JP2017052471A - Vehicle parking block recognizing device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To set a target parking block at a correct position even in a case where a part of a parking block line is not detected because of stain or blurring.SOLUTION: A parking block detection part 46 detects a parking block from an image that has been taken by an imaging part 20. A target parking block setting part 48 sets a target parking block from among detected parking blocks. A parking block correction part 50 corrects a position of the target parking block that has been set so that a proper target parking block is set.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a vehicular parking area recognizing device that detects a parking area indicating a parking area from an image taken by an in-vehicle camera.

  Recently, when a vehicle is parked at a predetermined parking position, a vehicle parking assistance device that automatically detects a target parking section and automatically parks the vehicle has been put into practical use.

  In such a parking assist device for a vehicle, a parking area that can be parked is detected from an image obtained by photographing the periphery of the vehicle, and a movement route for moving the vehicle toward the detected parking area is calculated. Then, the vehicle is automatically driven along the calculated movement route to perform a parking operation (for example, Patent Document 1).

Japanese Patent Laying-Open No. 2015-74254

  However, in the parking assistance device described in Patent Document 1, the target parking area is set with reference to the detected parking line closer to the vehicle among the detected parking lines. It was. Therefore, for example, when the parking lot lines on both the left and right sides of the parking lot are both dirty and difficult to see, the target parking lot is set based on the detection result of the parking lot line that has become dirty and difficult to see. There is a problem that is set in a position deeper than actual.

  For example, as shown in FIG. 23 (a), when a plurality of parking lot lines K1, K2, K3, K4 are detected in the vicinity of the vehicle 100, the paint on the front end portion of the parking lot lines K2, K3 on the vehicle 100 side is painted. When it is faded and thinned, there is a possibility that the parking section is detected as being in the back position. Therefore, when the detected parking area is set as the target parking area PF as it is, the target parking area is set at a position deeper than the actual parking area as shown in FIG. In such a case, since the length of the target parking section in the depth direction is insufficient, it may be determined that the vehicle 100 cannot be parked.

  The present invention has been made in view of the above problems, and an object of the present invention is to set a target parking lot at a correct position even when a part of the parking lot line is not detected due to dirt or blur. .

  In order to solve the above-described problem, a vehicle parking area recognition device according to the present invention is provided in a vehicle, and includes at least one imaging unit that captures an image around the vehicle, and an image captured by the imaging unit. A parking area detection unit for detecting a parking area, a target parking area setting unit for setting a target parking area for parking the vehicle based on a detection result of the parking area, and the target in the image A parking area correction unit that corrects the position of the parking area.

  According to the vehicle parking area recognizing device according to the present invention configured as described above, the target parking area setting unit sets the target parking area from among the parking areas detected by the parking area detecting unit because of the configuration described above. Then, since the parking area correction unit corrects the position of the set target parking area, even when the boundary line of the parking area is dirty and difficult to see, it is necessary to set an appropriate target parking area. Can do.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a top view of a vehicle provided with a vehicle parking area recognition device according to a first embodiment of the present invention. 1 is a hardware block diagram illustrating a hardware configuration of a vehicle parking area recognition device according to a first embodiment. It is a functional block diagram which shows the function structure of the parking area recognition apparatus for vehicles which concerns on Example 1. FIG. 3 is a flowchart illustrating a flow of the entire process performed in the first embodiment. It is a figure which shows the example of the image imaged with each camera installed in the vehicle. FIG. 5B is a diagram showing an example in which each image shown in FIG. 5A is converted into a bird's-eye view image, and each bird's-eye view image is further synthesized to generate one bird's-eye view synthesized image. 6 is a flowchart illustrating a flow of white line detection processing in the first embodiment. It is a flowchart which shows the flow of the parking area detection process in Example 1. FIG. It is a figure which shows an example of a parking area detection result. It is a flowchart which shows the flow of the target parking area setting process in Example 1. FIG. It is a flowchart which shows the flow of the parking area correction process in Example 1. FIG. In Example 1, it is a figure which shows an example of the state before performing a parking area correction process. It is a figure which shows the example which performed the parking area correction process when it exists in the state of FIG. 11A. It is a functional block diagram which shows the function structure of the parking area recognition apparatus for vehicles which concerns on Example 2. FIG. 10 is a flowchart showing the overall flow of processing performed in the second embodiment. 12 is a flowchart illustrating a flow of a space map generation process in the second embodiment. It is a flowchart which shows the flow of the target parking area setting process in Example 2. FIG. It is a flowchart which shows the flow of the parking area correction process in Example 2. FIG. It is a figure which shows a mode that a spatial map is produced | generated in Example 2, (a) is a figure which shows the state of the spatial map in t = t0-2 (DELTA) t. (B) is a figure which shows the state of the space map in t = t0- (DELTA) t. (C) is a figure which shows the state of the space map in t = t0. It is a figure explaining the operation | movement of the parking area correction process in Example 2, (a) is a figure which shows an example of the produced | generated space map. (B) is a figure which shows the result of having performed the parking area correction process in the space map shown to Fig.17B (a). It is a functional block diagram which shows the function structure of the parking area recognition apparatus for vehicles which concerns on Example 3. FIG. 12 is a flowchart illustrating the overall flow of processing performed in the third embodiment. 12 is a flowchart illustrating a flow of an initial route generation process in the third embodiment. It is a flowchart which shows the flow of the target parking area reset process in Example 3. It is a figure explaining the operation example of Example 3, and is an example of the space map which shows the detection result of the parking area around a vehicle in a certain timing. It is a figure which shows the example which performed the setting of the target parking area, and the correction | amendment of the target parking area on the space map. It is a figure which shows the example which set the initial route which reaches the vicinity of a target parking area. It is a figure which shows the example which redetected the target parking area after moving a vehicle along an initial route. It is a figure which shows the example which produced | generated the parking route which leads to the re-detected target parking area. (A) It is a 1st figure explaining the subject in the parking assistance apparatus of a comparative example. (B) It is a 2nd figure explaining the subject in the parking assistance apparatus of a comparative example.

  Hereinafter, specific embodiments of a vehicular parking area recognition device according to the present invention will be described with reference to the drawings.

  In this embodiment, the vehicle is automatically parked in the set target parking area.

(Description of hardware configuration)
First, the hardware configuration of this apparatus will be described with reference to FIGS. 1 and 2. The vehicle parking area recognizing device 10a of this embodiment is mounted on the vehicle 100 shown in FIG. A plurality of small cameras are provided on the front, rear, left and right of the vehicle 100 as shown in FIG.

