Vehicle control system

Abstract

To provide a vehicle control system that can suppress an erroneous detection of the position of a specified target.SOLUTION: A vehicle control system comprises: a projection device for projecting a predefined shape on the road surface surrounding an own vehicle; a target recognition device for recognizing a specified target OB existing around the own vehicle on the basis of a peripheral image acquired by taking a picture of the peripheral region of the own vehicle, and for outputting information about the relative position between the own vehicle and the specified target OB; and a processor for controlling the projection device and the target recognition device. The processor performs a predetermined correction processing for correcting the relative position acquired from the position information, when the target recognition image, which is the region recognized as the specified target in the peripheral image, overlaps the shape image projected on the road surface by the projection device.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a vehicle control system including a projection device that projects a predetermined figure onto a road surface around a host vehicle, and a target recognition device that detects the position of a specific target (distance between the host vehicle and the specific target) located around the host vehicle based on an image obtained by photographing the surrounding area of the host vehicle.

Background Art

[0002] A projection device that projects a predetermined figure onto a road surface around a host vehicle has been proposed (see, for example, Patent Document 1 below).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0004] By the way, a target recognition device that analyzes a peripheral image obtained by photographing the peripheral area of a host vehicle (based on learned data), recognizes a specific target (for example, a pedestrian), and acquires the position of the target (distance between the host vehicle and the specific target) is well known. When a specific target enters within the figure projected onto the road surface, or when the specific target is located near the figure, the beam (direct light or reflected light) of the projection device irradiates a part of the specific target, so that in the peripheral image, a part of the image of the specific target may become unclear. In this case, in the peripheral image, the accuracy of the area recognized as a specific target by the target recognition device is low, and the accuracy (precision) of the position information obtained based on the coordinates of the area is low.

[0005] One of the objects of the present invention is to provide a vehicle control system including a projection device that projects a predetermined figure onto a road surface around a host vehicle, and an object recognition device that detects the position (distance between the host vehicle and the specific object) of a specific object located in the area based on an image of the area around the host vehicle, the vehicle control system being capable of suppressing a decrease in the detection accuracy of the position of the specific object.

[0006] To solve the above problems, a vehicle control system (1) of the present invention includes a projection device (20) that projects a predetermined figure onto a road surface around the host vehicle, an object recognition device (30) that recognizes a specific object located around the host vehicle based on a peripheral image obtained by photographing the area around the host vehicle and outputs position information, which is information regarding the relative position between the host vehicle and the specific object, and a processor (10) that controls the projection device and the object recognition device. The vehicle control system is configured as follows. When an object recognition image (R), which is an image of an area recognized as the specific object in the peripheral image, and a figure image (PTN) projected onto the road surface by the projection device overlap, the processor executes a predetermined correction process for correcting the relative position obtained from the position information.

[0007] The vehicle control system according to the present invention includes a projection device that projects a predetermined figure onto a road surface around the host vehicle, and an object recognition device that obtains position information representing the relative position between the host vehicle and a specific object based on a peripheral image. Here, when the object recognition image (an area recognized as a specific object in the peripheral image) and the figure image overlap, the accuracy of the position information may be low. According to the vehicle control system of the present invention, when the two images overlap, the relative position, which is the position of the specific object with respect to the host vehicle obtained from the position information, is corrected by a predetermined correction process. As a result, a decrease in the detection accuracy of the position of the specific object with respect to the host vehicle is suppressed.

[0008] In a vehicle control system according to an aspect of the present invention, A position deviation map (M1) in which a deviation amount between a first position (ΔD1ave) and a second position (ΔD2ave) respectively obtained from the position information output from the object recognition device when the positional relationship between the host vehicle and the specific object target is the same, the first position being the position of the specific object target with respect to the host vehicle obtained from the position information output when the figure image overlaps the object recognition image in a first state, and the second position being the position of the specific object target with respect to the host vehicle obtained from the position information output when the figure image does not overlap the object recognition image in a second state, is defined. The correction process includes a process of correcting the first position (ΔD1ave) obtained when in the first state, based on the position deviation map.

[0009] According to this, in the first state, the processor can relatively easily correct the position of the specific object target with respect to the host vehicle.

