Block parking space parking control method, device and equipment and storage medium

Abstract

The invention discloses a block-shaped parking space parking control method, device and equipment and a storage medium, relates to the technical field of parking control, and discloses a block-shaped parking space parking control method which comprises the steps that a parking space aerial view and vehicle size information are acquired; determining block parking space center point information and block parking space mark point information based on the parking space aerial view; determining parking frame information and parking space type information based on at least one of the vehicle size information, the block parking space center point information and the block parking space mark point information; and according to the parking frame information and the parking space type information, controlling the own vehicle to park in the corresponding block-shaped parking space. According to the scheme, parking control can be carried out based on blocky parking spaces of different sizes.

Description

Technical Field

[0001] The present application relates to the field of parking control technology, and in particular to a method, device, equipment and storage medium for controlling parking in a block parking space. Background Art

[0002] With the rapid development of autonomous driving technology, automatic parking has become an important part of smart cars. Automatic parking can not only improve driving convenience and safety, but also effectively utilize limited urban space resources. In the actual parking control process, in addition to the common rectangular parking spaces, there are also some unconventional parking spaces such as block parking spaces.

[0003] Existing solutions are generally parking space detection and parking methods based on pure vision or vision and radar fusion. For conventional linear parking spaces (rectangular frame size is larger than the size of the vehicle), corner point detection based on neural networks has a good effect. However, for unconventional block parking spaces, existing parking space detection methods and parking methods cannot well meet the requirements of parking space identification and parking. Since the characteristics of block parking spaces are different from those of conventional parking spaces, and the size of the frame is not strictly larger than the size of the vehicle, special processing is required in parking space detection and parking control to meet the requirements of parking in block parking spaces. How to perform parking control based on block parking spaces of different sizes has become a problem to be solved.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device, equipment and storage medium for controlling parking entry into block parking spaces, aiming to solve the technical problem of how to perform parking entry control based on block parking spaces of different sizes.

[0006] To achieve the above objectives, the present application proposes a parking control method for block parking spaces, the method comprising:

[0007] Get a bird's-eye view of parking spaces and information about your vehicle's dimensions;

[0008] Determine block parking space center point information and block parking space marking point information based on the parking space bird's-eye view;

[0009] Determine parking frame information and parking space type information based on at least one of the vehicle size information, the block parking space center point information, and the block parking space marking point information;

[0010] The vehicle is controlled to park in a corresponding block parking space according to the parking frame information and the parking space type information.

[0011] In one embodiment, the step of determining the parking frame information and the parking space type information based on at least one of the vehicle size information, the block parking space center point information, and the block parking space marking point information includes:

[0012] Determine the block parking space corner point information based on the block parking space mark point information;

[0013] Determine parking frame information based on the vehicle size information, the block parking space center point information, and the block parking space corner point information;

[0014] The parking space type information is determined based on the block parking space marking point information.

[0015] In one embodiment, the step of determining the block parking space corner point information based on the block parking space marking point information includes:

[0016] When it is detected that the first corner point and the second corner point exist in the block parking space mark point information, and the third corner point and the fourth corner point do not exist, acquiring the block parking space depth information according to the parking space bird's-eye view;

[0017] Determine the third corner point and the fourth corner point based on the first corner point, the second corner point and the block parking space depth information;

[0018] The first corner point, the second corner point, the third corner point and the fourth corner point are used as block parking space corner point information.

[0019] In one embodiment, the step of determining the third corner point and the fourth corner point based on the first corner point, the second corner point and the block parking space depth information includes:

[0020] Get a unit vector from the first corner point to the second corner point;

[0021] Determine a third corner point based on the rotation matrix, the unit vector, the second corner point and the block parking space depth information;

[0022] A fourth corner point is determined based on the rotation matrix, the unit vector, the first corner point, and the block parking space depth information.

[0023] In one embodiment, the step of determining the parking space type information based on the block parking space marking point information includes:

[0024] Acquire block parking space width information and block parking space depth information according to the parking space bird's-eye view;

[0025] Determine the entrance line information based on the block parking space marking point information;

[0026] The parking space type information is determined according to the block parking space width information, the block parking space depth information and the entrance line information.