  Specifically, a front camera 20 a is attached to the front bumper or front grill of the vehicle 100 toward the front of the vehicle 100. Further, a rear camera 20 b is mounted on the rear bumper or rear garnish of the vehicle 100 toward the rear of the vehicle 100. A left side camera 20c is attached to the left door mirror of the vehicle 100 toward the left side of the vehicle 100, and a right side camera 20d is attached to the right door mirror of the vehicle 100 toward the right side of the vehicle 100. Has been.

  The front camera 20a, the rear camera 20b, the left side camera 20c, and the right side camera 20d are each equipped with a wide-angle lens and a fish-eye lens capable of observing a wide range, and include the road surface around the vehicle 100 with four cameras. The area can be observed without omission.

  Further, as shown in FIG. 1, distance measuring devices including sonars 30a, 30b, 30c, 30d, 30e, and 30f are mounted on the front, rear, left, and right sides of the vehicle 100.

  Specifically, a sonar 30 a is attached to the front bumper and front grill of the vehicle 100 toward the front of the vehicle 100. Sonars 30 b and 30 c are attached to the left side portion of the vehicle 100 toward the left side of the vehicle 100. The rear bumper and rear garnish of the vehicle 100 are equipped with a sonar 30d toward the rear of the vehicle 100, and sonars 30e and 30f are attached to the right side of the vehicle 100 toward the right side of the vehicle 100. Has been.

  These sonars 30a to 30f each have a distance measuring range that spreads in the horizontal direction, and all the sonars 30a to 30f can be combined to measure the surroundings of the vehicle 100 without omission.

  A radar device such as a millimeter wave radar may be installed in place of the sonars 30a to 30f. In general, the radar is excellent in distance measurement performance far from the sonar, and therefore, a sensor to be used may be appropriately selected based on the size of the distance range around the vehicle 100 required for automatic parking.

  The vehicle parking area recognizing device 10a is composed of the units shown in FIG. That is, the vehicle parking area recognition device 10a controls the front camera 20a, the rear camera 20b, the left camera 20c, the right camera 20d, and these cameras mounted on the vehicle 100, and detects the parking area. A camera ECU 22 that performs processing such as setting of a target parking area and position correction of the parking area, sonars 30a to 30f described above, and a sonar that controls these sonars 30a to 30f and detects obstacles around the vehicle 100 An ECU 32 is included. Moreover, the monitor 41 which has a touchscreen function which displays information required when operating the parking area recognition apparatus 10a for vehicles is provided.

  Furthermore, the vehicular parking area recognition device 10a includes an automatic parking start switch 29 for instructing the start of automatic parking, and based on information detected by the camera ECU 22 and the sonar ECU 32, a target parking area when performing automatic parking A vehicle control ECU 64 that determines candidates and further determines an approach direction that the vehicle 100 should take. Then, based on the vehicle control information determined by the vehicle control ECU 64, a steering control unit 70 that controls the steering angle of the vehicle 100, a throttle control unit 80 that controls the throttle of the vehicle 100, and a brake that controls the brake of the vehicle 100. And a control unit 90.

  Further, the vehicle parking section recognition device 10a acquires information necessary for specifying the current position of the vehicle 100 and information necessary for controlling the vehicle speed and the steering angle of the vehicle 100 when performing automatic parking. A speed sensor 93, a rudder angle sensor 94, a yaw rate sensor 95, and a shift position sensor 96 are provided.

  The steering control unit 70 drives the power steering actuator 72 to control the steering angle of the vehicle 100.

  The throttle control unit 80 drives the throttle actuator 82 to control the throttle of the vehicle 100.

  The brake control unit 90 controls the brake of the vehicle 100 by driving the brake actuator 92.

  A sensor information network 55 constituted by, for example, CAN (registered trademark) (Controller Area Network), which is a network laid in the vehicle 100, is provided between the camera ECU 22 and the sonar ECU 32 and the vehicle control ECU 64. It is connected. In addition, vehicle information constituted by, for example, CAN (registered trademark), which is a network laid in the vehicle 100, between the steering control unit 70, the throttle control unit 80, the brake control unit 90, and the vehicle control ECU 64. It is connected to the system network 56.

  Here, in FIG. 2, a radar not shown in FIG. 2 may be installed instead of the sonars 30a to 30f. When a radar is installed, a radar ECU (not shown in FIG. 2) that controls the radar and detects obstacles around the vehicle 100 is installed.

  Since the sonars 30a to 30f and the radar have different ranging ranges, of course, both may be mixed. In order to realize the distance measuring function, the front camera 20a, the rear camera 20b, the left camera 20c, and the right camera 20d detect obstacles by comparing images captured at different times, respectively. A so-called motion stereo function may be implemented. Hereinafter, in order to simplify the explanation, it is assumed that only the sonars 30a to 30f and the sonar ECU 32 are mounted on the vehicle parking area recognition device 10a as distance measuring means.

(Description of Functional Configuration of Example 1)
Next, the functional configuration of the vehicular parking area recognition device 10a will be described with reference to FIG. The vehicle parking section recognition device 10a includes an imaging unit 20, a distance measurement unit 30, an overhead conversion unit 40, an image composition unit 42, a white line detection unit 44, and a parking section detection unit 46, which are mounted on the vehicle 100. And a target parking zone setting unit 48, a parking zone correction unit 50, a parking route generation unit 60, and an automatic parking execution unit 62.

  The imaging unit 20 includes a front camera 20a, a rear camera 20b, a left side camera 20c, and a right side camera 20d shown in FIGS. 1 and 2, and captures an image around the vehicle 100.

  The distance measurement unit 30 (object detection unit) includes the sonars 30a, 30b, 30c, 30d, 30e, and 30f shown in FIGS. 1 and 2, measures the distance around the vehicle 100, and has a height different from the road surface. An object is detected.

  The bird's-eye conversion unit 40 is a bird's-eye view obtained by bird's-eye view of the images taken by the respective cameras (the front camera 20a, the rear camera 20b, the left-side camera 20c, and the right-side camera 20d) constituting the imaging unit 20, respectively. Convert to image.

  The image synthesis unit 42 synthesizes each overhead view image converted by the overhead view conversion unit 40 into one image.

  The white line detection unit 44 detects a white line or a yellow line constituting the boundary line of the parking section from the image generated by the image composition unit 42. Details of the processing will be described later.

  Based on the detection result of the white line and the yellow line in the white line detection unit 44, the parking section detection unit 46 detects a parking section formed by these white lines and yellow lines. Details of the processing will be described later.

  The target parking zone setting unit 48 sets a target parking zone where the vehicle 100 is parked. Details of the processing will be described later.

  The parking section correction unit 50 corrects at least one of the end point position and direction of the set parking section. Details of the processing will be described later.

  The parking route generation unit 60 generates a parking route from the current position of the vehicle 100 to the target parking section. Details of the processing will be described later.

