JP2007280132A - Travel guide obstacle detector, and controller for vehicle - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a travel guide obstacle detector which can detect exactly an obstacle such as a lane separation sign and a pylon, out of a solid object existing in front of own vehicle. <P>SOLUTION: The travel guide obstacle detector 1 is provided with: an imaging means 2 for photographing a scene in front of the own vehicle including a road to output a pair of images having a brightness value p1ij in every pixel; an image processing means 6 for calculating a distance Zij in a real space as to the each pixel of the at least one image T, based on the imaged paired images; and a detecting means 9 for detecting the solid image Sn from the one image T, based on information of the brightness value p1ij and the distance Zij, and for calculating a size of the real space of the solid image Sn. The detecting means 9 detects the solid image Sn as the travel guide obstacle Kn, when the size of the solid image Sn on the real space is within a preset threshold value, and when a vertical-directional brightness change of the solid image Sn detected in the one image T has a fixed pattern. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a travel guidance obstacle detection device and a vehicle control device, and more particularly to a travel guidance obstacle detection device that detects a travel guidance obstacle such as a lane separator or a pylon from a captured image in front of the host vehicle. The present invention relates to a vehicle control device using the

  In order to perform automatic control for improving the stability and safety of driving in vehicles such as passenger cars, lanes marked on the left and right road surfaces of the host vehicle and preceding vehicles existing in front of the host vehicle In addition, it is necessary to accurately detect a three-dimensional object such as a parked vehicle or a pedestrian as accurately as possible to recognize the traveling environment of the host vehicle.

  Therefore, in recent years, lanes are recognized from captured images in front of the host vehicle (see, for example, Patent Document 1), road shapes are recognized (for example, see Patent Documents 2, 3, etc.), or on or around a driving lane. Techniques such as recognizing a three-dimensional object or a vehicle (see, for example, Patent Documents 2, 4 to 6) have been developed.

In the present invention, a continuous line or a broken line marked on a road surface such as a road center line such as an overtaking prohibition line, a vehicle traffic zone boundary line, a lane line dividing a roadside zone and a roadway is called a lane, and a lane A vehicle lane where the vehicle between the vehicle and the lane travels is called a travel lane. Further, a lane separator as shown in FIG. 17A or a pylon called a color cone (registered trademark) placed on a road as shown in FIG. A driving-guided obstacle is used to represent an object.
JP 2001-92970 A JP-A-5-265547 Japanese Patent Laid-Open No. 11-203458 JP-A-10-283461 Japanese Patent Laid-Open No. 10-283477 JP 2006-47057 A

  By the way, among the driving guidance obstacles arranged on or around the driving lane of the own vehicle, the lane separator may be erected in the center of the road instead of the lane as a sign indicating the road center line, for example. . In such a case, it is possible to recognize the right end position of the travel lane only after detecting the lane separator, and it is possible to perform automatic control such as key plane control along that.

  In addition, when a pylon is placed in the lane for road construction or civil engineering work, the pylon is not detected along the lane on the left or right side of the host vehicle, but is accurately detected. If the control is not performed along the pylon according to the guidance of the vehicle, the host vehicle cannot be properly driven.

  On the other hand, a radar device is often used in a technique for recognizing a vehicle existing around the host vehicle. The radio wave emitted from the radar is strongly reflected by the lane separator shown in FIGS. 17A and 17B and the reflecting material R applied or wound on the surface of the pylon, so that it is mounted on the vehicle. Inexpensive radars may misrecognize lane markings, travel-guided obstacles such as pylons, etc. as vehicles.

  For this reason, a travel-guided obstacle stationary on the road is mistakenly recognized as a vehicle and the host vehicle is automatically stopped to avoid a collision with it, or a travel-guided obstacle such as a lane separator or pylon is used. There arises a problem that the vehicle cannot travel along the road. As described above, it is desired to develop a technique that enables detection of a travel guidance obstacle from a three-dimensional object existing in front of the host vehicle as a travel guidance obstacle without erroneous recognition.

  The present invention has been made in view of such circumstances, and is capable of accurately detecting a traveling guidance obstacle such as a lane separator or a pylon from a three-dimensional object existing in front of the host vehicle. An object of the present invention is to provide a guidance obstacle detection device. It is another object of the present invention to provide a vehicle control device that effectively uses this travel guidance obstacle detection device.

In order to solve the above problem, the first invention provides:
In the travel guidance obstacle detection device,
Imaging means for imaging a landscape including a road ahead of the host vehicle and outputting a pair of images having a luminance value for each pixel;
Image processing means for calculating a distance in real space for each pixel of at least one image based on the pair of captured images;
Detecting means for detecting a three-dimensional object from the one image based on the information on the luminance value and the distance, and calculating a size of the three-dimensional object in real space;
When the size of the three-dimensional object in real space is within a preset threshold and the luminance change in the vertical direction of the three-dimensional object detected in the one image has a constant pattern The three-dimensional object is detected as a traveling guidance obstacle.

  According to a second aspect of the present invention, in the travel guidance obstacle detection device according to the first aspect, the detecting means calculates a position of the three-dimensional object in real space and is detected as a travel guidance obstacle in the one image. The arrangement of the three-dimensional object is approximated by a straight line or a curve, the straight line or curve obtained by the approximation is extended to a region far from the host vehicle, and the detected three-dimensional object on the extended straight line or curve Is detected as a traveling guidance obstacle.

  According to a third aspect of the present invention, in the travel-guided obstacle detection device of the first aspect, the detection means calculates the position of the three-dimensional object in real space and finds it in the one image by the behavior of the host vehicle. The location of past driving guidance obstacles that are no longer being updated is recorded based on the behavior of the host vehicle, and the position of the past driving guidance obstacle is detected as a driving guidance obstacle in the one image. The position of the three-dimensional object is approximated by a straight line or a curve, the straight line or curve obtained by the approximation is extended to a region far from the host vehicle, and the detection is on or near the extended straight line or curve. The detected three-dimensional object is detected as a travel guidance obstacle.

4th invention is a control apparatus for vehicles,
A travel guidance obstacle detection device according to any one of the first to third inventions;
Information collecting means for collecting information about a three-dimensional object around the host vehicle by means other than the imaging means;
Control for recognizing the three-dimensional object as a traveling guidance obstacle when the information on the three-dimensional object collected by the information collecting means corresponds to the information on the traveling guidance obstacle detected by the traveling guidance obstacle detection device. It has the apparatus.

  According to a fifth aspect of the present invention, there is provided the vehicle control device according to the fourth aspect, wherein the control device treats a three-dimensional object outside the three-dimensional object recognized as the traveling guidance obstacle when viewed from the host vehicle as a three-dimensional object. It is excluded from the control object of the control for adjusting the distance.