[0027] In one embodiment, the step of obtaining a bird's-eye view of a parking space includes:

[0028] Get the fisheye image of the parking space;

[0029] The fisheye image of the parking space is subjected to a dedistortion process, and a surround map is constructed on the dedistorted fisheye image of the parking space to obtain a bird's-eye view of the parking space.

[0030] In one embodiment, the step of controlling the vehicle to park in the corresponding block parking space according to the parking frame information and the parking space type information includes:

[0031] determining a parking path according to the parking frame information and the parking space type information;

[0032] When it is detected that the parking path has no collision risk, the vehicle is controlled to park in the corresponding block parking space according to the parking path.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a parking control device for block parking spaces, the parking control device for block parking spaces comprising:

[0034] An information acquisition module is used to obtain a bird's-eye view of parking spaces and vehicle size information;

[0035] A block parking space determination module, used to determine block parking space center point information and block parking space marking point information based on the parking space bird's-eye view;

[0036] A parking frame determination module, used to determine parking frame information and parking space type information based on at least one of the vehicle size information, the block parking space center point information and the block parking space marking point information;

[0037] The parking control module is used to control the vehicle to park in the corresponding block parking space according to the parking frame information and the parking space type information.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a block parking space parking control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the block parking space parking control method described above.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the block parking space parking control method described above are implemented.

[0040] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the block parking space parking control method described above are implemented.

[0041] One or more technical solutions proposed in this application have at least the following technical effects:

[0042] A bird's-eye view of parking spaces and vehicle size information are obtained, block parking space center point information and block parking space marking point information are determined based on the parking space bird's-eye view, parking frame information and parking space type information are determined based on at least one of the vehicle size information, the block parking space center point information and the block parking space marking point information, and the vehicle is controlled to park in the corresponding block parking space according to the parking frame information and the parking space type information. By determining the block parking space marking point information according to the parking space bird's-eye view, scaling the marked parking space outer frame based on the vehicle size information and the block parking space marking point information, and outputting the scaled parking frame information and parking space type information, the vehicle parking path planning requirements are met, and the problem of searching and parking in block parking spaces of different sizes is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 A flowchart diagram of the first embodiment of the parking control method for block parking spaces of the present application;

[0046] Figure 2 A schematic diagram of a conventional parking space provided in Example 1 of the parking control method for block parking spaces of the present application;

[0047] Figure 3 A schematic diagram of a block parking space provided in Example 1 of the block parking space parking control method of the present application;

[0048] Figure 4 A schematic diagram of corner point reasoning provided for the first embodiment of the parking control method for block parking spaces of the present application;

[0049] Figure 5 A block parking space detection result diagram provided in Example 1 of the block parking space parking control method of the present application;

[0050] Figure 6 A flow chart of the second embodiment of the parking control method for block parking spaces of the present application;

[0051] Figure 7 A schematic diagram of a simplified flow chart of a method for controlling parking in a block parking space provided in the second embodiment of the present application;

[0052] Figure 8 This is a schematic diagram of the module structure of the block parking space parking control device according to an embodiment of the present application;

[0053] Fig. 9 Schematic diagram of the device structure of the hardware operating environment involved in the block parking space parking control method in the embodiment of the present application.

[0054] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0056] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0057] The main solution of the embodiment of the present application is: obtain a bird's-eye view of parking spaces and size information of the own vehicle; determine the center point information of block parking spaces and the marking point information of block parking spaces based on the bird's-eye view of parking spaces; determine the parking frame information and parking space type information based on at least one of the size information of the own vehicle, the center point information of the block parking spaces and the marking point information of the block parking spaces; and control the own vehicle to park in the corresponding block parking space according to the parking frame information and the parking space type information.

[0058] In this embodiment, for the convenience of description, the following description is made by taking identification of the vehicle-mounted terminal as the execution subject.

[0059] Since the existing solutions are generally based on pure vision or vision and radar fusion parking space detection and parking methods, for conventional linear parking spaces (rectangular frame size is larger than the size of the vehicle), corner point detection based on neural networks has a good effect. However, for unconventional block parking spaces, the existing parking space detection methods and parking methods cannot well meet the requirements of parking space identification and parking. Since the characteristics of block parking spaces are different from those of conventional parking spaces, and the size of their size frame is not strictly larger than the size of the vehicle, special processing is required in parking space detection and parking control to meet the requirements of parking in block parking spaces.