  The automatic parking execution unit 62 controls the vehicle speed, the steering angle, and the brake of the vehicle 100 according to instructions from the vehicle control ECU 64 (FIG. 2) along the parking route generated by the parking route generation unit 60. Perform automatic parking. Details of the processing will be described later.

(Description of process flow in embodiment 1)
Hereinafter, the overall flow of processing performed by the vehicle parking section recognition device 10a will be described with reference to FIG.

  (Step S10) The overhead image conversion unit 40 (FIG. 3) performs overhead image generation processing.

  (Step S20) In the white line detection unit 44 (FIG. 3), a white line detection process for detecting a white line constituting the boundary line of the parking section is performed.

  (Step S50) In the parking area detection part 46 (FIG. 3), the parking area detection process which detects a parking area is performed.

  (Step S100) In the target parking area setting unit 48 (FIG. 3), a target parking area setting process for setting the target parking area is performed.

  (Step S150) The parking section correction unit 50 (FIG. 3) performs a parking section correction process for correcting the position and direction of the parking section as necessary.

  (Step S200) The parking route generation unit 60 (FIG. 3) generates a parking route from the current position of the vehicle 100 to the target parking section.

  (Step S250) In the automatic parking execution unit 62 (FIG. 3), the vehicle 100 is automatically parked in the target parking section PF.

  Although not described in the flowchart of FIG. 4, an object at a height different from the road surface by the distance measurement unit 30 (object detection unit) (for example, an obstacle on the road surface or a hole generated on the road surface). Is detected, and when the object is in a position that hides the parking line of the target parking area, the position correction of the target parking area is not performed and another target parking area is set. It is presented to the passenger of vehicle 100. Alternatively, when an obstacle is detected around the vehicle 100, white line detection by the white line detection unit 44 may not be performed in the vicinity of the obstacle.

  Hereinafter, the detailed contents of the processing performed in each step described in FIG. 4 will be described in order.

(Description of overhead image generation processing)
FIG. 5A is a diagram illustrating examples of images captured by the front camera 20a, the rear camera 20b, the left side camera 20c, and the right side camera 20d (the imaging unit 20 in FIG. 3) installed in the vehicle 100. As shown in FIG. 5A, an image including a road surface around the vehicle 100 is observed on each camera in a state in which the perspective transformation is performed. Each camera is equipped with a wide-angle lens such as a fish-eye lens or an ultra-wide-angle lens so that a wide range of images can be captured.

  FIG. 5B is a view of each image (If (x, y), Il (x, y), Ir (x, y), Ib (x, y)) shown in FIG. Is converted into an overhead image (Ife (x, y), Ile (x, y), Ire (x, y), Ibe (x, y)), and each overhead image is further synthesized to form a single overhead view. It is a figure which shows the example which produced | generated the synthetic | combination image Ie (x, y).

  The image picked up by the image pickup unit 20 is subjected to coordinate conversion on the assumption that a planar road surface is observed a predetermined distance below a viewpoint position provided at a predetermined position in the sky. , Converted into an overhead image. And since the relative relationship of the installation position of each camera (front camera 20a, rear camera 20b, left side camera 20c, right side camera 20d) is known in advance, each overhead view image is synthesized so as to have a predetermined positional relationship. Thus, a single overhead view composite image Ie (x, y) can be obtained. Since the central portion of the overhead view composite image Ie (x, y) is a blind spot, an icon 110 indicating a state where the vehicle 100 is looked down from directly above is displayed.

(Description of white line detection processing)
FIG. 6 is a flowchart illustrating the flow of the white line detection process (step S20 in FIG. 4) according to the first embodiment. A white line here is a white line which comprises the boundary line of a parking area. In addition, since the boundary line of a parking area may be formed by a yellow line other than the white line, for example, the white line detected here is not limited to the “white line”. That is, generally, processing for detecting a boundary line having contrast with the road surface is performed. Hereinafter, the processing content of each step shown in FIG. 6 will be described in order.

  (Step S22) The overhead view composite image Ie (x, y) generated previously is read out.

  (Step S24) An edge is detected from the overhead view composite image Ie (x, y).

  (Step S26) The image in which the edge is detected is scanned in a certain direction (for example, the overhead view composite image Ie (x, y) in FIG. 5B is the x-axis direction in FIG. 5B), and the gray value of the image is greater than or equal to a predetermined value A rising edge position that changes brighter with the difference and a falling edge position that changes darker due to the difference are extracted. The scanning direction is preferably set to a direction orthogonal to the parking lot line drawn on the road surface. That is, when the parking lot line extends in a direction orthogonal to the icon 110 representing the vehicle, it is desirable to scan in the y-axis direction in FIG. 5B. In general, since the direction in which the parking partition line extends is unknown, scanning may be performed twice in each of the x-axis direction and the y-axis direction in FIG. 5B.

  (Step S28) A pair of rising edge position and falling edge position on the same scan line is searched.

  (Step S30) The rising edge position and falling edge position pairs extracted in step S28 are grouped.

  (Step S32) Continuous rising edges that do not satisfy a predetermined length by performing filtering based on the lengths of line segments constituted by continuous rising edge positions and line segments constituted by continuous falling edge positions Remove positions and successive falling edge positions. By this process, the parking lot lines K1 and K2 shown in FIG. 8 are detected.

  (Step S <b> 34) The positions of the end points remaining as a result of the filtering by the length and the line segments composed of continuous rising edge positions and the line segments composed of continuous falling edge positions are calculated. Thereafter, the process of FIG. 6 is terminated and the process returns to the main routine (FIG. 4).

(Description of parking area detection processing)
FIG. 7 is a flowchart illustrating the flow of the parking zone detection process (step S50 in FIG. 4) in the first embodiment. Moreover, FIG. 8 is a figure which shows an example of a parking area detection result. Hereinafter, the processing content of each step shown in FIG. 7 will be described in order with reference to FIG.

  (Step S52) Among the line segments detected by the white line detection process (FIG. 6), two adjacent line segments that may form a parking section are selected. The two line segments selected here are the line segments constituting the left and right ends in the extending direction of the parking section line that partitions the parking section. That is, a line segment composed of rising edge positions and a line segment composed of continuous falling edge positions.

  (Step S54) It is determined whether or not the difference between the angles θL (1) and θR (1) (FIG. 8) of the two selected line segments is equal to or smaller than a threshold value Th_θmax. If the condition is satisfied, the process proceeds to step S56; otherwise, the process proceeds to step S64.

  (Step S56) It is determined whether or not the interval W (FIG. 8) between the two selected line segments is not less than the threshold value Th_Wmin and not more than the threshold value Th_Wmax. If the condition is satisfied, the process proceeds to step S58, and otherwise, the process proceeds to step S64.