A sixth invention is a vehicle control device,
A travel guidance obstacle detection device according to any one of the first to third inventions;
An alarm device for issuing an alarm to the driver;
When the own vehicle is approaching a three-dimensional object recognized as the travel-guided obstacle, the vehicle has a control device that outputs an alarm to the alarm device.

The seventh invention is the vehicle control device of the sixth invention,
Lane detection means for detecting the lane on the left and right of the host vehicle,
The control device issues an alarm when the host vehicle is approaching the lane detected by the lane detecting means, and a three-dimensional object recognized as the travel guiding obstacle is detected by the lane detecting means. In the case of being in the vicinity, the timing for issuing an alarm is earlier than in the case of only the lane.

The eighth invention is a vehicle control device,
A travel guidance obstacle detection device according to any one of the first to third inventions;
It has a control apparatus which controls a run of the self-vehicle so that it may run along a solid thing recognized as the run guidance obstacle.

A ninth invention is the vehicle control device of the eighth invention,
Lane detection means for detecting the lane on the left and right of the host vehicle,
The control device controls the traveling of the host vehicle so that the host vehicle travels along the lane detected by the lane detecting unit, and detects the three-dimensional object recognized as the traveling guidance obstacle by the lane detecting unit. When the vehicle is in the vicinity of the lane, the traveling of the host vehicle is controlled so as to travel with a larger distance from the lane than when only the lane is detected.

A tenth aspect of the invention is a vehicle control device,
A travel guidance obstacle detection device according to any one of the first to third inventions;
Lane detection means for detecting lanes on the left and right of the host vehicle;
When the solid object detected inside the lane detected by the lane detection means or in the vicinity thereof and recognized as the traveling guidance obstacle is a pylon, Has a control device for determining that the road on which the vehicle is traveling is under construction.

  An eleventh invention is the vehicle control device according to the tenth invention, wherein the control device stops lane departure avoidance control when it is determined that the road on which the host vehicle is traveling is under construction. It is characterized by.

  A twelfth aspect of the invention is the vehicle control device according to the tenth aspect of the invention, wherein the control device stops the lane tracking control when it is determined that the road on which the host vehicle is traveling is under construction. And

  A thirteenth invention is the vehicle control device according to the tenth invention, wherein when the control device judges that the road on which the host vehicle is traveling is under construction, the host vehicle travels along the pylon. The tracking control is performed as described above.

  According to the first aspect of the present invention, the size of the three-dimensional object detected in the one image is selected based on the width and height, and further, the selection is performed based on the repetitive luminance pattern. It is possible to accurately detect a traveling guidance obstacle such as a lane separator or a pylon from among three-dimensional objects existing in the vehicle. Therefore, a three-dimensional object that is a traveling guidance obstacle can be appropriately detected as a traveling guidance obstacle without misrecognizing it as a vehicle, for example.

  According to the second aspect of the present invention, a three-dimensional object that has been excluded without being detected as a luminance repetition pattern because it is far from the host vehicle is detected by calculating the position of the three-dimensional object in real space. The arrangement of the plurality of travel guidance obstacles is approximated by a straight line or curve, and a three-dimensional object on or near the straight line or curve is detected as a travel guidance obstacle. For this reason, it is possible to accurately determine whether or not a three-dimensional object for which a repeated pattern of luminance has not been detected is a travel guidance obstacle, and to appropriately detect it as a travel guidance obstacle. Exhibited accurately.

  According to the third invention, not only a plurality of driving guidance obstacles detected in one image, but also past driving guidance obstacles that are no longer found in one image due to the behavior of the host vehicle are tracked. The three-dimensional object on the straight line or curve or in the vicinity thereof is detected as a travel guidance obstacle so that the effect of the second invention can be exhibited more effectively. It becomes possible.

  According to the fourth invention, as described above, when using a radar apparatus or the like, a traveling guidance obstacle may be misrecognized as a vehicle, for example, but the traveling guidance obstacle detection apparatus of the present invention is used. By comparing the information of the three-dimensional object extracted by the radar device or the like with the information of the driving guidance obstacle detected by the traveling guidance obstacle detection device, the corresponding three-dimensional object is recognized as a traveling guidance obstacle. It is possible to reliably prevent the travel-guided obstacle from being erroneously recognized as a vehicle or the like.

  According to the fifth aspect of the present invention, the driving guidance obstacle is identified from the three-dimensional object, and the three-dimensional object outside the three-dimensional object is excluded from the control control target of the control for adjusting the distance from the three-dimensional object. In addition to the above effect, it is possible to reduce the calculation processing for control, it is possible to reduce the calculation load of the control device, and it is possible to improve the processing speed.

  According to the sixth aspect of the present invention, it is possible to reliably detect a driving guidance obstacle such as a lane separator and to issue a warning when the host vehicle approaches it, thereby effectively raising the driver's attention and driving guidance. It is possible to appropriately prevent an obstacle from being touched or departing from the lane.

  According to the seventh invention, in a lane in which a travel guidance obstacle is erected in the vicinity and lane departure is strongly prohibited, by speeding up the timing of issuing an alarm than in the case of only a lane without a travel guidance obstacle, The driver's attention is alerted at an early stage, and lane departure can be reliably prevented, and the vehicle can be prevented from coming into contact with or colliding with a travel-guided obstacle. It becomes possible to demonstrate.

  According to the eighth aspect of the present invention, a lane is marked on the road surface by reliably detecting a travel-guided obstacle such as a lane separator and performing lane tracking control so that the host vehicle travels along the obstacle. Even when only a travel-guided obstacle such as a lane separator is erected, the host vehicle can automatically travel along the lane separator.

  According to the ninth aspect of the present invention, in a lane in which a travel guidance obstacle is erected in the vicinity and departure from the lane is strongly prohibited, the lane is largely separated from the lane as compared with a lane having no travel guidance obstacle. Deviations can be reliably prevented, and the host vehicle can be prevented from coming into contact with or colliding with a travel-guided obstacle, and the effects of the present invention can be more effectively exhibited.

  According to the tenth aspect of the invention, the travel guidance obstacle detection device distinguishes and detects the lane separation mark and the pylon, and determines that the detected travel guidance obstacle is a pylon. It becomes possible to accurately determine that the road is under construction for road construction or civil engineering work, and it is possible to perform appropriate vehicle control.

  According to the eleventh aspect of the present invention, if the road is under construction, it is assumed that the own vehicle deviates from the travel lane and travels across the lane or changes to the adjacent travel lane. Therefore, when it is determined that the road on which the host vehicle is traveling is under construction, lane departure avoidance control is stopped, and when the driver intentionally departs from the lane, lane departure avoidance control is performed. Therefore, the host vehicle is controlled so as to be pulled back to the original travel lane against the driver's intention, and it is possible to prevent the travel from becoming unstable.