[0060] The present application provides a solution, which determines the block parking space marking point information according to the parking space bird's-eye view, scales the marked parking space frame based on the vehicle size information and the block parking space marking point information, and outputs the scaled parking frame information and parking space type information to meet the parking path planning needs of the vehicle and solve the problem of searching and parking in block parking spaces of different sizes.

[0061] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a vehicle-mounted terminal, etc. The following takes the vehicle-mounted terminal as an example to illustrate this embodiment and the following embodiments.

[0062] Based on this, the embodiment of the present application provides a parking control method for block parking spaces, referring to Figure 1 , Figure 1 Schematic diagram of the flow of the first embodiment of the block parking space parking control method of the present application.

[0063] In this embodiment, the block parking space parking control method includes steps S10 to S40:

[0064] Step S10, obtaining a bird's-eye view of the parking space and the size information of the vehicle;

[0065] It should be noted that the existing parking space detection and parking methods based on pure vision or vision and radar fusion, for conventional linear parking spaces, please refer to Figure 2 , Figure 2 The conventional parking space diagram provided in the first embodiment of the parking control method for block parking spaces of this application has a good effect on the corner point detection method based on neural network in parking space recognition. For unconventional block parking spaces, please refer to Figure 3 , Figure 3 The block parking space schematic diagram provided in the first embodiment of the block parking space parking control method of the present application, the existing parking space detection method and parking method cannot well meet the requirements of the identification and parking of the block parking space, because the characteristics of the block parking space are different from those of the conventional parking space, and the size of the size frame is not strictly larger than the size of the vehicle, so special processing is required in the parking space detection and identification and parking control to meet the requirements of the block parking space. The solution of the present application is aimed at the block parking space scenario, and proposes a detection and parking control method for block parking spaces of different sizes.

[0066] In addition, it should be noted that when a parking space needs to be searched to control the parking of the vehicle, the camera will collect image information around the vehicle, and the parking space detection result will be determined based on the collected image information. When a parking space is detected in the collected image, the image around the vehicle will be spliced ​​to obtain a bird's-eye view of the parking space, which provides a global view of the block parking space, including information such as the location, shape and size of the block parking space.

[0067] It should be understood that, considering that the size of most block parking spaces is smaller than the vehicle itself, it is necessary to obtain the vehicle size information so as to infer a reasonable parking frame based on the vehicle size and block parking space information. The vehicle size information includes the length information and width information of the vehicle.

[0068] In a feasible implementation, step S10 may include: acquiring a fisheye image of a parking space; performing a dedistortion process on the fisheye image of the parking space, and performing a surround view mapping on the dedistorted fisheye image of the parking space to obtain a bird's-eye view of the parking space.

[0069] It should be noted that the four fisheye images (i.e., the parking space fisheye images) collected by the camera can be stitched together to obtain a bird's-eye view of the parking space. Considering the distortion effect of the fisheye image, the collected parking space fisheye image needs to be distorted to eliminate the extreme bending effect caused by the lens. After obtaining the de-distorted parking space fisheye image, the de-distorted parking space fisheye image can be registered by feature point matching or optical flow method to align them in the same coordinate system, and the registered images can be fused together using weighted average or maximum stitching method to generate a complete ring view, and the stitched ring view is perspective transformed and mapped to a bird's-eye view to obtain a bird's-eye view of the parking space.

[0070] For example, four pictures taken by fisheye cameras can be processed by Around View Monitor (AVM), dedistorted and then spliced ​​to obtain a bird's-eye view (FisheyeBEV), and the generated AVM spliced ​​bird's-eye view is the parking space bird's-eye view.

