CN-119132102-B - Parking space detection method, controller, vehicle and computer readable storage medium

CN119132102BCN 119132102 BCN119132102 BCN 119132102BCN-119132102-B

Abstract

The invention relates to the technical field of vehicles, in particular to a parking space detection method, a controller, a vehicle and a computer readable storage medium, wherein the method acquires a ground image and extracts lane lines in the ground image; according to the geometric information of the lane lines, at least one corner point is obtained, wherein the corner point is an intersection point formed by intersecting the lane lines, the corner points of the parking spaces representing the parking spaces are determined from all the corner points, and the parking space information is determined according to the corner points of the parking spaces and the lane lines, so that real-time parking space detection on a low-calculation-force platform is realized, and the efficiency and the accuracy of parking space detection are improved.

Inventors

ZHANG JUN
YANG DONGSHENG
HAN BING
SU QI
ZHANG QIAN

Assignees

比亚迪股份有限公司

Dates

Publication Date: 20260505
Application Date: 20230612

Claims (11)

1. The parking space detection method is characterized by comprising the following steps of: Acquiring a ground image, and extracting lane lines in the ground image; Obtaining at least one corner point according to the geometric information of the lane lines, wherein the corner point is a point formed by intersecting the lane lines; determining parking space corner points representing the parking space from all the corner points; Determining parking space information according to the parking space corner points and the lane lines; determining the parking space corner points for representing the parking space from all the corner points comprises the following steps: For any corner point, respectively acquiring the direction and the length of each lane line, constructing a polygonal area of each lane line, acquiring the brightness mean value and the brightness variance of the polygonal area, and detecting whether the two lane lines are intersected or not; acquiring the angular point type confidence coefficient corresponding to each preset angular point type of the angular point according to the direction, the length, the brightness mean value, the brightness variance and the detection value; obtaining intersection scores and included angle scores between two lane lines, and obtaining the corner confidence of the corner according to the corner type confidence, the intersection scores and the included angle scores, wherein the calculation expression of the corner confidence is as follows: Wherein, the For the angular point confidence, the value range of the angular point confidence is 0,1, For the degree of confidence of the corner type, In order for the intersection score to be a fraction, Is the fraction of the included angle; If the angular point confidence coefficient is detected to be not smaller than the preset angular point confidence coefficient threshold value, confirming that the corresponding angular point is a parking space angular point.
2. The parking space detection method according to claim 1, wherein the parking space information includes a first parking space coordinate of a parking space in an image coordinate system, and further comprising: and converting the first vehicle position coordinate into a second vehicle position coordinate of the vehicle position under the world coordinate system according to the conversion relation between the image coordinate system of the ground image and the world coordinate system.
3. The parking space detection method according to claim 1, wherein the extracting lane lines in the ground image comprises: The method comprises the steps of extracting lane edge lines in a ground image, clustering the lane edge lines to obtain at least one cluster, clustering each cluster to obtain target lane edge lines corresponding to each cluster, and determining the lane lines based on the target lane edge lines and endpoints of the target lane edge lines.
4. The parking space detection method according to claim 3, wherein the clustering each cluster to obtain the target lane edge line corresponding to each cluster includes: for any cluster, calculating the distance between any two lane edge lines respectively; for any distance, detecting whether the distance is smaller than a preset distance threshold value, and if the distance is detected to be smaller than the preset distance threshold value, taking two lane edge lines corresponding to the distance as first lane edge lines; Acquiring all first lane edge lines in the cluster, respectively calculating the length of each first lane edge line in the cluster, and selecting one first lane edge line in the cluster as a target lane edge line according to the length.
5. The parking space detection method according to claim 1, wherein the extracting the lane lines in the ground image comprises: And aiming at any lane line, acquiring an edge parallel score and an edge distance score of the lane line, and calculating the lane line confidence coefficient of the lane line according to the edge parallel score and the edge distance score.
6. The parking space detection method according to claim 1, wherein the obtaining at least one corner point according to the geometric information of the lane line comprises: Optionally, two lane lines are used as target lane lines, whether the target lane lines intersect or not is detected based on the positions of the target lane lines, and if the intersection between the target lane lines is detected, the intersection between the target lane lines is used as an angular point.
7. The parking space detection method according to claim 1, wherein determining parking space information from the parking space corner points and the lane lines comprises: Acquiring angular point information of all the angular points of the parking spaces and geometric information of all the lane lines, and constructing at least one parking space according to the angular point information of all the angular points of the parking spaces and the geometric information of all the lane lines; aiming at any parking place, calculating the parking place position degree of the parking place according to the corner information of the parking place corner corresponding to the parking place and the geometric information of the lane line; and acquiring a parking space corresponding to the parking space position degree not smaller than a preset parking space position degree threshold as a target parking space, and determining parking space information of the target parking space.
8. The method for detecting a parking space according to claim 7, wherein calculating the parking space position of the parking space according to the corner information of the corner of the parking space corresponding to the parking space and the geometric information of the lane lines comprises: calculating to obtain a parking space morphology score of the parking space according to the corner information of the parking space corner corresponding to the parking space and the geometric information of the lane line, calculating to obtain a corner distance score of the parking space according to the corner information of the parking space corner corresponding to the parking space, and calculating to obtain a lane line confidence coefficient of the parking space according to the geometric information of the lane line of the parking space; And calculating the parking position degree of the parking position according to the parking position morphology score, the corner distance score, the corner type confidence degree and the lane line confidence degree of the parking position.
9. A controller comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the parking spot detection method according to any one of claims 1 to 8 when executing the computer program.
10. A vehicle comprising an image acquisition device for acquiring an image and the controller of claim 9.
11. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the parking space detection method according to any one of claims 1 to 8.