  According to the twelfth invention, even when it is determined that the road on which the host vehicle is running is under construction, the driver intentionally departs the lane so as not to collide with the pylon. In such a case, by stopping the tracking control for the lane, it is possible to prevent the vehicle from being unstable due to control so that the host vehicle is pulled back to the original travel lane against the driver's intention. Become.

  According to the thirteenth invention, in order to perform the follow-up control by issuing the instruction signal to the responding unit so that the host vehicle travels along the pylon detected by the travel-guided obstacle detection device, When the vehicle is placed, it becomes possible for the host vehicle to travel along it, and to appropriately avoid contact and collision with the pylon.

  DESCRIPTION OF EMBODIMENTS Hereinafter, embodiments of a travel guidance obstacle detection device and a vehicle control device according to the present invention will be described with reference to the drawings.

[First Embodiment]
First, the traveling guidance obstacle detection device will be described. As shown in FIG. 1, the travel guidance obstacle detection apparatus 1 according to the present embodiment mainly includes an imaging unit 2, an image processing unit 6, and a detection unit 9.

  The imaging means 2 is for imaging the periphery of the vehicle, and is configured to capture a landscape including a road ahead of the vehicle at a predetermined sampling period and output a pair of images. In the present embodiment, a stereo camera including a pair of main camera 2a and sub-camera 2b each incorporating a synchronized image sensor such as a CCD or CMOS sensor is used. In the present embodiment, CCD cameras are used for the main camera 2a and the sub camera 2b.

  The main camera 2a and the sub camera 2b are attached, for example, in the vicinity of a rearview mirror with a predetermined interval in the vehicle width direction. Of the pair of stereo cameras, a camera closer to the driver, as will be described later, a main camera 2a that captures an image serving as a basis for detecting distances and detecting lanes for each pixel, and a camera farther from the driver Is a sub-camera 2b that captures an image to be compared in order to obtain the distance or the like.

  A / D converters 3a and 3b as conversion means 3 are connected to the main camera 2a and the sub camera 2b, respectively. In the A / D converters 3a and 3b, each of the pair of analog images output from the main camera 2a and the sub camera 2b has a luminance value of a predetermined luminance gradation such as a gray scale of 256 gradations for each pixel. It is configured to be converted into an image. The digital image converted from the image on which the distance is calculated for each pixel and the lane is detected is used as the reference image, and the digital image converted from the image to be compared for obtaining the distance is compared. It is output as an image.

  An image correction unit 4 is connected to the A / D converters 3a and 3b. In the image correction unit 4, the luminance includes a deviation caused by an error in the attachment positions of the main camera 2 a and the sub camera 2 b and noise removal with respect to the reference image and the comparison image output from the A / D converters 3 a and 3 b. Image correction such as value correction is performed using affine transformation or the like.

  For example, as shown in FIG. 2, the reference image T is image data composed of luminance values of 512 pixels in the horizontal direction and 200 pixels in the vertical direction. The image correction unit 4 is configured to output image data composed of luminance values for 200 pixels in the vertical direction. Each image data is stored in an image data memory 5 connected to the image correction unit 4 and is simultaneously transmitted to the detection means 9.

  As described above, in this embodiment, a CCD camera is used for the main camera 2a and the like. The main camera 2a and the sub camera 2b scan and capture the landscape in front of the host vehicle in a line in the horizontal direction sequentially from the lower side, and sequentially transmit the data captured for each horizontal line to the conversion means 3. Then, after the imaging data is converted into a luminance value of a predetermined luminance gradation for each pixel of the horizontal line transmitted by the conversion means 3 and image correction is performed by the image correction unit 4, Image data is stored in the image data memory 5 and simultaneously transmitted to the detection means 9 at the same time.

  The image data memory 5 stores digital data of images transmitted from the main camera 2a and the sub camera 2b at regular time intervals and subjected to image correction and the like in time series. .

  An image processing unit 6 is connected to the image correction unit 4, and the image processing unit 6 mainly includes an image processor 7 and a distance data memory 8.

  In the image processor 7, each setting area composed of each pixel or a block composed of a plurality of pixels of the reference image T based on the digital data of the reference image T and the comparison image output from the image correction unit 4 by the stereo matching process and the filtering process. The parallax d for calculating the distance in the real space is calculated. The calculation of the parallax d is described in detail in Japanese Patent Application Laid-Open No. H5-114099 previously filed by the applicant of the present application.

  The image processor 7 calculates one parallax d for each pixel block of 4 × 4 pixels for the reference image T having 512 × 200 pixels. As described above, the luminance value p1ij of 0 to 255 is assigned to each of the 16 pixels constituting one pixel block, and the luminance value p1ij of the 16 pixels forms a luminance value characteristic unique to the pixel block. Yes.

  The subscripts i and j of the luminance value p1ij are the i coordinates of the pixel at the lower left corner of the pixel block when the lower left corner of the image plane of the reference image T is the origin, the horizontal direction is the i coordinate axis, and the vertical direction is the j coordinate axis. And the j coordinate. For the comparison image, the i-coordinate and the j-coordinate are similarly taken with the pixel previously associated with the origin of the reference image T as the origin.

In the stereo matching process in the image processor 7, the reference image T is divided into a maximum of 128 × 50 pixel blocks every 4 × 4 pixels as described above, and the comparison image is a horizontal line having a width of 4 pixels extending in the horizontal direction. Divide into Then, one pixel block of the reference image T is taken out and the city block distance CB obtained by the following equation (1) is minimized while shifting the horizontal line of the corresponding comparison image one pixel at a time in the horizontal direction, that is, in the i direction. The pixel block on the horizontal line to be, that is, the pixel block on the comparative image having the luminance value characteristic similar to the pixel block of the reference image T is searched.
CB = Σ | p1ij−p2ij | (1)

  P2ij represents the luminance value of the pixel at the coordinates (i, j) on the comparison image. In the present embodiment, as described above, the image data for each horizontal line is output from the image correction unit 4. Therefore, the image processor 7 receives the 4 × horizontal image data every time the image data for four horizontal lines is input. Stereo matching processing is performed on a pixel block of 4 pixels.

  The image processor 7 calculates a shift amount between the pixel block on the comparison image specified in this way and the pixel block on the reference image T, and sets the shift amount as a parallax d to the pixel block on the reference image T. It is designed to be assigned.

  The parallax d is a horizontal relative shift amount with respect to the mapping position of the same object in the reference image T and the comparison image derived from the fixed distance between the main camera 2a and the sub camera 2b. The distance from the center position of the camera 2b to the object and the parallax d can be associated based on the principle of triangulation.