[0071] Step S20, determining block parking space center point information and block parking space marking point information based on the parking space bird's-eye view;

[0072] It should be understood that after obtaining the parking space bird's-eye view, an image processing algorithm can be used to extract the geometric features of the block parking space based on the parking space bird's-eye view to obtain the block parking space center point information and the block parking space marking point information. The block parking space center point information is the coordinate information of the center position of the detected block parking space, and the block parking space marking point information is the coordinate information of the corner point of the detected block parking space. Generally, the block parking space is considered to be a parallelogram, which is represented by four vertex coordinates (i.e., corner point coordinates).

[0073] For example, the parking space bird's-eye view image can be input into a YOLO10-based marker detector that has been pre-trained using a parking space data set. The marker detector will identify the block parking spaces in the image, mark the location and boundaries of each parking space, and extract key point information of the block parking spaces, such as the block parking space center point information and the block parking space corner point information. After the parking space bird's-eye view image is input into the YOLO10-based marker detector, the block parking space marker frame and the block parking space center point information will be obtained. In actual parking scenarios, it is not necessarily possible to identify the four corner points of the block parking space frame in the parking space bird's-eye view image. In this case, the detected corner point information of the block parking space, i.e., the block parking space marker point information, will be output.

[0074] Step S30, determining parking frame information and parking space type information based on at least one of the vehicle size information, the block parking space center point information, and the block parking space marking point information;

[0075] It should be noted that in actual parking scenarios, when searching for parking spaces, it is not necessarily possible to detect every corner point information of a block parking space. If the complete four corner point information of a block parking space is not detected, the corner point information of the non-marked points of the block parking space will be obtained by deep prior reasoning based on the detected block parking space corner point information, that is, the block parking space marking point information, and then the block parking space marking frame will be obtained. Considering that the size of most block parking spaces is smaller than the vehicle itself, the inferred block parking space marking frame will be enlarged by combining the vehicle size information and the block parking space center point information to obtain a parking frame suitable for the vehicle's parking needs, and then determine the parking frame information and parking space type information. The parking frame information must include the parking frame size information and the parking frame position information, and the parking space types include vertical parking spaces and parallel parking spaces.

[0076] In a feasible implementation, step S30 may include steps S31 to S33:

[0077] Step S31, determining the block parking space corner point information based on the block parking space mark point information;

[0078] It should be understood that the block parking space corner point information visible in the parking space bird's-eye view can be directly obtained based on the block parking space marking point information. For the case where the block parking space corner point information is not fully visible, the non-marked point information (i.e. the block parking space corner points that are invisible in the parking space bird's-eye view) can be inferred based on the visible block parking space corner point information, and then all the corner point information of the block parking spaces can be obtained.

[0079] In a feasible implementation, step S31 may include steps A11 to A13:

[0080] Step A11, when it is detected that the first corner point and the second corner point exist in the block parking space mark point information, and the third corner point and the fourth corner point do not exist, acquiring the block parking space depth information according to the parking space bird's-eye view;

[0081] It should be noted that each block parking space has four corner points, the first corner point and the second corner point are the points at both ends of a certain boundary line of the block parking space, the third corner point and the fourth corner point are the other two corner points in the block parking space that are different from the first corner point and the second corner point, the depth information of the block parking space is the length of the block parking space along the parking direction of the vehicle, and the depth information of the parking space is the vertical size of the block parking space, that is, the distance from the front boundary to the rear boundary of the block parking space. The depth information of the parking space can be detected using the FisheyeBEV image information.

[0082] Step A12, determining the third corner point and the fourth corner point based on the first corner point, the second corner point and the block parking space depth information;

[0083] It should be noted that if the first corner point and the second corner point are detected in the block parking space marking point information, when the third corner point and the fourth corner point do not exist in the detected block parking space marking point information, depth prior reasoning can be performed based on the first corner point, the second corner point and the block parking space depth information to obtain the third corner point and the fourth corner point to complete the block parking space marking box.

[0084] In a feasible implementation, step A12 may include: obtaining a unit vector from the first corner point to the second corner point; determining a third corner point based on the rotation matrix, the unit vector, the second corner point and the block parking space depth information; determining a fourth corner point based on the rotation matrix, the unit vector, the first corner point and the block parking space depth information.