[0010] In a vehicle control system according to another aspect of the present invention, The position deviation map includes a plurality of position deviation tables selected according to at least one of the image size of the object recognition image, the luminance of the peripheral image, and the first position.

[0011] The accuracy of the position information is affected by the luminance of the peripheral image, the image size of the object recognition image, and the first position. In particular, in the first state, the influence of these conditions on the accuracy of the position information is large. According to the vehicle control system according to this aspect, the position of the specific object target with respect to the host vehicle can be corrected according to at least one of these conditions.

[0012] In a vehicle control system according to another aspect of the present invention, The processor acquires the first position (ΔD1ave), the luminance (BRave) of the peripheral image, and the image size (Have) of the object recognition image. The position deviation map includes a plurality of position-specific tables (TD1, TD2, ···, TD5) selected according to the first position. Each position-specific table includes a plurality of brightness-specific tables (TBR1, TBR2, TBR3) selected according to the brightness of the peripheral image, Each of the brightness-based tables includes size-based tables (TH1, TH2, . . . , TH6) in which a plurality of deviation amounts selected according to the image size are defined.

[0013] According to the vehicle control system of this aspect, the position of the specific object relative to the host vehicle can be corrected according to the first position, the brightness of the peripheral image, and the image size of the specific object.

[0014] In another aspect of the present invention, there is provided a vehicle control system, The size-specific table defines the relationship between the image size and the deviation amount so that the larger the image size of the target recognition image, the smaller the deviation amount.

[0015] In another aspect of the present invention, there is provided a vehicle control system, the peripheral image is an image obtained by photographing a view in front of the host vehicle, The target recognition device applies the surrounding image to a pre-trained deep neural network to identify the specific target, and obtains the distance between the vehicle and the specific target in the fore-and-aft direction of the vehicle as the position information based on the coordinates of the bottom edge of the area of the surrounding image that is recognized as the specific target (target recognition image).

[0016] In another aspect of the present invention, there is provided a vehicle control system, The target recognition image is a rectangular image, The processor executes the correction process when the graphic image overlaps the lower end of the target recognition image.

[0017] When the lower end of the object recognition image overlaps with the graphic image, the lower end of the object recognition image becomes unclear. Therefore, the accuracy of the position information output from the object recognition device is likely to be low. For example, the distance between the host vehicle and the specific object may be larger than the actual distance. According to the vehicle control system according to this aspect, when the lower end of the object recognition image overlaps with the graphic image, the distance (the distance between the host vehicle and the specific object) obtained based on the image is corrected.

Brief Description of the Drawings

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Embodiments for Carrying Out the Invention

[0019] (Schematic) As shown in FIG. 1, a vehicle control system 1 according to an embodiment of the present invention is applied to a vehicle V (hereinafter referred to as the "host vehicle") having an automatic driving function. In addition, the vehicle control system 1 has a first notification function of projecting a predetermined pattern graphic on the road surface in front of the host vehicle and providing predetermined information to others located around the host vehicle. The vehicle control system 1 has a second notification function of providing predetermined information to the driver of the host vehicle when the risk of contact between the host vehicle and a specific object OB is high based on an image obtained by photographing the front area of the host vehicle in a state where the automatic driving function is disabled.

[0020] (Specific configuration) As shown in FIG. 1, the vehicle control system 1 includes an ECU 10, a projection device 20, an object recognition device 30, and a notification device 40.

[0021] The ECU 10 includes a microcomputer including a CPU 10a, a ROM 10b (rewritable nonvolatile memory), a RAM 10c, a timer 10d, and the like. The CPU realizes various functions by executing a program (instruction) stored in the ROM. The ECU 10 is connected to the ECUs of other devices via a CAN (Controller Area Network).

[0022] The projection device 20 irradiates a beam representing a pattern figure corresponding to a command acquired from the ECU 10 onto the road surface in front of the host vehicle (diagonally right front and / or diagonally left front), and projects the pattern figure onto the road surface.