Specifically, in real space, a point on the road surface directly below the center of the main camera 2a and the sub camera 2b is set as the origin, and the vehicle width direction of the own vehicle, that is, the X axis in the left-right direction, the Y axis in the vehicle height direction, When the Z-axis is taken in the vehicle length direction, that is, the distance direction, coordinate transformation from the point (i, j, d) on the image to the point (X, Y, Z) on the real space is as follows (2) to (4 ) Based on the formula.
X = CD / 2 + Z * PW * (i-IV) (2)
Y = CH + Z × PW × (j−JV) (3)
Z = CD / (PW × (d−DP)) (4)

  That is, the center position of the main camera 2a and the sub camera 2b, more precisely, the distance from the point on the road surface directly below the center to the object and the parallax d are uniquely determined by using Z in the equation (4) as a distance. It is associated. Here, CD is the distance between the main camera 2a and the sub camera 2b, PW is the viewing angle per pixel, CH is the mounting height of the main camera 2a and the sub camera 2b, and IV and JV are infinity points in front of the host vehicle. I coordinate and j coordinate, and DP represent vanishing point parallax.

  Further, for the purpose of improving the reliability of the parallax d, the image processor 7 performs a filtering process on the parallax d thus obtained, and outputs only the parallax d that has been validated. That is, for example, even if a 4 × 4 pixel block consisting of only a road image is scanned on a horizontal line having a width of 4 pixels of the comparison image, all the portions of the comparison image where the road is imaged are correlated. Even if the corresponding pixel block is specified and the parallax d is calculated, the reliability of the parallax d is low. Therefore, such parallax d is invalidated in the filtering process, and 0 is output as the value of parallax d.

  Therefore, the distance Z of each pixel of the reference image T output from the image processor 7, that is, the parallax d for calculating the distance in the real space for each pixel block of the reference image T is usually in the left-right direction of the reference image T. The data has an effective value only for a so-called edge portion in which the difference in luminance value p1ij is large between adjacent pixels.

  The parallax d of each pixel block of the reference image T calculated by the image processor 7 is stored in the distance data memory 8 of the image processing means 6 as distance data. In the distance data memory 8, distance data transmitted from the image processor 7 at a constant time interval is stored in time series.

  In the processing in the detection means 9 described below, one pixel block of the reference image T is treated as 4 × 4 pixels, and 16 pixels belonging to one pixel block are regarded as independent pixels having the same parallax d. To be processed. Hereinafter, the pseudo image in which the parallax d is assigned to each pixel stored in the distance data memory 8 is referred to as a distance image.

  The detection means 9 includes a lane detection means 91, a three-dimensional object detection means 92, a travel guidance obstacle detection means 93, and a past obstacle update means 94.

  Sensors A such as a vehicle speed sensor and a yaw rate sensor are connected to the detection means 9 via an I / O interface (not shown), and a vehicle speed V, a yaw rate γ, and the like are input from the sensors A. ing. Instead of using the yaw rate sensor, for example, a yaw rate estimation device such as a vehicle motion model generation device described in Japanese Patent Application Laid-Open No. 2004-249812 can be connected.

  The lane detection unit 91 detects a lane candidate point on the reference image T based on the luminance value p1ij of each pixel of the reference image T and the distance Zij of each pixel in the real space, and the host vehicle based on the detected lane candidate point The left and right lane positions are detected.

  The lane detection unit 91 may be any device that can detect the lane position from the reference image T, and the method of detecting the lane position is not limited to a specific method. In the present embodiment, the lane detection means 91 is configured based on the lane recognition device described in Patent Document 1 and the like. A detailed description of the configuration is left to the same publication, but the configuration will be briefly described below.

  The lane detection unit 91 reads information on the luminance value p1ij of each pixel of the reference image T from the image data memory 5 and reads information on the parallax d of each pixel of the distance image from the distance data memory 8. Then, the horizontal line j having a width of one pixel on the reference image T is searched while being offset by one pixel in the left-right direction, and each pixel is determined based on the luminance value p1ij of each pixel of the reference image T as shown in FIG. Are detected as lane candidate points (Ij, Jj), respectively.

  At that time, the distance Zij of each pixel is calculated based on the information on the parallax d of each pixel assigned to the distance image corresponding to the reference image T, and the detected pixel is excluded if it is not on the road surface. It is not detected as a candidate point.

  The lane detecting means 91 sequentially detects lane candidate points while offsetting the horizontal line j to be searched upward by one pixel width from the lower side of the reference image T. As shown in FIG. Lane candidate points are detected in the area A and the left area B, respectively. Then, by removing the lane candidate points that cannot be consistent among them and connecting the remaining lane candidate points, the right lane position LR on the right side of the host vehicle on the reference image T as shown in FIG. The left lane position LL is detected on the left side. The left and right lane positions LR and LL are also converted into lane positions LR and LL in real space, respectively.

  The search for lane candidate points is performed by setting a search area on the reference image T. That is, in this detection process, a search area is set in a certain range on the reference image T including the lane position based on the lane position detected in the previous detection process. In this detection, when the pixels are sequentially detected while the horizontal line j is offset by one pixel width upward from the lower side of the reference image T, no pixel satisfying the above condition is detected in a certain horizontal line j. In this case, the search area is expanded on the next horizontal line to search for lane candidate points.

  The lane detecting unit 91 stores information on the left and right lane positions LR and LL detected in this way in a memory (not shown) and outputs the information to the outside of the apparatus.

  The three-dimensional object detection unit 92 detects a three-dimensional object on the reference image T based on the distance Zij in the real space calculated from the parallax d of each pixel of the distance image. The three-dimensional object detection unit 92 only needs to be capable of accurately detecting a three-dimensional object present at a position higher than the road surface, and the detection method is not limited to a specific method. In the present embodiment, the three-dimensional object detection means 92 is configured based on the vehicle exterior monitoring device described in Patent Document 5 and the like, and the detailed description is left to the same publication. The configuration will be briefly described below.

  The three-dimensional object detection unit 92 first divides the distance image read from the distance data memory 8 into strip-shaped sections extending in the vertical direction with a predetermined pixel width. Then, the distance Zij is calculated for each pixel from the parallax d of each pixel belonging to each of the strip-shaped sections, and a histogram relating to the distance Zij that is positioned at a position higher than the road surface is created. Let the distance be the distance of the three-dimensional object included in the strip-shaped section. This is done for all categories.

  For example, when the distance of each section obtained by dividing the distance image corresponding to the reference image T shown in FIG. 2 into strip-shaped sections is converted into points on the real space, a three-dimensional object is obtained as shown in FIG. Each point is plotted with some variation in the part corresponding to the part facing the host vehicle MC.

  As shown in FIG. 7, the three-dimensional object detection unit 92 groups the points into groups G1 to G7 based on the distance and directionality of each point. As shown in FIG. The groups arranged are labeled as front O1-O3, and the groups where each point is arranged substantially in the Z-axis direction are labeled as side walls W1-W4 to detect the three-dimensional object as "front" and "side walls". Yes.

  Here, the X-axis direction is the vehicle width direction perpendicular to the traveling direction of the host vehicle, that is, the left-right direction, and the Z-axis direction is the vehicle length direction, ie, the front-rear direction, and the origin is the center of the main camera 2a and the sub camera 2b. Taken at a point on the road just below the location. The Y-axis direction refers to the vehicle height direction, that is, the vertical direction.