[0085] For example, please refer to Figure 4 , Figure 4 A schematic diagram of corner point reasoning provided in the first embodiment of the block parking space control method of the present application. 1 and the second corner point P 2 , we can use the first corner point P 1 and the second corner point P 2 The coordinates of the first corner point P are calculated 1 To the second corner point P 2 The unit vector Then through the rotation matrix Unit Vector And the first corner point P 1 , the second corner point P 2 The coordinates and block parking space depth information d 1 Calculate the third corner point P respectively 3 and the fourth corner point P4 , the calculation formula is as follows:

[0086]

[0087] Step A13: taking the first corner point, the second corner point, the third corner point and the fourth corner point as block parking space corner point information.

[0088] It should be understood that the first corner point, the second corner point, the third corner point and the fourth corner point are complete block parking space corner point information.

[0089] Step S32, determining parking frame information based on the vehicle size information, the block parking space center point information, and the block parking space corner point information;

[0090] It should be understood that after obtaining the block parking space corner point information including the positions of all corner points of the block parking space, the completed block parking space marking frame can be obtained, because the size of the block parking space marking frame is often smaller than the size of the vehicle. At this time, the vehicle size information and the block parking space center point information are obtained, and the completed block parking space marking frame is scaled according to the vehicle size information to obtain a parking frame that meets the size of the vehicle, and the position information of the parking frame is determined according to the block parking space center point information to obtain the parking frame information. Specifically, a parking frame with the center point of the block parking space as the center point of the rectangle, parallel to the two side lines of the block parking space marking frame, and generated at 1.5 times the length and width of the vehicle can be used to plan the parking path. Please refer to Figure 5 , Figure 5 This is a block parking space detection result diagram provided in Example 1 of the block parking space parking control method of this application. Figure 5 As shown, the blue is a block parking space, the green border and the red center point are the block parking space marking frame and marking point generated by YOLO10, the blue outer frame is the parking frame formed based on the scaling of the vehicle size, and the marking points P1 and P2 are the parking frame marking points.

[0091] Step S33: determining parking space type information based on the block parking space marking point information.

[0092] It should be understood that when there are first corner points and second corner points in the block parking space marking point information, the prior information obtained based on the bird's-eye view of the parking space can be used to verify whether the block parking space dividing line connecting the first corner point and the second corner point is the boundary line in the block parking space used to mark the vehicle entering the parking space, that is, the entrance line, and the entrance line recognition result is obtained. According to the entrance line recognition result, it can be determined whether the block parking space is a parallel parking space or a vertical parking space, and the parking space type information of the block parking space is obtained.

[0093] In a feasible implementation, step S33 may include: obtaining block parking space width information and block parking space depth information based on the parking space bird's-eye view; determining entrance line information based on the block parking space marking point information; determining parking space type information based on the block parking space width information, the block parking space depth information and the entrance line information.

[0094] It should be understood that the block parking space width information w can be obtained according to the parking space bird's-eye view (i.e., Fisheye BEV map) 1 and block parking space depth information d 1 , where the width information is the horizontal size of the parking space, that is, the distance from one side boundary of the parking space to the other side boundary, and the depth information is the vertical size of the parking space, that is, the distance from the front end boundary to the rear end boundary of the parking space.

[0095] It should be noted that when there are two corner points P connecting a certain block parking space boundary line in the block parking space mark point information 1 , P 2 When the length of the boundary line connecting the two corner points is Respectively with the block parking space width information w 1 and block parking space depth information d 1 , compare and verify this P 1 , P 2 Whether the connected boundary line is an entrance line, if the result is no, deep prior reasoning can be performed based on the information of the two corner points to complete the block parking space mark frame, and the length information and position information of the entrance line can be determined from the completed block parking space mark frame to obtain the entrance line information. According to the length information of the entrance line, it can be judged whether the block parking space is a parallel parking space or a vertical parking space, and the parking space type information can be obtained.

[0096] Additionally, it should be understood that the determined entry line should be close to the width information w 1 , the entrance line length of the parallel parking space should be greater than the depth information d 1 , the length of the vertical parking space entrance line should be less than the depth information d 1 .

[0097] Step S40: Control the vehicle to park in a corresponding block parking space according to the parking frame information and the parking space type information.