  (Step S58) It is determined whether or not the deviation B (FIG. 8) between the lower ends of the two selected line segments is not less than the threshold value Th_Bmin and not more than the threshold value Th_Bmax. When the condition is satisfied, the process proceeds to step S60, and otherwise, the process proceeds to step S64.

  (Step S60) An area configured with two line segments as the left and right ends is registered in the parking section detection unit 46 (FIG. 3) as a parking section PF (i). In FIG. 8, the parking section PF (1) is registered.

  (Step S62) The parking lot line positions (PL (i), PR (i)) and the parking lot line direction θm (i), which are the end point positions on both the left and right ends, are registered in the parking lot detection unit 46 (FIG. 3). To do. In FIG. 8, the parking lot line positions (PL (1), PR (1)) and the parking lot line direction θm (1) are registered.

  (Step S64) It is determined whether or not confirmation has been performed for all line segment combinations. When the condition is satisfied, the process of FIG. 7 is terminated and the process returns to the main routine (FIG. 4). Otherwise, the process returns to step S52.

(Explanation of target parking area setting process)
FIG. 9 is a flowchart illustrating the flow of the parking zone detection process (step S50 in FIG. 4) in the first embodiment. Hereinafter, the processing contents of each step shown in FIG. 9 will be described in order.

  (Step S102) The parking area around the vehicle detected by the parking area detection process (step S50 in FIG. 4) is displayed on the monitor 41 (FIG. 2).

  (Step S104) It is determined whether the user has selected one parking section PF (i). If the condition is satisfied, the process proceeds to step S106. Otherwise, the process proceeds to step S108. The selection of the parking section PF (i) is performed, for example, by pressing the position of the desired parking section PF (i) using the touch panel function of the monitor 41 (FIG. 2).

  (Step S106) The selected parking section PF (i) is set as the target parking section PF. Thereafter, the process of FIG. 9 is terminated and the process returns to the main routine (FIG. 4).

  (Step S108) The parking section PF (i) closest to the front wheel axle center of the vehicle 100 is set as the target parking section PF. Thereafter, the process of FIG. 9 is terminated and the process returns to the main routine (FIG. 4).

(Description of parking area correction processing)
FIG. 10 is a flowchart illustrating the flow of the parking zone correction process (step S150 in FIG. 4) according to the first embodiment. Moreover, FIG. 11A and FIG. 11B are figures which show an example of a parking area correction process. Hereinafter, the processing content of each step shown in FIG. 10 will be described in order with reference to FIGS. 11A and 11B.

  (Step S152) The target parking area PF set in the target parking area setting process (FIG. 9) and the parking area PF (i) detected in the parking area detection process (FIG. 7) are read. Here, the description will be made assuming that the parking section PF (3) illustrated in FIG. 11A is set as the target parking section PF.

  (Step S154) It is determined whether a plurality of parking sections PF (i) are detected on the own vehicle side of the target parking section PF. If the condition is satisfied, the process proceeds to step S156; otherwise, the process proceeds to step S170. For example, in FIG. 11B, a plurality of parking sections PF (1) and PF (2) are detected on the own vehicle side of the parking section PF (3) set as the target parking section PF. move on.

  (Step S156) The average direction θm of the plurality of parking sections PF (i) is calculated. For example, in FIG. 11A, the average direction θm is calculated as the average value of the directions θm (1) and θm (2) (see FIG. 8) of the parking sections PF (1) and PF (2).

  (Step S158) It is determined whether or not the absolute value of {θm−θL (i)} is larger than the threshold value TH_θ. If the condition is satisfied, the process proceeds to step S160. Otherwise, the process proceeds to step S162. For example, in FIG. 11A, it is assumed that the absolute value of {θm−θL (i)} is smaller than the threshold value TH_θ. That is, the process proceeds to step S162.

  (Step S160) θL (i) is corrected to θm.

  (Step S162) It is determined whether or not the absolute value of {θm−θR (i)} is larger than the threshold value TH_θ. If the condition is satisfied, the process proceeds to step S164. Otherwise, the process proceeds to step S166. For example, in FIG. 11A, it is assumed that the absolute value of {θm−θR (i)} is smaller than the threshold value TH_θ. That is, the process proceeds to step S166.

  (Step S164) θR (i) is corrected to θm.

  (Step S166) A reference straight line L determined by parking lot line positions (PL (i), PR (i), i = 0, 1, 2,...) Which are detected end point positions is determined by the least square method. . For example, in FIG. 11B, the reference straight line L is determined.

  (Step S168) Based on the reference straight line L, the position of the end point of the target parking section PF is corrected and stored in the parking section correction unit 50 (FIG. 3). For example, in FIG. 11B, the parking lot line position PR (3) is a position where the extended line M that forms the inner side of the parking lot line including the parking lot line position PR (3) intersects the reference straight line L, that is, The parking lot line position PR ′ (3) shown in FIG. 11B is corrected. Thereafter, the processing of FIG. 10 is terminated and the process returns to the main routine (FIG. 4).

  (Step S170) The position of the end point of the target parking section PF is not corrected. Thereafter, the processing of FIG. 10 is terminated and the process returns to the main routine (FIG. 4).

(Description of parking route generation processing)
The parking route generation unit 60 (FIG. 3) generates a parking route for moving the vehicle 100 from the current position to the target parking portion PF with respect to the target parking portion PF that has undergone the parking portion correction process. There are various variations in the generated parking route, such as a parking route that minimizes the distance until parking is completed, a parking route that parks from the front end of the vehicle 100, and a parking route that has the least number of turnovers. An appropriate parking route may be selected by presenting conditions regarding the route to be generated from 100 passengers.

(Description of automatic parking execution process)
The automatic parking execution unit 62 (FIG. 3) controls the vehicle speed, the steering angle, and the brake of the vehicle 100 along the parking route generated by the parking route generation unit 60, and executes automatic parking of the vehicle 100. Specifically, in FIG. 2, the shift position of the vehicle 100 is detected by the shift position sensor 96, the vehicle speed is detected by the wheel speed sensor 93, the steering angle is detected by the steering angle sensor 94, and the throttle actuator 82 and brake The vehicle speed is controlled by controlling the actuators 92 respectively. Further, the power steering actuator 72 is controlled to control the steering angle. Thus, automatic parking is performed by moving the vehicle 100 along the generated parking route.

  At that time, the surroundings of the vehicle 100 are sequentially observed by the imaging unit 20 and the distance measuring unit 30 shown in FIG. 3, and the vehicle 100 is targeted while correcting the parking route by avoiding obstacles as necessary. Move toward the parking area PF. Then, after confirming that the position of the target parking section PF has been reached, it is determined that automatic parking has been completed.

  Hereinafter, a second specific embodiment of the vehicle parking area recognizing device according to the present invention will be described with reference to the drawings.