Description

Parking space detection method, controller, vehicle and computer readable storage medium Technical Field The present invention relates to the field of vehicle technologies, and in particular, to a parking space detection method, a controller, a vehicle, and a computer readable storage medium. Background In recent years, with the development of automobile intellectualization, an automatic parking technology is popularized and applied in various scenes, the automatic parking technology can enable an automobile to automatically find and accurately park at a proper parking position, and corresponding parking space detection becomes a core sensing module in the automatic parking technology. In the related art, the pure vision parking space detection method based on the neural network model is favored by related practitioners, but the application of the neural network model has higher and higher calculation power requirements on a vehicle platform. Disclosure of Invention In view of the above, the embodiments of the present invention provide a parking space detection method, a controller, a vehicle, and a computer readable storage medium, so as to solve the problem that a vehicle platform cannot meet a high calculation force requirement. In a first aspect, an embodiment of the present invention provides a parking space detection method, where the parking space detection method includes acquiring a ground image, and extracting lane lines in the ground image; Obtaining at least one corner point according to the geometric information of the lane lines, wherein the corner point is a point formed by intersecting the lane lines; determining parking space corner points representing the parking space from all the corner points; and determining parking space information according to the parking space corner points and the lane lines. In a second aspect, an embodiment of the present invention provides a controller, where the controller includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the parking space detection method according to the first aspect when executing the computer program. In a third aspect, a vehicle comprises an image acquisition device for acquiring an image and a controller according to the second aspect. In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the parking space detection method according to the first aspect. Compared with the prior art, the embodiment of the invention has the beneficial effects that: The method comprises the steps of obtaining a ground image, extracting lane lines in the ground image, obtaining at least one corner point according to geometric information of the lane lines, determining a parking space corner point representing a parking space from all the corner points, and determining parking space information according to the parking space corner point and the lane lines, so that real-time parking space detection on a low-calculation-force platform is realized, and the efficiency and accuracy of parking space detection are improved. Drawings In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Fig. 1 is a schematic flow chart of a parking space detection method according to an embodiment of the present invention; fig. 2 is an extraction schematic diagram of a lane edge line according to a first embodiment of the present invention; Fig. 3 is a schematic drawing illustrating the extraction of a lane line according to a first embodiment of the present invention; Fig. 4 is a schematic diagram of parking space corner detection according to a first embodiment of the present invention; FIG. 5 is a schematic diagram showing the correlation between the edge line spacing of lane lines and the lane line confidence according to the first embodiment of the present invention; fig. 6 is a schematic structural diagram of a vehicle according to a second embodiment of the present invention; fig. 7 is a schematic structural diagram of a controller according to a third embodiment of the present invention. Detailed Description In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present i