[0098] It should be understood that after obtaining the parking frame information and parking space type information, the center point position of the parking frame can be determined according to the parking frame information, and the center point position of the parking frame can be used as the target parking position. The optimal path from the current vehicle position to the target parking frame is determined by the path planning algorithm, and the speed and direction are adjusted using a PID controller or MPC according to the parking space type information to ensure that the vehicle travels along the calculated path until the vehicle is parked in the corresponding block parking space.

[0099] This embodiment provides a method for controlling parking in a block parking space, which obtains a bird's-eye view of the parking space and the size information of the own vehicle, determines the center point information of the block parking space and the marking point information of the block parking space based on the bird's-eye view of the parking space, determines the parking frame information and the parking space type information based on the size information of the own vehicle, the center point information of the block parking space and at least one of the marking point information of the block parking space, and controls the own vehicle to park in the corresponding block parking space according to the parking frame information and the parking space type information. By determining the marking point information of the block parking space according to the bird's-eye view of the parking space, scaling the marked parking space outer frame based on the size information of the own vehicle and the marking point information of the block parking space, and outputting the scaled parking frame information and parking space type information, the parking path planning requirements of the own vehicle are met, and the problem of searching and parking in block parking spaces of different sizes is solved.

[0100] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 6 , step S40 may include steps S41 to S42:

[0101] Step S41, determining a parking path according to the parking frame information and the parking space type information;

[0102] It should be noted that after obtaining the parking frame information and parking space type information of the block parking space, when determining the parking path, the corresponding parking path composed of multiple arcs and straight lines can be calculated based on the parking frame position information, parking frame size information and parking space type information.

[0103] It should be understood that the parking frame position information is used to determine the initial position of the vehicle relative to the block parking space and the target parking position of the parking path. The parking frame size information is used to ensure that the parking path allows the vehicle to park in the parking space without colliding with other objects. For perpendicular parking spaces and parallel parking spaces, it can be determined based on the parking frame size information whether the vehicle needs to perform steering and reverse operations when parking in the block parking space.

[0104] Step S42: when it is detected that the parking path has no collision risk, the vehicle is controlled to park in a corresponding block parking space according to the parking path.

[0105] It should be understood that the various sensors (such as lidar and cameras) carried by the vehicle can be used to obtain surrounding environment data in real time and build an environmental model. After obtaining the parking path, the parking path will be evaluated for collision risk based on the location information of the parking path and the built environmental model. When it is detected that there are no obstacles (such as people, other vehicles, etc.) on the parking path, the initial speed, steering angle and braking strategy will be determined, and the vehicle will be controlled to park in the corresponding block parking space according to the parking path.

[0106] It should be noted that during the process of parking in the corresponding block parking space, the surrounding environment will be continuously monitored to prevent possible collisions and accidents. When an obstacle is detected during the parking process, it is determined whether to change or stop the parking operation based on the obstacle type, obstacle movement state and obstacle location information to ensure the safety of the parking control process.

[0107] This embodiment determines a parking path according to the parking frame information and the parking space type information. When it is detected that there is no collision risk in the parking path, the vehicle is controlled to park in the corresponding block parking space according to the parking path. In the process of controlling the vehicle to park in the block parking space, the collision risk of the parking path is identified, thereby ensuring the safety of the parking process.

[0108] For example, in order to help understand the implementation process of the block parking space parking control method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 7 , Figure 7 A brief flow chart of a parking control method for block parking spaces is provided, specifically:

[0109] When searching for parking spaces, the camera reads the surround images of the front, back, left, and right sides of the vehicle, dedistorts them, builds a surround map, and splices them to generate a FisheyeBEV visual map. The YOLO10 target detection model is used to detect parking spaces on the FisheyeBEV map, and the target box (i.e., the block parking space marking box) and the center point (i.e., the block parking space center point information) are output. If P is detected, 1 and P 2 point, cannot detect P 3 and P 4 If there are points, deep prior reasoning is performed to generate points P3 and P4, complete the parking space frame, and output the corrected parking frame, center point, parking space type, and entrance line, and generate a parking path. If a parking path without collision risk can be obtained, the detected block parking space and the generated parking path are output.

