflection point from the front vehicle.

Therefore, the variation in the length of each reflection line at the position corresponding to the rectangular region and the height of the rectangular region at the position of the reflection line are evaluated, and the variation is equal to or less than a predetermined value. By selecting the reflection point corresponding to the reflection line, even if the front vehicle is only within the detection range of the laser radar, only the reflection point from the front vehicle is selected as a vehicle candidate. Will be possible.

According to the third and seventh aspects of the present invention, there are variations in the length of each reflection line at the position corresponding to the rectangular area and in the height of the rectangular area at the position of the reflection line. By selecting a reflection line that is less than the specified value as a vehicle candidate group, even if the front vehicle is only within a part of the detection range of the laser radar, the reflection line corresponding to the reflection point from the front vehicle Only the vehicle candidate group can be selected as the vehicle candidate group, and the selected vehicle candidate group is coordinate-converted into the coordinate system for image processing and collated with the rectangular area. When they match,
Since the vehicle candidate group and the rectangular area can be determined as the front vehicle, the front vehicle can be accurately detected under any circumstances.

According to the fourth aspect of the present invention, when extracting the rectangular area as the vehicle candidate from the edge histogram, it is possible to exclude other than the vehicle, and the rectangular area as the vehicle candidate is accurately extracted. It becomes possible to do.

[Brief description of drawings]

FIG. 1 is a block diagram of an embodiment of the present invention.

FIG. 2 is an operation explanatory diagram of the embodiment of the present invention.

FIG. 3 is an operation explanatory diagram of the embodiment of the present invention.

FIG. 4 is an operation explanatory diagram of the embodiment of the present invention.

FIG. 5 is an operation explanatory diagram of the embodiment of the present invention.

FIG. 6 is an operation explanatory diagram of vehicle recognition by the scan laser radar which is the background of the present invention.

FIG. 7 is an operation explanatory diagram of vehicle recognition by the scan laser radar which is the background of the present invention.

[Explanation of symbols]

1 Laser radar module 2 CCD camera module (image processing unit) 3 CPU (former, recognizer, collator, judger)

─────────────────────────────────────────────────── ─── Continuation of front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) G01B 11/00 G06T 1/00 330B G06T 1/00 330 5/40 5/40 7/00 150 7/00 150 300F 300 300G G08G 1/16 C G08G 1/16 G01S 17/88 A F Term (reference) 2F065 AA06 AA22 AA24 BB05 BB15 CC11 FF04 FF11 GG04 JJ03 JJ26 CB13 CA08DB12CAQ12 5B08CA1212B24CA0812B24CA0812B24CA08A12B24CA1212B24CA0812122424 DC16 DC19 DC32 5H180 AA01 CC03 CC04 CC14 LL01 LL04 LL11 5J084 AA05 AB01 AC02 AD01 BA03 CA32 DA01 EA07 5L096 AA06 BA04 CA02 FA06 FA35 FA66 FA69 JA20

Claims (7)

[Claims] 1. A front vehicle recognizing device for recognizing a vehicle traveling in front of the host vehicle, wherein a plurality of laser beams are emitted in front of the host vehicle while being horizontally scanned and reflected light is received from a reflection point. A laser radar that identifies the position of the reflection point, an image capturing unit that captures an image of the front of the vehicle, and an image processing unit that extracts a predetermined rectangular area including the rear end face image of the vehicle ahead from the image captured by the image capturing unit, A forming unit that two-dimensionally extends and projects each of the reflection points specified by the laser radar in a height direction corresponding to a vehicle height, and forms a reflection line corresponding to each of the reflection points; Recognition of a front vehicle, characterized by comprising a recognition unit for recognizing a front vehicle based on a length of each of the reflection lines formed by a portion at a position corresponding to the rectangular area and a height of the rectangular area. apparatus. 2. The recognizing unit collates the length of each of the reflection lines at a position corresponding to the rectangular region and the height of the rectangular region at the position of the reflection line to evaluate the variation. The front vehicle recognition device according to claim 1, wherein the rectangular area is determined to be a front vehicle when the variation is less than or equal to a predetermined value. 3. The recognizing unit has variations in the length of each of the reflection lines at a position corresponding to the rectangular region and the height variation of the rectangular region at the position of the reflection line is equal to or less than a specified value. The reflection line is used as a vehicle candidate group, the vehicle candidate group is coordinate-converted into a coordinate system for image processing and collated with the rectangular area, and the vehicle candidate group after coordinate conversion is at least a part of the rectangular area. The vehicle front recognition device according to claim 2, further comprising: a vehicle candidate group and a determination unit that determines the rectangular area as a vehicle ahead when the vehicle candidate group and the rectangular area substantially match. 4. The image processing unit sets a predetermined gaze area for an image picked up by the image sensor, and an edge histogram in the X direction from the grayscale of each pixel in the gaze area, in the Y direction orthogonal thereto. Edge histogram of,
4. The front vehicle recognition according to claim 1, wherein the rectangular area as a vehicle candidate is extracted by calculating a product of edge histograms in both directions and deriving a maximum point thereof. apparatus. 5. A front vehicle recognizing method for recognizing a vehicle traveling ahead of the own vehicle, wherein a laser radar irradiates the front of the own vehicle with laser light while scanning the same in a horizontal direction and reflects light from a reflection point. A distance measurement step of receiving light and detecting the distance to a plurality of the reflection points to specify the position of each reflection point, an imaging step of imaging the front of the vehicle by an imaging unit, and an image captured by the imaging step An extraction step of processing to extract a predetermined rectangular area including the rear end face image of the front vehicle, and two-dimensionally extending each of the reflection points specified by the laser radar in the height direction corresponding to the vehicle height, A forming step of forming a reflection line corresponding to each of the reflection points by projecting, and a length at a position corresponding to the rectangular area of each reflection line formed by the forming step and a height of the rectangular area. Based on Recognition method of the forward vehicle, characterized in that it comprises a recognizing step the vehicle. 6. The recognizing step collates the length of each of the reflection lines at a position corresponding to the rectangular region and the height of the rectangular region at the position of the reflection line to evaluate the variation. The method for recognizing a front vehicle according to claim 5, further comprising the step of determining that the rectangular area is a front vehicle when the variation is equal to or less than a predetermined value. 7. In the recognition step, the variation in the length of each of the reflection lines at a position corresponding to the rectangular area and the height of the rectangular area at the position of the reflection line is equal to or less than a specified value. A matching step of converting the reflection line into a vehicle candidate group, converting the vehicle candidate group into a coordinate system for image processing and matching the rectangular area, and the vehicle candidate group after the coordinate conversion is at least a part of the rectangular area. 7. The method for recognizing a front vehicle according to claim 6, further comprising a determination step of determining the vehicle candidate group and the rectangular area as a front vehicle when they substantially match.