  When the “front” and the “side wall” belong to one solid object as in the front O1 and the side wall W1 in FIG. 8, the three-dimensional object detection unit 92 is a combination of the “front” and the “side wall”. Is recognized as a three-dimensional object S, and the corner of the three-dimensional object such as the boundary between the front surface O1 and the side wall W1 is calculated as the corner point C.

  When the front surface On, the side wall Wn, and the three-dimensional object Sn detected in this way are displayed on the reference image T so as to be surrounded by a frame line, the image is displayed as shown in FIG. Hereinafter, the front On, the side wall Wn, and the three-dimensional object Sn are collectively referred to as a three-dimensional object Sn.

  The three-dimensional object detection unit 92 stores information on the coordinates and height of the left and right ends of each group of three-dimensional objects Sn detected in this manner in a memory and outputs them to the outside of the apparatus.

  The traveling guidance obstacle detecting means 93 is applied or wrapped with a reflector R as shown in FIGS. 17A and 17B from among the three-dimensional objects Sn detected by the three-dimensional object detecting means 92. A travel-guided obstacle is detected.

  Specifically, for example, the three-dimensional objects S1 to S15 as shown in FIG. 11 detected by the three-dimensional object detection unit 92 from the reference image T in which the vehicle, the lane, the lane separator, etc. as shown in FIG. On the other hand, the traveling guidance obstacle detecting means 93 calculates the distance in the real space from the left end to the right end of each solid object Sn group, that is, the width of each solid object Sn. In FIGS. 10 and 11, the light and darkness of the black and white striped pattern of the lane separator represented by the three-dimensional objects S <b> 1 to S <b> 5 or the like is shown contrary to the actual situation.

  The traveling guidance obstacle detecting means 93 performs selection based on the size of the three-dimensional object Sn. That is, the three-dimensional object Sn whose width is within a preset threshold value and whose height is within the preset threshold value is selected, and the other three-dimensional object Sn is excluded. .

  In the present embodiment, the width threshold value and the height threshold value of the travel guidance obstacle are provided separately for the case where the travel guidance obstacle is the lane separator shown in FIG. . Since the lane separator is usually thinner than the pylon and has a different height, the respective threshold values are appropriately set so that they can be distinguished.

  Subsequently, the traveling guidance obstacle detecting means 93 performs the sorting based on the luminance pattern for each of the three-dimensional objects Sn selected as corresponding in the sorting based on the size. In the detection of the luminance pattern, as shown in FIG. 12, the traveling guidance obstacle detecting unit 93 offsets the center of the left and right ends of the selected three-dimensional object Sn one pixel downward from the upper end one pixel at a time. The value p1ij is detected, and the difference Δp between the luminance value p1ij of each pixel and the luminance value of the pixel immediately below it is taken.

  Subsequently, the travel guidance obstacle detection means 93 uses a bright portion B with a reflective material for the travel guidance obstacle and a dark portion without a reflective material as a pixel portion where the difference Δp in luminance value indicated by Q in FIG. D is detected as a boundary with D, and average values pbnave and pdnave of the brightness values of each bright portion B and each dark portion D are calculated at pixel portions other than the boundary pixels.

  Then, the distribution of the average luminance value pbnave of each bright part B is obtained for all the bright parts B, and the difference Δpb between the maximum value and the minimum value is calculated. In addition, for all the dark portions D, the distribution of the luminance average value pdnave of each dark portion D is obtained, and the difference Δpd between the maximum value and the minimum value is calculated. Further, the average luminance value pbave of all bright portions B and the average luminance value pdave of all dark portions D are calculated.

  The traveling guidance obstacle detection means 93 has a predetermined difference Δpb between the maximum and minimum luminance average values for each bright portion B and a difference Δpd between the maximum and minimum luminance average values for each dark portion D. If the difference between the average brightness value pbave of all bright parts B and the average brightness value pdave of all dark parts D is equal to or greater than a predetermined specified value, the three-dimensional object Sn becomes a travel-induced obstacle. It is determined that the object has a repetitive pattern of luminance specific to the object. Then, the three-dimensional object Sn having such a luminance pattern is selected as a travel guidance obstacle.

  The traveling guidance obstacle detecting means 93 generally adopts the length in the vertical space of each bright portion B of the three-dimensional object Sn selected as the traveling guidance obstacle based on the distance image as a reflector. If it is significantly different from the length to be generated, the three-dimensional object Sn is excluded from the traveling guidance obstacle.

  The traveling guidance obstacle detecting means 93 detects the three-dimensional object Sn finally sorted and survived as a traveling guidance obstacle.

  Further, the traveling guidance obstacle detecting means 93 is a traveling guidance obstacle as viewed from the arrangement of the detected traveling guidance obstacle Kn among the three-dimensional objects Sn excluded as not corresponding to the traveling guidance obstacle in the selection based on the luminance pattern. The three-dimensional object Sn that is determined to be an object is newly detected as a traveling guidance obstacle.

  In the present embodiment, the travel guidance obstacle detection means 93 is updated and recorded by the position of the solid object Sn detected as the travel guidance obstacle as described above in the real space and the past obstacle update means 94 described later. Based on the arrangement of the past travel-guided obstacle with the position in the real space, it is determined and detected whether or not the farther three-dimensional object Sn is a travel-guide obstacle.

  Specifically, as shown in FIG. 13, the vehicle MC that can be found on the reference image T according to the position of the travel guidance obstacles K1 to K3 detected by the selection based on the luminance pattern and the behavior of the vehicle. A curve C is obtained by applying the least square method to the arrangement of the positions of the past driving guidance obstacles Kus1 to Kus3 that are not found on the reference image T because they have moved to the near side from the nearest position P. It is designed to approximate. In the present embodiment, the curve C is approximated as a quadratic curve, but it is also possible to approximate the line C by a Hough transform or the like, for example.

  Subsequently, the curve C is extended far from the host vehicle MC, and among the three-dimensional objects Sn that are excluded as not corresponding to the travel guidance obstacle by the selection based on the luminance pattern, the curve C is predetermined on the extended curve C or from the curve C. The three-dimensional object Sn within the distance is newly detected as the travel guidance obstacle Kn.

  The travel guidance obstacle detection means 93 is configured to store information and the like of each travel guidance obstacle Kn detected in this manner in a memory and to output it outside the apparatus.

  The past obstacle update means 94 tracks and records past driving guidance obstacles Kus that are no longer found in the reference image T due to the behavior of the host vehicle, and converts the coordinates in the real space into the behavior of the host vehicle. Based on this, the coordinates at the next detection timing are updated.

  For example, the traveling guidance obstacle K1 shown in FIG. 10 or the like is not found in the reference image T when the host vehicle moves forward or turns. However, the coordinates in the real space of the traveling guidance obstacle K1 are detected by the three-dimensional object detection means 92.