[0110] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the parking control method for block parking spaces of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0111] This application also provides a block parking space parking control device, please refer to Figure 8 , the block parking space parking control device comprises:

[0112] The information acquisition module 10 is used to obtain a bird's-eye view of the parking space and the size information of the vehicle;

[0113] A block parking space determination module 20, configured to determine block parking space center point information and block parking space marking point information based on the parking space bird's-eye view;

[0114] A parking frame determination module 30, configured to determine parking frame information and parking space type information based on at least one of the vehicle size information, the block parking space center point information, and the block parking space marking point information;

[0115] The parking control module 40 is used to control the vehicle to park in the corresponding block parking space according to the parking frame information and the parking space type information.

[0116] In one embodiment, the parking frame determination module 30 is further used to determine the block parking space corner point information based on the block parking space marking point information; determine the parking frame information based on the vehicle size information, the block parking space center point information and the block parking space corner point information; determine the parking space type information based on the block parking space marking point information.

[0117] In one embodiment, the parking box determination module 30 is further used to obtain block parking space depth information according to the parking space bird's-eye view when it is detected that there are a first corner point and a second corner point in the block parking space marking point information, but there are no third corner point and a fourth corner point; determine the third corner point and the fourth corner point based on the first corner point, the second corner point and the block parking space depth information; and use the first corner point, the second corner point, the third corner point and the fourth corner point as block parking space corner point information.

[0118] In one embodiment, the parking box determination module 30 is also used to obtain a unit vector from the first corner point to the second corner point; determine a third corner point based on the rotation matrix, the unit vector, the second corner point and the block parking space depth information; determine a fourth corner point based on the rotation matrix, the unit vector, the first corner point and the block parking space depth information.

[0119] In one embodiment, the parking frame determination module 30 is also used to obtain block parking space width information and block parking space depth information based on the parking space bird's-eye view; determine entrance line information based on the block parking space marking point information; determine parking space type information based on the block parking space width information, the block parking space depth information and the entrance line information.

[0120] In one embodiment, the information acquisition module 10 is further used to acquire a fisheye image of a parking space; perform dedistortion processing on the fisheye image of the parking space, and perform surround mapping on the dedistorted fisheye image of the parking space to obtain a bird's-eye view of the parking space.

[0121] In one embodiment, the parking control module 40 is further used to determine a parking path according to the parking frame information and the parking space type information; when it is detected that there is no collision risk on the parking path, control the vehicle to park in the corresponding block parking space according to the parking path.

[0122] The block parking space parking control device provided by the present application adopts the block parking space parking control method in the above embodiment, and can solve the technical problem of how to perform parking control based on block parking spaces of different sizes. Compared with the prior art, the beneficial effects of the block parking space parking control device provided by the present application are the same as the beneficial effects of the block parking space parking control method provided by the above embodiment, and other technical features of the block parking space parking control device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0123] The present application provides a block parking space parking control device, which includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the block parking space parking control method in the above-mentioned embodiment 1.

[0124] Reference below Fig. 9 , which shows a schematic diagram of the structure of a block parking space parking control device suitable for implementing the embodiment of the present application. The block parking space parking control device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9 The block-shaped parking space parking control device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0125] like Fig. 9As shown, the block parking space parking control device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the block parking space parking control device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the block parking control device to communicate with other devices wirelessly or by wire to exchange data. Although the block parking control device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0126] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0127] The block parking space parking control device provided by the present application adopts the block parking space parking control method in the above embodiment, which can solve the technical problem of how to perform parking control based on block parking spaces of different sizes. Compared with the prior art, the beneficial effects of the block parking space parking control device provided by the present application are the same as the beneficial effects of the block parking space parking control method provided by the above embodiment, and other technical features in the block parking space parking control device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0128] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0129] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0130] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the block parking space parking control method in the above-mentioned embodiment.

[0131] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0132] The computer-readable storage medium may be included in the block parking space parking control device; or may exist independently without being assembled into the block parking space parking control device.