[0023] The object recognition device 30 includes an imaging device. The imaging device incorporates, for example, a CCD. The imaging device is installed at the front of the host vehicle. The imaging device is directed forward of the host vehicle. The imaging device captures the foreground of the host vehicle at a predetermined frame rate and acquires image data representing the foreground image PIC. The object recognition device 30 further includes an image analysis device. The image analysis device acquires the image data from the imaging device and obtains the brightness BR (average value of the brightness of all pixels) of the foreground image PIC. Further, the image analysis device analyzes the image data (applies it to a pre-trained deep neural network DNN (=Deep Neural Network)) to identify the image of a specific object OB (for example, a pedestrian) within the foreground image PIC and the image of the pattern graphic projected onto the road surface by the projection device 20 (pattern graphic image PTN) (see FIG. 2). Based on the vertical coordinate Y of the lower end line L1 of the image (object recognition image) of the region (rectangular region R) recognized as the specific object OB in the foreground image PIC, the image analysis device calculates the longitudinal distance ΔD between the host vehicle and the specific object OB. Specifically, the image analysis device obtains the distance ΔD by referring to a map (not shown) that defines the relationship between the vertical coordinate Y and the distance ΔD. The map is designed such that the smaller the vertical coordinate Y (the closer the rectangular region R is to the lower end of the foreground image PIC), the smaller the distance ΔD. The distance ΔD corresponds to information (position information) regarding the relative position between the host vehicle and the specific object OB. Further, the image analysis device obtains the size (vertical size H) of the rectangular region R. The vertical size H corresponds to the image size of the object recognition image. The image analysis device provides these calculation results (brightness BR, vertical size H, and distance ΔD) to the ECU 10. Further, the image analysis device determines whether or not the lower end line L1 of the rectangular region R overlaps the pattern graphic image PTN in the foreground image PIC. The image analysis device provides the determination result to the ECU 10.

[0024] The notification device 40 includes an image display device and an acoustic device. The image display device is arranged, for example, on the instrument panel (near the speed display device). The image display device displays an image according to a command obtained from the ECU 10. The acoustic device reproduces a sound according to a command obtained from the ECU 10.

[0025] (First notification function) When a predetermined condition is satisfied, the ECU 10 causes the projection device 20 to project a predetermined pattern graphic onto the road surface. For example, when the host vehicle makes a left turn (or a right turn) (when the direction indicator on the left side (right side) of the host vehicle is operating (flashing)), the ECU 10 causes the projection device 20 to project an arrow pointing left (right) onto the road surface diagonally in front of the left (right) of the host vehicle. Thereby, the traveling direction of the host vehicle is notified to pedestrians and drivers of other vehicles located around the host vehicle.

[0026] (Second notification function) The ECU 10 sequentially acquires the distance ΔD from the target recognition device 30. The ECU 10 calculates an average distance ΔDave, which is an average value of the distances ΔD corresponding to a plurality of consecutive frames. When the average distance ΔDave is equal to or less than a threshold value ΔDth, the ECU 10 transmits a command to display a predetermined image (icon) on the image display device of the notification device 40 so that information indicating that there is a high risk that the host vehicle will contact the specific target OB is provided to the driver of the host vehicle, and at the same time, transmits a command to reproduce a predetermined sound (beep sound) from the acoustic device of the notification device 40.

[0027] Here, when the specific target OB enters the pattern graphic projected on the road surface, or when the specific target OB is located in the vicinity of the pattern graphic, a part of the beam (direct light or reflected light) of the projection device 20 irradiates a part of the specific target OB, so that in the foreground image PIC, a part of the image of the specific target OB may become unclear. In this case, in the foreground image PIC, the accuracy of the area (rectangular area R) recognized as the specific target OB by the image analysis device is low, and the accuracy (accuracy) of the distance ΔD obtained based on the coordinates of the lower end line L1 of the rectangular area becomes low. Specifically, the distance ΔD obtained in a state where the lower end line L1 of the rectangular area R overlaps the pattern graphic image PTN (first state) is larger than the distance ΔD obtained in a state where the pattern graphic is not projected on the road surface or the two do not overlap (second state). (Need to confirm if it is correct)

[0028] Also, when the specific object target OB is relatively far from the host vehicle, the image of the specific object target OB in the foreground image PIC becomes unclear, so the accuracy of the distance ΔD decreases. Also, the smaller (darker) the brightness BR (ambient brightness) of the foreground image PIC, the more unclear the image of the specific object target OB becomes, so the accuracy of the distance ΔD decreases. Also, the smaller the size (vertical size H of the rectangular region R) of the specific object target OB in the foreground image PIC, the more unclear (lower resolution) the image of the specific object target OB becomes, so the accuracy of the distance ΔD decreases. Thus, the actual position, brightness BR, and vertical size H of the specific object target OB affect the detection accuracy of the distance ΔD, but the degree of influence in the first state is greater than that in the second state.