  Therefore, in the present embodiment, the past obstacle update means 94 is the traveling guidance obstacle K1 when the host vehicle MC moves forward or turns at the current vehicle speed V and yaw rate γ transmitted from the vehicle speed sensor and the yaw rate sensor. It is calculated that the position of the coordinates of the traveling guidance obstacle that becomes the past traveling guidance obstacle Kus1 that is not found in the reference image T due to the behavior of the traveling guidance obstacle, that is, the own vehicle, is at the next imaging timing. It has become.

  In the present embodiment, the past obstacle update means 94 stores the coordinates of the three travel guidance obstacles as past travel guidance obstacles, and thus newly creates a travel guidance obstacle in the past. When stored as a travel guide obstacle, the record of the past travel guide obstacle Kus3 in the example of FIG. 13 is deleted.

  The past obstacle update means 94 is also configured to calculate and update the coordinates at the next imaging timing based on the current vehicle speed V and the yaw rate γ for the coordinates of other past travel guidance obstacles. When the past travel guidance obstacle Kus1 is newly recorded as described above, the coordinates of the past travel guidance obstacles Kus1 and Kus2 in FIG. 13 are updated as the past travel guidance obstacles Kus2 and Kus3, respectively. The

  The past obstacle update means 94 stores the coordinates of the past travel guidance obstacles Kus1 to Kus3 updated in this way in a memory. It is also possible to configure to output these coordinates outside the apparatus.

  Next, the operation of the travel guidance obstacle detection device 1 according to this embodiment will be described.

  The travel guidance obstacle detection means 93 of the detection means 9 of the travel guidance obstacle detection device 1 detects, for example, the three-dimensional objects S1 to S15 from the reference image T shown in FIG. For the three-dimensional objects S1 to S15, the three-dimensional objects S1 to S5 and the three-dimensional object S14 in which the width and height of the groups of the respective three-dimensional objects Sn are within preset threshold values are selected, and the other three-dimensional objects Sn are selected. exclude.

  Subsequently, the traveling guidance obstacle detecting unit 93 performs the selection of the selected three-dimensional objects S1 to S5 and the three-dimensional object S14 using the luminance pattern as described above, and the three-dimensional object has a constant luminance change in the vertical direction. Solid objects S1 to S3 are detected as travel guidance obstacles K1 to K3, and solid objects S4, S5, and S14 are excluded.

  However, there is a possibility that the excluded three-dimensional objects S4, S5, and S14 are travel guidance obstacles because they are far away from the host vehicle MC, but the luminance pattern is not clearly visible.

  Therefore, the travel guidance obstacle detection means 93 is a past travel guidance obstacle Kus1 whose position is updated based on the arrangement of the detected travel guidance obstacles K1 to K3 and the behavior of the host vehicle by the past obstacle update means 94. Based on the arrangement of .about.Kus3, the shape of the arrangement is approximated by a straight line or a curve, and the three-dimensional objects S4, S5 on the extension line of the straight line or the curve are detected as the traveling guidance obstacles K4, K5.

  The three-dimensional object S14 is not detected as a traveling guidance obstacle because it is far away from the approximated straight line or curve.

  For example, when the three-dimensional object S2 is not detected as a travel guidance obstacle and only the three-dimensional objects S1 and S3 are detected as travel guidance obstacles as a result of selection based on the luminance pattern, the three-dimensional object S2 is detected as the travel guidance obstacle S1. And a solid object existing on or near the approximate straight line or the approximate curve based on the arrangement of S2 and is detected again as the travel guidance obstacle S2.

  As described above, according to the traveling guidance obstacle detection device 1 according to the present embodiment, the three-dimensional object Sn detected in the reference image T is selected based on the size based on the width and the height, and further the luminance is increased. By selecting according to the repetitive pattern, it is possible to accurately detect a traveling guidance obstacle such as a lane separator or a pylon from among three-dimensional objects existing in front of the host vehicle.

  Therefore, a three-dimensional object that is a traveling guidance obstacle can be appropriately detected as a traveling guidance obstacle without misrecognizing it as a vehicle, for example.

  In addition, the three-dimensional object Sn that has been excluded in the detection of the travel-guided obstacle without being detected by the repetition pattern of the luminance because it has been selected by the size selection but is far from the host vehicle is detected. Approximate with the straight line or curve the arrangement of past travel guidance obstacles that have not been found in the reference image T, and detect solid objects on or near the straight line or curve as travel guidance obstacles To do.

  For this reason, it is possible to accurately determine whether or not a three-dimensional object for which a repeated luminance pattern has not been detected is a travel guidance obstacle, and appropriately detect it as a travel guidance obstacle.

  In the present embodiment, a luminance pattern is not detected by linear approximation or curve approximation based on the arrangement of the position of the traveling guidance obstacle Kn detected on the reference image T and the position of the past traveling guidance obstacle Kusn. The new detection of a three-dimensional object as a traveling guidance obstacle was described. However, it is also possible to perform a linear approximation or a curve approximation based only on the arrangement of the travel guidance obstacle Kn detected on the reference image T, and the travel guidance obstacle Kn on the reference image T. Even if no detection is detected, a three-dimensional object in which the luminance pattern on the reference image T is not detected by performing linear approximation or curve approximation based only on the past arrangement of the driving guidance obstacle Kusn is newly detected as a driving guidance obstacle. It is also possible to configure so as to.

[Second Embodiment]
Next, in the following embodiments, various vehicle control devices using the travel guidance obstacle detection device 1 according to the first embodiment will be described.

  In the second embodiment, a vehicle control device will be described as a lane departure prevention device using the travel guidance obstacle detection device 1 according to the first embodiment. As shown in FIG. 14, the vehicle control device 10 according to the present embodiment includes the travel guidance obstacle detection device 1 according to the first embodiment, a control device 11, and an alarm device 12.

  When the control device 11 determines that the host vehicle may deviate from the left or right lane position detected by the traveling guidance obstacle detection device 1, the control device 11 issues an alarm to the connected alarm device 12 from its speaker or the like. The instruction is to be issued. In addition, it is also possible to provide the lane detection means as a device different from the travel guidance obstacle detection device 1 according to the first embodiment.

  The control device 11 also alerts the connected alarm device 12 from its speaker or the like even when the host vehicle approaches the travel guidance obstacle detected by the travel guidance obstacle detection device 1 within a predetermined distance. The instruction is to be issued.

  Furthermore, when the travel guidance obstacle detected by the travel guidance obstacle detection device 1 is in the vicinity of one of the left and right lanes, the control device 11 may advance the timing for issuing an alarm as compared with the case of only the lane. It has become.