[0133] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the block parking space parking control device, the block parking space parking control device: obtains a bird's-eye view of the parking space and the size information of the own vehicle; determines the center point information of the block parking space and the marking point information of the block parking space based on the bird's-eye view of the parking space; determines the parking frame information and the parking space type information based on at least one of the size information of the own vehicle, the center point information of the block parking space and the marking point information of the block parking space; and controls the own vehicle to park in the corresponding block parking space according to the parking frame information and the parking space type information.

[0134] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0135] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0137] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned block parking space parking control method, and can solve the technical problem of how to perform parking control based on block parking spaces of different sizes. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the block parking space parking control method provided in the above-mentioned embodiment, and will not be repeated here.

[0138] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned block parking space parking control method when executed by a processor.

[0139] The computer program product provided in this application can solve the technical problem of how to control parking based on block parking spaces of different sizes. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the block parking control method provided in the above embodiment, which will not be repeated here.

[0140] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A parking control method for block parking spaces, characterized in that: The block parking space parking control method comprises: Get a bird's-eye view of parking spaces and information about your vehicle's dimensions; Determine block parking space center point information and block parking space marking point information based on the parking space bird's-eye view; Determine parking frame information and parking space type information based on at least one of the vehicle size information, the block parking space center point information, and the block parking space marking point information; The vehicle is controlled to park in a corresponding block parking space according to the parking frame information and the parking space type information.

2. The method according to claim 1, characterized in that The step of determining the parking frame information and the parking space type information based on at least one of the vehicle size information, the block parking space center point information, and the block parking space marking point information comprises: Determine the block parking space corner point information based on the block parking space mark point information; Determine parking frame information based on the vehicle size information, the block parking space center point information, and the block parking space corner point information; The parking space type information is determined based on the block parking space marking point information.

3. The method according to claim 2, characterized in that The step of determining the block parking space corner point information based on the block parking space marking point information comprises: When it is detected that the first corner point and the second corner point exist in the block parking space mark point information, and the third corner point and the fourth corner point do not exist, acquiring the block parking space depth information according to the parking space bird's-eye view; Determine the third corner point and the fourth corner point based on the first corner point, the second corner point and the block parking space depth information; The first corner point, the second corner point, the third corner point and the fourth corner point are used as block parking space corner point information.

4. The method according to claim 3, characterized in that The step of determining the third corner point and the fourth corner point based on the first corner point, the second corner point and the block parking space depth information comprises: Get a unit vector from the first corner point to the second corner point; Determine a third corner point based on the rotation matrix, the unit vector, the second corner point and the block parking space depth information; A fourth corner point is determined based on the rotation matrix, the unit vector, the first corner point, and the block parking space depth information.

5. The method according to claim 2, characterized in that The step of determining the parking space type information based on the block parking space marking point information comprises: Acquire block parking space width information and block parking space depth information according to the parking space bird's-eye view; Determine the entrance line information based on the block parking space marking point information; The parking space type information is determined according to the block parking space width information, the block parking space depth information and the entrance line information.

6. The method according to claim 1, characterized in that The step of obtaining a bird's-eye view of a parking space comprises: Get the fisheye image of the parking space; The fisheye image of the parking space is subjected to a dedistortion process, and a surround map is constructed on the dedistorted fisheye image of the parking space to obtain a bird's-eye view of the parking space.

7. The method according to any one of claims 1 to 6, characterized in that The step of controlling the vehicle to park in the corresponding block parking space according to the parking frame information and the parking space type information comprises: determining a parking path according to the parking frame information and the parking space type information; When it is detected that the parking path has no collision risk, the vehicle is controlled to park in the corresponding block parking space according to the parking path.

8. A parking control device for a block parking space, characterized in that: The device comprises: An information acquisition module is used to obtain a bird's-eye view of parking spaces and vehicle size information; A block parking space determination module, used to determine block parking space center point information and block parking space marking point information based on the parking space bird's-eye view; A parking frame determination module, used to determine parking frame information and parking space type information based on at least one of the vehicle size information, the block parking space center point information and the block parking space marking point information; The parking control module is used to control the vehicle to park in the corresponding block parking space according to the parking frame information and the parking space type information.

9. A parking control device for block parking spaces, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the block parking space parking control method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the block parking space parking control method according to any one of claims 1 to 7 are implemented.

Images