[0029] Therefore, the ECU 10 sequentially acquires from the target recognition device 30 the determination result as to whether or not the lower end line L1 of the rectangular region R overlaps with the pattern graphic image PTN. When the lower end line L1 and the pattern graphic image PTN overlap, the ECU 10 corrects the average distance ΔDave based on the offset value OFS obtained from the map M1 (position deviation map) as described below.

[0030] As shown in FIG. 3, map M1 is a database that defines the relationship between distance ΔD (distance level), luminance BR (luminance level), and vertical size H (vertical size level), and offset value OFS. In map M1, the distance ΔD is classified into multiple levels (for example, 5 levels (distance level 1 (short) to distance level 5 (long))). Also, in map M1, the luminance BR is classified into multiple levels (for example, 3 levels (luminance level 1 (bright) to luminance level 3 (dark))). Further, the vertical size H is classified into multiple levels (for example, 6 levels (vertical size level 1 (large) to vertical size level 6 (small))). Map M1 is composed of a table that defines the relationship between each level of distance ΔD, luminance BR, and vertical size H, and offset value OFS. Specifically, map M1 includes tables TD1 to TD5 corresponding to distance levels 1 to 5. These tables TD1 to TD5 correspond to position-specific tables. Also, each table TDn (n = 1, 2,..., 5) is composed of tables TBR1, TBR2, and TBR3 corresponding to luminance levels 1 to 3. These tables TBR1 to TBR3 correspond to luminance-specific tables. Furthermore, each table TBRn (n = 1, 2, 3) is composed of vertical size tables THm (m = 1, 2,..., 6) that show the relationship between vertical size levels 1 to 6 and offset value OFS. These tables TH1 to TH6 correspond to size-specific tables.

[0031] Each offset value OFS is determined by performing a predetermined calibration process using a calibration device (computer) and six types of mock-ups TS1 to TS6 (models of specific object OB) with different heights at the design stage of the host vehicle (or at the time of factory shipment). Note that these six types of mock-ups TS1 to TS6 correspond to vertical size levels 1 to 6. Hereinafter, the procedure of the calibration process will be described.

[0032] First, a test vehicle equipped with the vehicle control system 1 is placed in a predetermined test room. Next, a pattern graphic is projected onto the floor of the test room by the projection device 20. Next, a dummy object TS1 corresponding to vertical size level 1 is placed at a predetermined position within the pattern graphic projected onto the road surface, at point P1 corresponding to distance level 1. In this state, in the foreground image PIC, the bottom line L1 of the rectangular area R and the pattern graphic image PTN overlap. Next, the brightness of the lighting in the test room is adjusted to match a predetermined brightness corresponding to luminance level 1.

[0033] Next, the calibration device sequentially acquires the brightness BR of the foreground image PIC, the vertical size H of the rectangular region R, and the distance ΔD from the target object recognition device 30. The calibration device calculates the average values of a predetermined number of distances ΔD, brightness BR, and vertical sizes H acquired from the target object recognition device 30, and stores the calculation results (average distance ΔD1ave, average brightness BRave, and average vertical size Have). Next, the operation of the projection device 20 is stopped so that the pattern graphic is not projected onto the road surface. In this state, the calibration device sequentially acquires the distances ΔD from the target object recognition device 30, calculates their average value (average distance ΔD2ave), and stores the calculation result. Next, the calibration device acquires the deviation between the average distance ΔD1ave and the average distance ΔD2ave as an offset value OFS (see FIG. 4). The calibration device then associates the offset value OFS with the average distance ΔD1ave, average brightness BRave, and average vertical size Have. In this way, the offset value OFS for distance level 1, brightness level 1, and vertical size level 1 is determined. The average distance ΔD1ave is the representative value d1 for distance level 1. The average brightness BRave is the representative value br1 for brightness level 1. The average vertical size Have is the representative value h1 for vertical size level 1. The average distance ΔD1ave corresponds to the first position, and the average distance ΔD2ave corresponds to the second distance. The offset value OFS corresponds to the deviation amount between the first position and the second position.