  In this embodiment, the vehicle is automatically parked in the set target parking area. In particular, it has a function of automatically generating a space map around the vehicle according to the movement of the vehicle, and selects a target parking area from the generated space map around the vehicle, and if necessary, its position and After correcting the direction, automatic parking is executed for the target parking area.

(Description of Functional Configuration of Example 2)
The functional configuration of the vehicular parking area recognition device 10b will be described with reference to FIG. The vehicle parking section recognition device 10b includes an imaging unit 20, a distance measurement unit 30, an overhead conversion unit 40, an image composition unit 42, a white line detection unit 44, and a parking section detection unit 46, which are mounted on the vehicle 100. A space map generation unit 47, a target parking zone setting unit 48, a parking zone correction unit 50, a parking route generation unit 60, an automatic parking execution unit 62, a vehicle information acquisition unit 66, and a dead reckoning calculation unit 68. And consist of The hardware configuration of the second embodiment is the same as the hardware configuration of the first embodiment (FIG. 2).

  Of the constituent parts shown in FIG. 12, parts common to the functional configuration of the first embodiment (FIG. 3) have the same functions.

  Of the constituent parts that only Example 2 has, the vehicle information acquisition unit 66 detects wheel speed, steering angle, yaw rate, and shift position, which are information necessary for detecting the behavior of the vehicle.

  The dead reckoning calculation unit 68 calculates the current position and direction of the vehicle 100 using the information acquired by the vehicle information acquisition unit 66.

  Based on the behavior of the vehicle 100 calculated by the dead reckoning calculation unit 68, the space map generation unit 47 integrates the position of the parking block detected in the past and the position of the currently detected parking block into one map. Thus, a space map around the vehicle 100 is generated.

(Description of process flow in Embodiment 2)
Hereinafter, the overall flow of the process performed by the vehicle parking section recognizing device 10b will be described with reference to FIG.

  (Step S300) An overhead image generation process is performed in the overhead conversion unit 40 (FIG. 12).

  (Step S350) In the white line detection unit 44 (FIG. 12), a white line detection process for detecting a white line constituting the boundary line of the parking section is performed.

  (Step S400) In the parking area detection part 46 (FIG. 12), the parking area detection process which detects a parking area is performed.

  (Step S450) The spatial map generation unit 47 (FIG. 12) performs a spatial map generation process for generating a spatial map around the vehicle 100.

  (Step S500) In the target parking area setting unit 48 (FIG. 12), a target parking area setting process for setting the target parking area is performed.

  (Step S550) The parking area correction unit 50 (FIG. 12) performs a parking area correction process for correcting the position and direction of the parking area as necessary.

  (Step S600) The parking route generation unit 60 (FIG. 12) generates a parking route from the current position of the vehicle 100 to the target parking section.

  (Step S650) The automatic parking execution unit 62 (FIG. 12) automatically parks the vehicle 100 in the target parking area.

  Although not described in the flowchart of FIG. 13, as in the first embodiment, the distance measurement unit 30 (object detection unit) detects an object at a height different from the road surface, and the object is the target. When the parking lot line is in a position where the parking lot line is concealed, the position of the target parking zone is not corrected, and the passenger of the vehicle 100 is presented to set another target parking lot.

  In the following, the detailed contents of the process performed in each step described in FIG. 13 will be described only for the process different from the process performed in the first embodiment.

(Explanation of spatial map generation process)
FIG. 14 is a flowchart illustrating the flow of the space map generation process (step S450 in FIG. 13) according to the second embodiment. FIGS. 17A (a) to 17 (c) are diagrams showing how the space map S (t) at time t is generated. Hereinafter, the processing content of each step shown in FIG. 14 will be described in order with reference to FIGS. 17A (a) to 17 (c).

  (Step S452) The dead reckoning calculation unit 68 (FIG. 12) acquires wheel speed, steering angle, yaw rate, and shift position as behavior information of the vehicle 100, respectively. For example, in FIGS. 17A (a) and 17 (b), behavior information of the vehicle 100 between time t3 = t1-2Δt and time t2 = t1-Δt is acquired. Here, the time interval Δt is a time interval for detecting the parking area. The dead reckoning calculation unit 68 calculates the current position and direction of the vehicle 100 based on the behavior information of the vehicle 100. Therefore, it is necessary to integrate the wheel speed, the steering angle, and the yaw rate obtained as the behavior information of the vehicle 100, respectively. Therefore, such behavior information is acquired at a shorter time interval with respect to the time interval Δt for detecting the parking section.

  (Step S454) Based on the calculation result of the dead reckoning calculation unit 68 (FIG. 12), the current position and direction of the vehicle 100 are calculated. The current position and direction calculated here become the current position and direction of the vehicle 100 in the space map. For example, in FIG. 17A (b), the current position and direction of the vehicle 100 at time t2 = t1−Δt are calculated.

  (Step S456) The parking section PF (i) _t2 detected at time t2 = t1−Δt is read from the parking section detection unit 46. Hereinafter, the detection result of the parking area at time t is represented by PF (i) _t.

  (Step S458) The same parking area as the parking area at time t2 = t1−Δt detected in the parking area detection process (step S400 in FIG. 13) is in the already created space map S (t3). It is determined whether or not. In addition, whether it is the same parking area is, for example, the detection result of the parking area at the current time t2 = t1-Δt and the detection timing one cycle before that, that is, the parking area at t3 = t1-2Δt. The detection results may be compared, and the determination may be made in consideration of the position and direction of the parking section, the arrangement order of the adjacent parking sections, and the like. When the same parking area is found, the process proceeds to step S460, and otherwise, the process proceeds to step S464. For example, as shown in FIG. 17A (c), the parking area detected at time t3 = t1-2Δt and the parking area detected at time t2 = t1-Δt are compared, and parking area PF (2) _t3 And the parking section PF (1) _t2 are determined to be the same parking section.

  (Step S460) It is determined whether or not the two parking sections detected in step S458 are close to each other on the space map S (t2). If they are close to each other, the process proceeds to step S462, and otherwise, the process of FIG. 14 is terminated and the process returns to the main routine (FIG. 13). For example, in FIGS. 17A (a) and 17 (b), the parking section PF (2) _t3 detected at time t3 = t1-2Δt and the parking section PF (1) detected at time t2 = t1-Δt. It is determined that _t2 is in a position close to each other. In FIGS. 17A (b) and 17 (c), the parking section PF (2) _t2 detected at time t2 = t1−Δt and the parking section PF (1) _t1 detected at time t1 are mutually connected. It is determined to be in an approached position.