  As described above, according to the vehicle control device 10 according to the present embodiment, the driver's vehicle can be detected by reliably detecting a travel guidance obstacle such as a lane separator and issuing an alarm when the host vehicle approaches the vehicle. It is possible to effectively attract attention and prevent lane departure appropriately.

  In addition, it is possible to make the driver's attention faster by issuing a warning earlier than in the case of a lane that does not have a driving guidance obstacle in a lane in which a driving guidance obstacle is set up nearby and lane departure is strongly prohibited. This makes it possible to reliably prevent lane departure and prevent the vehicle from coming into contact with or colliding with a traveling guidance obstacle.

  Note that it is also possible to automatically control various actuators or the like so that the host vehicle is automatically pulled back to the traveling lane instead of or in parallel with issuing an alarm.

[Third Embodiment]
3rd Embodiment demonstrates the control apparatus for vehicles as a tracking assistance apparatus using the driving | running | working guidance obstacle detection apparatus 1 which concerns on the said 1st Embodiment. As shown in FIG. 15, the vehicle control device 20 according to the present embodiment includes the travel guidance obstacle detection device 1 according to the first embodiment and a control device 21. A responding part B including a control system having a steering servo function is connected.

  The control device 21 sets a line on which the host vehicle should travel so that the host vehicle travels in a travel lane that is divided into left and right lane positions detected by the travel guidance obstacle detection device 1. A target point is set in front of a predetermined distance, and an instruction signal is issued to the responding part B to perform follow-up control on the lane.

  Further, the control device 21 issues an instruction signal to the responding part B so that the host vehicle travels along the travel guidance obstacle detected by the travel guidance obstacle detection device 1 and performs follow-up control on the travel guidance obstacle. It is like that.

  Furthermore, when the travel guidance obstacle detected by the travel guidance obstacle detection device 1 is in the vicinity of either the left or right lane, the control device 21 increases the separation distance from the lane compared to the case of only the lane. Thus, the traveling of the host vehicle is controlled so as to travel near the center of the traveling lane.

  As described above, according to the vehicle control device 20 according to the present embodiment, it is possible to reliably detect a travel guidance obstacle such as a lane separator and perform follow-up control so that the host vehicle travels along the obstacle. Even when a lane is not marked on the road surface and only a travel-guided obstacle such as a lane separator is erected, the host vehicle can automatically travel along the lane separation mark.

  In addition, the lane departure is surely prevented by separating the lane from the lane more than the lane where there is a lane that does not have a travel guidance obstacle. Thus, it is possible to accurately prevent the host vehicle from coming into contact with or colliding with the traveling guidance obstacle.

[Fourth Embodiment]
The travel guidance obstacle detection device 1 according to the first embodiment can distinguish and detect the lane separation mark and the pylon by appropriately setting the width threshold and the height threshold of the travel guidance obstacle. it can.

  Therefore, in the control devices 11 and 21 of the vehicle control devices 10 and 20 according to the second and third embodiments, the threshold value is set so as to detect the pylon, and is detected inside or near the lane. When the three-dimensional object is a pylon, the road on which the host vehicle is traveling can be determined to be under construction for road construction or civil engineering work.

  And if the road is under construction, it is assumed that the host vehicle deviates from the travel lane and travels across the lane or changes to the adjacent travel lane. Therefore, in the vehicle control device 10 as the lane departure prevention device according to the second embodiment, when the control device 11 determines that the road on which the host vehicle is traveling is under construction, lane departure avoidance control is performed. Can be configured to stop.

  With this configuration, when the road is under construction and the driver intentionally departs from the lane, the lane departure avoidance control is stopped. It is possible to prevent the running from becoming unstable by being controlled to be pulled back.

  Further, in the vehicle control device 20 as the lane tracking support device according to the third embodiment, the control device 21 responds so that the host vehicle travels along the pylon detected by the travel guidance obstacle detection device 1. An instruction signal is issued to the part B to perform follow-up control on the traveling guidance obstacle. Therefore, for example, when the pylon is placed inside the travel lane, the host vehicle can travel along the lane, and contact and collision with the pylon can be appropriately avoided.

  In the vehicle control device 20 as the lane tracking support device according to the third embodiment, the control device 21 is configured to travel along the pylon detected by the travel guidance obstacle detection device 1. If not, it is preferable that the lane tracking control is stopped. If configured in this way, when the driver tries to depart from the lane so as not to collide with the pylon, the vehicle is controlled so that it is forcibly pulled back to the original travel lane, thereby preventing travel from becoming unstable. It becomes possible to do.

[Fifth Embodiment]
As shown in FIG. 16, the vehicle control device 30 according to the fifth embodiment includes a travel guidance obstacle detection device 1 according to the first embodiment, a control device 31, and a radar as information collection means 32. Device. The vehicle control device 30 according to the present embodiment can be used as, for example, a preceding vehicle detection device for detecting preceding vehicles around the host vehicle.

  The radar device is provided at the tip of the host vehicle. For example, the position and size of a three-dimensional object around the host vehicle are transmitted by transmitting radio waves of 30 GHz to 100 GHz around the host vehicle and receiving radio waves that are reflected and returned. It collects such information. The radar device is configured to transmit transmission / reception data to the control device 31.

  The control device 31 measures the time difference until the radio wave is reflected by the three-dimensional object and returns based on the transmission / reception data transmitted from the radar device, and calculates the relative distance from the host vehicle to the three-dimensional object. ing. Further, from the relative distance distribution state, a portion where the same distance value continues is extracted as one solid object and recorded in a memory (not shown).

  Further, the control device 31 reads out the data of the three-dimensional object extracted last time from the memory, obtains the probability that it is the same as the three-dimensional object extracted this time, and if the probability is equal to or higher than a preset threshold, The data of the three-dimensional object is updated and continuously registered as a three-dimensional object. If there is no corresponding past data, it is registered as a new three-dimensional object.

  Further, the control device 31 includes information such as the position of the traveling guidance obstacle transmitted from the traveling guidance obstacle detection device 1 and information such as the position of the three-dimensional object collected based on transmission / reception data from the radar device. In contrast, when the positions are almost the same and the sizes correspond within a predetermined range, the three-dimensional object collected based on the transmission / reception data from the radar device is recognized as a traveling guidance obstacle, and the three-dimensional object is recognized. It is labeled as a traveling guidance obstacle and recorded in the memory.

  In the present embodiment, the control device 31 excludes a three-dimensional object outside the three-dimensional object recognized as a travel guidance obstacle when viewed from the host vehicle from a control target of control for adjusting the distance from the three-dimensional object. It is like that. That is, when the vehicle control device 30 is used as a preceding vehicle detection device, for example, the three-dimensional object outside the traveling guidance obstacle is not detected as the preceding vehicle, but is deleted from the memory, for example. .