[0034] Next, instead of the dummy body TS1, a dummy body TS2 corresponding to the vertical size level 2 is placed at position P1. Note that the brightness of the lighting in the laboratory is maintained at the brightness corresponding to the luminance level 1. Under this test environment, in the same procedure as the above procedure, the average distance ΔD1ave, the average distance ΔD2ave, etc. are obtained. Next, the calibration device obtains the deviation between the average distance ΔD1ave and the average distance ΔD2ave as the offset value OFS. Then, the calibration device associates the offset value OFS with the average distance ΔD1ave, the average luminance BRave, and the average vertical size Have. In this way, the offset value OFS corresponding to the distance level 1, the luminance level 1, and the vertical size level 2 is determined. Note that the average vertical size Have is the representative value h2 of the vertical size level 2.

[0035] Next, without changing the brightness of the lighting in the laboratory, dummy bodies TS3, TS4, TS5, and TS6 are sequentially placed at position P1, and in the same procedure as the above procedure, the offset values OFS corresponding to the distance level 1, the distance level 1, and the vertical size level m (m = 3, 4, 5, 6) are sequentially obtained.

[0036] Next, the brightness of the lighting in the laboratory is adjusted to a predetermined brightness corresponding to the luminance level 2. Then, dummy bodies TS1 to TS6 are sequentially placed at position P1, and in the same procedure as the above procedure, the offset values OFS corresponding to the distance level 1, the luminance level 2, and the vertical size level m (m = 1, 2, ···, 6) are sequentially obtained. Next, the brightness of the lighting in the laboratory is adjusted to a predetermined brightness corresponding to the luminance level 3. Then, dummy bodies TS1 to TS6 are sequentially placed at position P1, and in the same procedure as the above procedure, the offset values OFS corresponding to the distance level 1, the luminance level 3, and the vertical size level m (m = 1, 2, ···, 6) are sequentially obtained.

[0037] Next, the brightness of the laboratory lighting is readjusted to a predetermined brightness corresponding to luminance level 1. Then, the mock-ups TS1 to TS6 are sequentially arranged at position P2 corresponding to distance level 2, and in the same procedure as the above procedure, offset values OFS corresponding to distance level 2, luminance level 1, and vertical size level m (m = 1, 2, ···, 6) are sequentially obtained.

[0038] Thereafter, offset values OFS corresponding to other test environments (other combinations of distance level, luminance level, and vertical size level) are obtained in the same procedure as the above procedure.

[0039] In each luminance-specific table TBRa (a = 1, 2, 3) of the map M1 constructed by the above procedure, the offset value OFS of the vertical size level m (m = 1, 2, ···) is smaller than the offset value OFS of the vertical size level n (m < n). Also, the offset value OFS of the vertical size level m in the luminance-specific table TBRa of the distance table (position-specific table) TDx is less than or equal to the offset value OFS of the vertical size level m in the luminance-specific table TBRb (b > a) of the same distance table TDx. Also, the offset value OFS of the vertical size level m in the luminance-specific table TBRa of the distance table TDi (i = 1, 2, ···) is less than or equal to the offset value OFS of the vertical size level m in the luminance-specific table TBRa of the distance table TDj (j > i). This map M1 is written into the ROM10b during the production of the vehicle V.