  (Step S462) In the space map generation unit 47 (FIG. 12), the detection result of the latest (current) parking section PF (i) is overwritten and registered with the detection result of the past parking section PF (i). For example, in FIG. 17A (b), the parking section PF (2) _t3 detected at time t3 = t1-2Δt is overwritten by the parking section PF (1) _t2 detected at time t2 = t1-Δt. The In FIG. 17A (c), the parking section PF (2) _t2 detected at time t2 = t1−Δt is overwritten by the parking section PF (1) _t1 detected at time t1. Thereafter, the process of FIG. 14 is terminated and the process returns to the main routine (FIG. 13).

  (Step S464) In the space map generation unit 47 (FIG. 12), the latest (current) parking section PF (i) is registered as a new parking section. For example, in FIG. 17A (b), the parking section PF (2) _t2 newly detected at time t2 is newly registered in the space map S (t2). Further, in FIG. 17A (c), the parking section PF (2) _t1 newly detected at time t1 is newly registered in the space map S (t1). Thereafter, the process of FIG. 14 is terminated and the process returns to the main routine (FIG. 13).

(Explanation of target parking area setting process)
FIG. 15 is a flowchart illustrating the flow of the target parking zone setting process (step S500 in FIG. 13) according to the second embodiment. Hereinafter, the processing contents of each step shown in FIG. 15 will be described in order.

  (Step S502) The parking area around the vehicle in the space map detected by the parking area detection process (step S400 in FIG. 13) is displayed on the monitor 41 (FIG. 2).

  (Step S504) The user sets the parking area PF (i) (hereinafter, unless otherwise specified, the parking area registered in the space map omits information indicating the time when the parking area was detected, and simply passes PF (i It is determined whether or not one) is selected. If the condition is satisfied, the process proceeds to step S506; otherwise, the process proceeds to step S508. The selection of the parking section PF (i) is performed, for example, by pressing the position of the desired parking section PF (i) using the touch panel function of the monitor 41 (FIG. 2).

  (Step S506) The selected parking area PF (i) is set as the target parking area. Thereafter, the process of FIG. 15 is terminated and the process returns to the main routine (FIG. 13).

  (Step S508) The parking section PF (i) closest to the front wheel axle center of the vehicle 100 is set as the target parking section. Thereafter, the process of FIG. 15 is terminated and the process returns to the main routine (FIG. 13).

(Description of parking area correction processing)
FIG. 16 is a flowchart illustrating the flow of the parking zone correction process (step S550 in FIG. 13) according to the second embodiment. FIG. 17B is a diagram for explaining the operation of the parking zone correction process at time t1. Hereinafter, the processing content of each step shown in FIG. 16 will be described in order with reference to FIG. 17B.

  (Step S552) The target parking area PF set in the target parking area setting process (step S500 in FIG. 13) and the parking area PF (i) detected in the parking area detection process (step S400 in FIG. 13) are read. Here, the description will be made assuming that the parking section PF (3) shown in FIG. 17B is set as the target parking section PF.

  (Step S554) It is determined whether or not a plurality of parking sections PF (i) are detected on the vehicle side of the target parking section PF in the space map S (t1). If the condition is satisfied, the process proceeds to step S556. Otherwise, the process proceeds to step S564. For example, in FIG. 17B (a), a plurality of parking sections PF (2), PF (1), and PF (0) are detected on the vehicle side of the parking section PF (3) set as the target parking section PF. Therefore, the process proceeds to step S556.

  (Step S556) The average direction θm of the plurality of parking sections PF (i) is calculated. For example, in FIG. 17B (a), the average azimuth | direction of parking area PF (2), PF (1), PF (0) is calculated.

  (Step S558) The direction of the target parking section PF is corrected as necessary. For example, in FIG. 7B (a), it is determined that there is no difference of a predetermined value or more between the heading of the target parking section PF (PF (3)) and the previously calculated average heading. The direction of the section PF is not corrected.

  (Step S560) The reference straight line L determined by the parking lot line positions (PL (i), PR (i), i = 0, 1, 2,...) That are the detected end point positions is determined by the least square method. . For example, in FIG. 17B (b), the reference straight line L is determined.

  (Step S562) Based on the reference straight line L, the position of the end point of the target parking section PF is corrected and stored in the parking section correction section 50 (FIG. 3). For example, in FIG. 17B (b), the extension line M of the line segment that forms the inside of the parking lot line including the parking lot line position PR (3) intersects with the reference straight line L. The position is corrected to the parking lot line position PR ′ (3). Thereafter, the process of FIG. 16 is terminated and the process returns to the main routine (FIG. 13).

  (Step S564) The position of the end point of the target parking section PF is not corrected. Thereafter, the process of FIG. 16 is terminated and the process returns to the main routine (FIG. 13).

  Of the processes shown in the flowchart of FIG. 13, processes not described here operate in the same manner as in the first embodiment.

  Hereinafter, a third specific embodiment of the vehicle parking area recognizing device according to the present invention will be described with reference to the drawings.

  In this embodiment, the vehicle is automatically parked in the set target parking area. In particular, after setting the target parking area, set an initial route to the vicinity of the target parking area, move the vehicle to the vicinity of the target parking area, and then again in the vicinity of the target parking area. Detection is performed, and automatic parking is executed for the re-detected target parking area.

(Description of Functional Configuration of Example 3)
The functional configuration of the vehicular parking area recognition device 10c will be described with reference to FIG. The vehicle parking area recognition device 10c includes an imaging unit 20, a distance measurement unit 30, an overhead conversion unit 40, an image composition unit 42, a white line detection unit 44, and a parking area detection unit 46, which are mounted on the vehicle 100. A space map generation unit 47, a target parking zone setting unit 48, a parking zone correction unit 50, an initial route generation unit 52, a target parking zone resetting unit 54, a parking route generation unit 60, and automatic parking execution. A unit 62, a vehicle information acquisition unit 66, and a dead reckoning calculation unit 68 are included. The hardware configuration of the third embodiment is the same as the hardware configuration of the first embodiment (FIG. 2).

  Of the components shown in FIG. 18, the components common to the functional configuration of the first embodiment (FIG. 3) and the functional configuration of the second embodiment (FIG. 12) have the same functions.

  Of the components included only in the third embodiment, the initial route generation unit 52 generates an initial route R that moves the vehicle 100 from the current position to the vicinity of the target parking section PF.

  When the target parking area PF is a corrected parking area, the target parking area resetting unit 54 resets the target parking area PF ′ detected again in the vicinity of the target parking area PF as the target parking area.

(Description of process flow in Embodiment 3)
Hereinafter, an overall flow of processing performed by the vehicle parking section recognition device 10c will be described with reference to FIG. 22A to 22E are diagrams for explaining an operation example of the third embodiment. Hereinafter, the processing content of each step shown in FIG. 19 will be described step by step with reference to FIGS. 22A to 22E as necessary.