  As described above, according to the vehicle control device 30 according to the present embodiment, the information on the three-dimensional object extracted by the radar device is compared with the information on the travel guidance obstacle detected by the travel guidance obstacle detection device 1. Thus, by recognizing the corresponding three-dimensional object as a travel guidance obstacle, it is possible to reliably prevent the travel guidance obstacle from being erroneously recognized as, for example, a preceding vehicle.

  In addition, it is unlikely that a vehicle outside the traveling guidance obstacle as viewed from the own vehicle will get over the traveling guidance obstacle and enter the traveling lane of the own vehicle. Therefore, as described above, the driving guidance obstacle is identified from among the three-dimensional objects, and the three-dimensional object outside the three-dimensional object is excluded from the control target of the control for adjusting the distance from the three-dimensional object, so that the arithmetic processing for the control is performed. As a result, it is possible to reduce the calculation load of the control device 31, and it is possible to improve the processing speed.

It is a block diagram which shows the structure of the driving | running | working guidance obstacle detection apparatus which concerns on 1st Embodiment. It is a figure which shows an example of a reference | standard image. It is a figure explaining the lane candidate point detected on the horizontal line j. It is a figure which shows the detected lane candidate point. It is a figure which shows the right lane position and the left lane position which were finally detected. It is the figure which plotted the distance of each division of a distance image as a point on real space. It is a figure which shows each group formed by grouping each point of FIG. It is a figure which shows the object and side wall which were detected by labeling each group of FIG. It is a figure which shows the reference | standard image displayed by overlapping the frame line which shows an object or a side wall. It is a figure which shows an example of the reference | standard image by which the lane separator was imaged. It is a figure showing the solid object detected in the reference | standard image of FIG. It is a graph showing the luminance value of each pixel and the pattern of the difference. It is a figure showing the detected driving guidance obstacle, the past driving guidance obstacle, and the curve C. It is a block diagram which shows the structure of the vehicle control apparatus which concerns on 2nd Embodiment. It is a block diagram which shows the structure of the vehicle control apparatus which concerns on 3rd Embodiment. It is a block diagram which shows the structure of the vehicle control apparatus which concerns on 5th Embodiment. (A) is a figure showing the example of a lane separator, (B) is a figure showing the example of a pylon.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Travel guidance obstacle detection apparatus 2 Imaging means 6 Image processing means 9 Detection means 91 Lane detection means 10, 20, 30 Vehicle control devices 11, 21, 31 Control device 12 Alarm device 32 Information collection means p1ij Luminance value MC Own vehicle T Reference image Zij Distance Sn Solid object Kn Traveling guidance obstacle Kusn Past traveling guidance obstacle C Curves LR, LL Lane position

Claims (13)

Imaging means for imaging a landscape including a road ahead of the host vehicle and outputting a pair of images having a luminance value for each pixel;
Image processing means for calculating a distance in real space for each pixel of at least one image based on the pair of captured images;
Detecting means for detecting a three-dimensional object from the one image based on the information on the luminance value and the distance, and calculating a size of the three-dimensional object in real space;
When the size of the three-dimensional object in real space is within a preset threshold and the luminance change in the vertical direction of the three-dimensional object detected in the one image has a constant pattern A three-dimensional object is detected as a traveling guidance obstacle.   The detecting means calculates the position of the three-dimensional object in real space and approximates the arrangement of a plurality of three-dimensional objects detected as traveling guidance obstacles in the one image by straight lines or curves, and is obtained by approximation. 2. The vehicle according to claim 1, wherein a straight line or a curved line is extended to a region far from the host vehicle, and the detected three-dimensional object on the extended straight line or the curved line is detected as a traveling guidance obstacle. Traveling guidance obstacle detection device.   The detection means calculates the position of the three-dimensional object in real space, and based on the behavior of the host vehicle, determines the position of a past driving guidance obstacle that is no longer found in the one image due to the behavior of the host vehicle. The position of the past travel guidance obstacle and the position of the three-dimensional object detected as the travel guidance obstacle in the one image are approximated by a straight line or curve, and obtained by approximation. The extended straight line or curve is extended to an area far from the host vehicle, and the detected three-dimensional object on or near the extended straight line or the curve is detected as a travel guidance obstacle. The travel guidance obstacle detection apparatus according to 1. The travel guidance obstacle detection device according to any one of claims 1 to 3,
Information collecting means for collecting information about a three-dimensional object around the host vehicle by means other than the imaging means;
Control for recognizing the three-dimensional object as a traveling guidance obstacle when the information on the three-dimensional object collected by the information collecting means corresponds to the information on the traveling guidance obstacle detected by the traveling guidance obstacle detection device. A vehicle control device comprising the device.   The control device excludes a three-dimensional object outside the three-dimensional object recognized as the travel guidance obstacle when viewed from the host vehicle from a control target of control for adjusting a distance from the three-dimensional object. Item 5. The vehicle control device according to Item 4. The travel guidance obstacle detection device according to any one of claims 1 to 3,
An alarm device for issuing an alarm to the driver;
A control apparatus for a vehicle, comprising: a control device that causes the alarm device to output an alarm when the host vehicle is approaching a three-dimensional object recognized as the travel guidance obstacle. Lane detection means for detecting the lane on the left and right of the host vehicle,
The control device issues an alarm when the host vehicle is approaching the lane detected by the lane detecting means, and a three-dimensional object recognized as the travel guiding obstacle is detected by the lane detecting means. The vehicle control device according to claim 6, wherein when the vehicle is in the vicinity, the timing for issuing an alarm is advanced as compared with the case of the lane alone. The travel guidance obstacle detection device according to any one of claims 1 to 3,
A control device for a vehicle, comprising: a control device that controls the travel of the host vehicle so as to travel along a three-dimensional object recognized as the travel guidance obstacle. Lane detection means for detecting the lane on the left and right of the host vehicle,
The control device controls the traveling of the host vehicle so that the host vehicle travels along the lane detected by the lane detecting unit, and detects the three-dimensional object recognized as the traveling guidance obstacle by the lane detecting unit. 9. The traveling of the host vehicle is controlled so that when the vehicle is in the vicinity of the lane, the vehicle is traveled with a larger distance from the lane than when only the lane is detected. Vehicle control device. The travel guidance obstacle detection device according to any one of claims 1 to 3,
Lane detection means for detecting lanes on the left and right of the host vehicle;
When the solid object detected inside the lane detected by the lane detection means or in the vicinity thereof and recognized as the traveling guidance obstacle is a pylon, Has a control device for determining that the road on which the host vehicle is traveling is under construction.   The vehicle control device according to claim 10, wherein the control device stops lane departure avoidance control when it is determined that a road on which the host vehicle is traveling is under construction.   The vehicle control device according to claim 10, wherein the control device stops the lane tracking control when it is determined that the road on which the host vehicle is traveling is under construction.   11. The control device according to claim 10, wherein when the road on which the host vehicle is traveling is determined to be under construction, the control device performs follow-up control so that the host vehicle travels along the pylon. Vehicle control device.

Images