[0040] When the target recognition device 30 is activated, the ECU 10 sequentially acquires the distance ΔD from the target recognition device 30. Further, when a pattern figure is projected onto the road surface by the projection device 20, the ECU 10 sequentially acquires from the target recognition device 30 the determination result regarding the overlap between the lower end line L1 of the rectangular region R in the foreground image PIC and the pattern figure image PTN. When the ECU 10 acquires a determination result indicating that the lower end line L1 and the pattern figure image PTN overlap, in addition to the distance ΔD, the ECU 10 sequentially acquires the luminance BR and the vertical size H from the target recognition device 30. The ECU 10 calculates the average distance ΔDave, the average luminance BRave, and the average vertical size Have, which are the average values of the distance ΔD, the luminance BR, and the vertical size H corresponding to a predetermined number of consecutive frames. The ECU 10 identifies the distance level among distance levels 1, 2, ···, 5 whose representative value is closest to the current average distance ΔDave. The ECU 10 identifies the luminance level among luminance levels 1, 2, ···, 3 whose representative value is closest to the current average luminance BRave. Also, the ECU 10 identifies the vertical size level among vertical size levels 1, 2, ···, 6 whose representative value is closest to the current value Have. The ECU 10 acquires the offset value OFS corresponding to the identified (selected) distance level, luminance level, and vertical size level from the map M1. When the corrected average distance ΔDave obtained by subtracting the offset value OFS from the average distance ΔDave is equal to or less than the threshold value ΔDth, the ECU 10 executes the second notification process.

[0041] On the other hand, when the ECU 10 does not acquire a determination result indicating that the lower end line L1 and the pattern figure image PTN overlap in the foreground image PIC, the ECU 10 does not correct the average distance ΔDave. That is, when the average distance ΔD, which is the average value of the distances ΔD sequentially acquired from the target recognition device 30, is equal to or less than the threshold value ΔDth, the ECU 10 executes the second notification process.

[0042] Next, referring to FIG. 5, a program PR1 executed by the CPU 10a (hereinafter simply referred to as "CPU") of the ECU 10 to implement the correction function of the average distance ΔDave will be described.

[0043] (Program PR1) When the pattern figure is projected onto the road surface by the projection device 20, the CPU starts executing the program PR1 at a predetermined cycle. The CPU starts executing the program PR1 from step 100 and proceeds to step 101 for processing.

[0044] At step 101, the CPU obtains from the target recognition device 30 a determination result regarding the overlap between the lower end line L0 of the rectangular region R and the pattern figure image PTN. When the CPU obtains a determination result indicating that the lower end line L1 and the pattern figure image PTN overlap (101: Yes), the CPU proceeds to step 102 for processing. On the other hand, when the CPU does not obtain a determination result indicating that the lower end line L1 and the pattern figure image PTN overlap (101: No), the CPU proceeds to step 105 for processing.

[0045] At step 102, the CPU obtains the distance ΔD, the luminance BR, and the vertical size H from the target recognition device 30. Each time the CPU obtains this information, it stores this information in the RAM 10c (ring buffer). As a result, the RAM 10c stores the distance ΔD, the luminance BR, and the vertical size H (time series data) corresponding to a predetermined number of frames (foreground image PIC). Based on this time series data, the CPU calculates the average distance ΔDave, the average luminance BRave, and the average vertical size Have. Next, the CPU proceeds to step 103 for processing.

[0046] In step 103, the CPU refers to map M1 to obtain an offset value OFS. That is, the CPU specifies the distance level, brightness level, and vertical size level of the average distance ΔDave, average brightness BRave, and average vertical size Have. Then, the CPU obtains an offset value OFS corresponding to each specified level from map M1. Next, the CPU proceeds to step 104.

[0047] In step 104, the CPU subtracts the offset value OFS from the average distance ΔDave and uses the result as the corrected average distance ΔDave. Then, the CPU proceeds to step 106, where it ends the execution of program PR1 (the correction process for the average distance ΔDave).

[0048] When the CPU proceeds from step 101 to step 105, it acquires the distance ΔD from the target object recognition device 30 and stores it in the RAM 10c. Then, the CPU calculates the average distance ΔDave based on the time-series data of the distance ΔD stored in the RAM 10c. Next, the CPU proceeds to step 106 without correcting the average distance ΔDave, and ends execution of the program PR1 at step 106.