  (Step S700) The overhead view conversion unit 40 (FIG. 18) performs an overhead image generation process.

  (Step S720) The white line detection unit 44 (FIG. 18) performs a white line detection process for detecting a white line constituting the boundary line of the parking section.

  (Step S740) In the parking area detection part 46 (FIG. 18), the parking area detection process which detects a parking area is performed.

  (Step S760) The spatial map generation unit 47 (FIG. 18) performs a spatial map generation process for generating a spatial map around the vehicle 100. By this processing, for example, a space map S (t1) shown in FIG. 22A is obtained.

  (Step S780) In the target parking area setting unit 48 (FIG. 18), a target parking area setting process for setting the target parking area is performed. For example, in FIG. 22A, it is assumed that the parking section PF (3) is set as the target parking section. At this time, it is assumed that the parking lot line position PR (3) far from the vehicle 100 in the parking lot PF (3) is detected by being interrupted by dirt or blurring of the parking lot line.

  (Step S800) The parking area correction unit 50 (FIG. 18) performs parking area correction processing for correcting the position and direction of the parking area as necessary. By this processing, for example, as shown in FIG. 22B, the position of the target parking section PF is corrected. That is, the parking lot line position PR (3) is corrected to the parking lot line position PR '(3) to be the target parking lot PF.

  (Step S820) The initial route generation unit 52 (FIG. 18) performs an initial route generation process for generating an initial route from the current position of the vehicle 100 to the vicinity of the target parking section PF. By this process, for example, an initial route R shown in FIG. 22C is generated.

  (Step S900) In the target parking area resetting unit 54 (FIG. 18), a target parking area resetting process for resetting the target parking area PF ′ re-detected in the vicinity of the target parking area PF to the target parking area is performed. By this process, for example, as shown in FIG. 22E, the target parking area PF is updated to the target parking area PF ′. Such a resetting process is performed by re-detecting the target parking area PF that has been detected from a distance and whose position has been corrected, in a state of approaching the target parking area PF, that is, from an adjacent position. This is because the position of the target parking section can be detected more reliably by reducing the influence of interruptions caused by dirt or fading of the parking section line.

  (Step S920) The parking route generation unit 60 (FIG. 18) generates a parking route from the current position of the vehicle 100 to the target parking section. By this process, for example, parking paths S1 and S2 shown in FIG. 22E are generated.

  (Step S940) In the automatic parking execution part 62 (FIG. 18), the vehicle 100 is automatically parked in the target parking section PF. For example, in FIG. 22E, the vehicle 100 can be reliably parked in the target parking section PF ′ by moving the vehicle 100 along the generated parking paths S1 and S2.

  In the following, the detailed contents of the process performed in each step described in FIG. 19 will be described only for the process different from the process performed in the first and second embodiments.

(Description of initial route generation processing)
FIG. 20 is a flowchart illustrating the flow of the initial path generation process (step S820 in FIG. 19) according to the third embodiment. 22A to 22E are diagrams for explaining an operation example of the third embodiment. Hereinafter, the processing content of each step shown in FIG. 20 will be described in order with reference to FIGS. 22A to 22D.

  (Step S822) The target parking area PF set in the target parking area setting process (step S780 in FIG. 19) is read. For example, in FIG. 22A, the following description will be made assuming that the parking section PF (3) is set as the target parking section PF.

  (Step S824) It is determined whether the set target parking area PF is the corrected target parking area. If it is the corrected target parking area, the process proceeds to step S826. Otherwise, the process of FIG. 20 is terminated and the process returns to the main routine (FIG. 19). For example, in FIGS. 22A to 22D, since the target parking area PF is corrected as shown in FIG. 22B, the process proceeds to step S826.

  (Step S826) An initial route R from the current position of the vehicle 100 to the vicinity of the set target parking section PF is generated. For example, in FIGS. 22A to 22D, an initial route R shown in FIG. 22C is generated.

  (Step S828) The vehicle 100 is moved along the initial route R. Then, when the vehicle reaches the end of the initial route R, that is, near the target parking section PF, the processing of FIG. 20 is terminated and the processing returns to the main routine (FIG. 19). For example, in FIGS. 22A to 22D, as shown in FIG. 22D, the vehicle 100 is moved to a position where the front wheel axle center Q reaches the vicinity of the target parking section PF.

(Explanation of target parking area resetting process)
FIG. 21 is a flowchart illustrating the flow of the target parking zone resetting process (step S900 in FIG. 19) according to the third embodiment. Hereinafter, the processing content of each step shown in FIG. 21 will be described in order with reference to FIG. 22E.

  (Step S902) It is determined whether or not the vehicle 100 has reached the end point of the initial route R. If the condition is satisfied, the process proceeds to step S904, and otherwise, step S902 is repeated.

  (Step S904) The overhead view conversion unit 40 (FIG. 3) performs overhead image generation processing.

  (Step S906) The white line detection unit 44 (FIG. 3) performs a white line detection process for detecting a white line constituting the boundary line of the parking section.

  (Step S908) The parking area detection unit 46 (FIG. 3) performs a parking area detection process for detecting a parking area. For example, in FIG. 22E, the target parking area PF (FIG. 22D) set by the target parking area setting process (step S780 in FIG. 19) is detected again. The target parking section PF ′ (FIG. 22E) re-detected in this way is used.

  (Step S910) The target parking area resetting unit 54 determines whether or not the recognition result of the target parking area PF has been updated, that is, whether or not the target parking area PF is a corrected parking area. If the condition is satisfied, the process proceeds to step S912. Otherwise, the process of FIG. 21 is terminated and the process returns to the main routine (FIG. 19). For example, in FIG. 22B, since the position of the target parking section PF has been corrected by the above-described parking section correction process (step S800 in FIG. 19), the process proceeds to step S912.

  (Step S912) The target parking area PF is updated to the target parking area PF '. For example, in FIG. 22E, the re-detected target parking area PF 'is set as a new target parking area. Thereafter, the process of FIG. 21 is terminated and the process returns to the main routine (FIG. 19).

  As described above, according to the vehicle parking area recognition device 10a described in the first embodiment, the parking area detection unit 46 detects the parking area PF (i) from the image captured by the imaging unit 20, Since the target parking area setting unit 48 sets the target parking area PF from the detected parking areas, and the parking area correction unit 50 corrects the position of the set target parking area PF, the parking area PF (i) Even when the boundary line is dirty and difficult to see, an appropriate target parking section PF can be set.

  Moreover, according to the vehicle parking area recognition device 10a described in the first embodiment, the parking area correction unit 50 includes the parking area line position PL (i) of the target parking area PF in the image captured by the imaging unit 20. , PR (i) (end point position) and azimuth θm (i) of the target parking section PF are corrected, so that the calculation for the correction can be executed at a low calculation cost. That is, correction can be performed in a shorter time.

  And according to the parking area recognition device 10a for a vehicle described in the first embodiment, the parking area correction unit 50 performs parking on the side close to the vehicle 100 in the parking area PF (i) adjacent to the target parking area PF. In order to correct the position of the target parking section PF based on the detection result of the section PF (i), the parking section line positions PL (i), PR of the parking section PF (i) detected on the side closer to the vehicle 100 Since the correction based on (i) and the direction θm (i), that is, the correction based on more accurate information, is performed, the accuracy of the correction of the target parking section PF can be improved.

  Furthermore, according to the vehicle parking area recognition device 10a described in the first embodiment, the parking area correction unit 50 includes a plurality of parking areas PF (including a parking area PF (i) adjacent to the set target parking area PF ( In order to correct the position of the target parking lot PF based on the detection result of each parking lot line position PL (i), PR (i) constituting i), a plurality of parking lot line positions PL (i), PR ( By performing the correction based on i) and the direction θm (i), the accuracy of the correction of the target parking section PF can be improved.

  In addition, according to the vehicle parking section recognition device 10a described in the first embodiment, the distance measuring unit 30 (object detecting unit) that is provided in the vehicle 100 and detects an object having a height from the road surface around the vehicle 100. However, when it is determined that a part of the target parking area PF is concealed by the object, the parking area correction unit 50 does not correct the position of the target parking area PF. Therefore, it is possible to prevent the error from being erroneously corrected. Therefore, the detection accuracy of the parking section can be improved.

  Then, according to the vehicular parking area recognition device 10b described in the second embodiment, the spatial map generation unit 47 includes the imaging unit based on the behavior of the vehicle 100 detected by the dead reckoning calculation unit 68 (vehicle behavior detection unit). The same parking area is identified from parking areas PF (i) detected from images captured at different times in 20, and the spatial arrangement of the parking areas PF (i) detected at a plurality of different times Are integrated into one space map S (t), and the position of the target parking section PF set in the integrated space map S (t) is corrected as necessary. The parking area PF (i) at a distant position can be set as the target parking area PF.

  Furthermore, according to the vehicular parking area recognition device 10c described in the third embodiment, the initial path generation unit 52 generates the initial path R from the current position of the vehicle 100 to the vicinity of the target parking area PF, and performs target parking. When the section PF is a target parking section where the position has been corrected, after the vehicle 100 moves along the initial route R, the parking section is detected from the images around the vehicle 100 that are captured again at the position after the movement. The unit 46 redetects the target parking section PF ′, and calculates parking paths S1 and S2 for parking in the target parking section PF ′ based on the re-detected position and direction of the target parking section PF ′. The influence of discontinuity caused by dirt or fading of the parking lot line is reduced, and the position of the target parking lot PF ′ can be detected more reliably.

  As mentioned above, although the Example of this invention was explained in full detail with drawing, since an Example is only an illustration of this invention, this invention is not limited only to the structure of an Example. Of course, changes in design and the like within a range not departing from the gist are included in the present invention.

  For example, in the first to third embodiments, an object having a height from the road surface is detected based on the output of the distance measurement unit 30 (object detection unit). It is also possible to use a so-called moving stereo method (motion stereo method) that uses only the image picked up by the image pickup unit 20 without using 30, and identifies the three-dimensional position of a three-dimensional object that moves over time. Alternatively, the distance measuring unit 30 and the moving stereo method may be used in combination.

  Each flowchart described through the first to third embodiments shows an example of the flow of processing, and the processing order may be changed as appropriate. For example, in each embodiment, after the target parking section PF is determined, the position or direction of the determined target parking section PF is corrected. For example, the detection of the parking section PF (i) is performed. It is good also as a structure which correct | amends the position of each parking area PF (i) after being performed, and sets the target parking area PF based on the corrected result.

20 ······· Imaging unit 30 ······· Distance measuring unit (object detection unit)
46... Parking zone detection unit 47... Space map generation unit 48... Target parking zone setting unit 50. ..... Initial route generation unit 68 ..... Dead reckoning calculation unit (vehicle behavior detection unit)
100 ··· Vehicle R ········· Initial route S1, S2 ··· Parking path PF (i) ··· Parking lot PF, PF '... Target parking lot θm ( i) ... Direction PL (i), PR (i) ... Parking lot line position (end point position)
10a, 10b, 10c ... Parking space recognition device for vehicles

Claims (7)

At least one imaging unit provided in the vehicle for capturing an image around the vehicle;
From the image captured by the imaging unit, a parking zone detection unit that detects a parking zone,
Based on the detection result of the parking area, a target parking area setting unit that sets a target parking area for parking the vehicle;
A vehicular parking area recognizing device, comprising: a parking area correction unit that corrects a position of the target parking area in the image.   The vehicle parking area recognition according to claim 1, wherein the parking area correction unit corrects at least one of an end point position of the target parking area and an orientation of the target parking area in the image. apparatus.   The said parking area correction | amendment part correct | amends the position of the said target parking area based on the detection result of the parking area adjacent to the said vehicle among the parking areas adjacent to the said target parking area. The vehicle parking area recognition device according to claim 1 or 2.   The parking area correction unit corrects the position of the target parking area based on the detection results of the respective parking area lines that respectively configure a plurality of parking areas including a parking area adjacent to the set target parking area. The parking area recognition apparatus for vehicles according to claim 1 or 2 characterized by these.   The vehicle includes an object detection unit that detects an object having a height from a road surface around the vehicle, and when the target parking area is concealed by the object, the parking area correction unit The vehicle parking area recognition device according to any one of claims 1 to 4, wherein the position of the target parking area is not corrected. A vehicle behavior detector for detecting the behavior of the vehicle;
A plurality of different times are specified by identifying the same parking section based on the behavior of the vehicle detected by the vehicle behavior detection section from among the parking sections detected from images captured at different times by the imaging section. A spatial map generating unit that integrates the spatial arrangement of each detected parking partition into a single spatial map, and sets a target parking partition in the spatial map generated by the spatial map generating unit The vehicle parking area recognizing device according to claim 1, wherein the position of the set target parking area is corrected as necessary.   A target parking section having an initial path generating section that generates an initial path from the current position of the vehicle to the vicinity of the target parking section for the detected target parking section, the position of the target parking section being corrected; When the vehicle is a zone, the parking zone detection unit redetects the target parking zone from the image around the vehicle that has been re-captured after the vehicle has moved along the initial route. The parking route when parking in the target parking area is calculated based on the re-detected position and direction of the target parking area, according to any one of claims 1 to 6. Vehicle parking area recognition device.