[0049] (effect) As described above, the vehicle control system 1 includes a projection device 20 that projects a predetermined graphic onto the road surface ahead of the host vehicle, and a target recognition device 30 that acquires the distance ΔD as position information representing the relative position between the host vehicle and a specific target OB based on the foreground image PIC. Here, if the bottom line L1 of the rectangular area R overlaps with the patterned graphic image PTN in the foreground image PIC, the accuracy of the position information may be low. According to the vehicle control system 1, if the two images overlap, the average distance ΔDave is corrected by a predetermined correction process. This prevents a decrease in the detection accuracy of the distance ΔD between the specific target OB and the host vehicle.

[0050] The present invention is not limited to the above-described embodiments, and as described below, various modifications can be adopted within the scope of the present invention.

[0051] <Modification Example 1> In the above embodiment, in map M1, the distance ΔD is classified into distance levels 1 to 5, but the number of distance levels (number of classification levels) may be changed. For example, in map M1, the distance ΔD may be classified into more types of levels than in the above embodiment. Also, in map M1, the number of luminance levels and vertical size levels may be changed.

[0052] <Modification Example 2> In the above embodiment, when a predetermined condition is satisfied, ECU10 causes the projection device 20 to project a graphic indicating the traveling direction of the host vehicle onto the road surface. Instead of this, when a predetermined condition is satisfied, ECU10 may cause the projection device 20 to project a pattern graphic for detecting the unevenness of the road surface onto the road surface. In this case, the target recognition device 30 detects the unevenness of the road surface based on the distortion of the pattern graphic image PTN in the foreground image PIC.

[0053] <Modification Example 3> In the above embodiment, when the average distance ΔD is equal to or less than the threshold value ΔDth, ECU10 executes the second notification process. Instead of this, or in addition to this, an automatic braking process for automatically braking the host vehicle may be executed.

[0054] <Modification Example 4> In the above embodiment, the projection device 20 is directed forward of the host vehicle, and the imaging device of the target recognition device 30 is directed forward of the host vehicle. Instead of this, these devices may be directed rearward of the host vehicle. That is, the projection device 20 may project a predetermined pattern graphic onto the road surface behind the host vehicle. And the target recognition device 30 may be able to recognize a specific target located behind the host vehicle.

Explanation of Reference Numerals

[0055] 1…Vehicle control system, 10…ECU, 20…Projection device, 30…Target detection device, 40…Notification device

Claims

1. A projection device that projects a predetermined figure onto the road surface around the host vehicle, An object recognition device that recognizes a specific object located around the host vehicle based on a peripheral image obtained by photographing the peripheral area of the host vehicle and outputs position information, which is information regarding the relative position between the host vehicle and the specific object, A processor that controls the projection device and the object recognition device, A vehicle control system comprising: When the figure image projected onto the road surface by the projection device overlaps with the object recognition image, which is an image of the area recognized as the specific object in the peripheral image, the processor executes a predetermined correction process for correcting the relative position obtained from the position information. The vehicle control system is configured as described above.

2. In the vehicle control system according to Claim 1, A first position and a second position respectively obtained from the position information output from the object recognition device when the positional relationship between the host vehicle and the specific object is the same. The first position is the position of the specific object with respect to the host vehicle obtained from the position information output when the figure image overlaps the object recognition image in a first state, and the second position is the position of the specific object with respect to the host vehicle obtained from the position information output when the figure image does not overlap the object recognition image in a second state. The vehicle control system includes a position deviation map in which the deviation amount is defined. The correction process includes a process of correcting the first position obtained in the first state based on the position deviation map. The vehicle control system.

3. In the vehicle control system according to Claim 2, The position deviation map includes a plurality of position deviation tables selected according to at least one of the image size of the object recognition image, the luminance of the peripheral image, and the first position. The vehicle control system.

4. In the vehicle control system according to Claim 2, The processor acquires the first position, the luminance of the peripheral image, and the image size of the object recognition image, The position deviation map includes a plurality of position-specific tables selected according to the first position, Each position-specific table includes a plurality of luminance-specific tables selected according to the luminance of the peripheral image, Each luminance-specific table includes a plurality of size-specific tables in which the deviation amount is defined, selected according to the image size. The vehicle control system.

5. In the vehicle control system according to any one of claims 1 to 4, the target recognition image is a rectangular image, the vehicle control system in which the processor executes the correction process when the graphic image overlaps with the lower end line of the target recognition image.

Images