Optimization Method and System for Parking Space Line Detection Based on Fisheye Images

Abstract

The present invention discloses an optimized method and system for detecting parking space lines based on fisheye images. It corrects the distortion of the inner edge line of the parking space line through a fisheye camera, searches for undistorted sampling points of the inner edge line according to the search range of the parking space line width based on the corrected inner edge line, divides the undistorted sampling points of the inner edge line into inner edge points and outer edge points through fitting correction, and uses the inner edge points to perform linear fitting to obtain the actual inner edge line of the parking space line. The optimized method for detecting parking space lines based on fisheye images only relies on cameras and traditional algorithms, has a relatively low recognition cost, simplifies the correction process, and only uses inner edge points for linear fitting, excluding the interference of outer points formed by other reasons such as line stains and shadows on the linear fitting of its inner edge line, so as to improve the recognition accuracy.

Description

Technical Field

[0001] The present invention relates to the technology of automatic parking space recognition, and in particular to an optimized method and system for detecting parking space lines based on a fisheye image. Background Art

[0002] For automatic parking, the vehicle to be parked uses on-vehicle sensors to collect information around the vehicle, transmits the collected information to the perception module for analysis to obtain target points, and then the planning module calculates the parking trajectory based on the target points analyzed by the perception module. Finally, the control module controls the vehicle to park in the parking space.

[0003] Since the cost of the camera is relatively low and the information collected around the vehicle is relatively rich, most of the current perception and recognition algorithm methods rely on vision. The fisheye lens is a kind of fixed-focus lens with a very large field of view, and the viewing angle is usually greater than 180°, resulting in large image distortion. Therefore, most of the parking space detection algorithms perform distortion correction on the fisheye image and then convert it into a bird's-eye view for parking space detection. Considering that there are errors in calculating the distortion coefficient during distortion correction and there is a stretching phenomenon for objects far from the camera center when converting to a bird's-eye view. Therefore, some parking space detection schemes will convert the bird's-eye view back into a fisheye image and perform parking space correction in the fisheye image.

[0004] During the fisheye image correction process, the general algorithm will identify the inner border and outer border of the parking space line, and then use the inner border as the starting point for correction and correct it horizontally towards the outer border. The correction method is to calculate the difference between adjacent pixels. Since the pixel difference between the parking space line and the ground is the largest, the pixel coordinates with large pixel differences will be set as the edge points for parking space correction, and then the corrected parking space points will be converted into the bird's-eye view for line fitting. The fitted line is the corrected parking space line. However, in addition to the large pixel value differences at the edge of the parking space line, if there are shadows and stains inside the parking space line, the calculated pixel differences will also be large. If the stains and shadow points are referred to during line fitting, there will be large errors in the fitted parking space line points. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above technical deficiencies, and propose an optimized method and system for detecting parking space lines based on a fisheye image, so as to solve the problem that there are large errors in the fitted parking space line points when referring to stains and shadow points in the existing line fitting.

[0006] To achieve the above technical purpose, the first aspect of the technical solution of the present invention provides an optimized method for detecting parking space lines based on a fisheye image, which includes the following steps:

[0007] Perform distortion correction on the fisheye image of the parking space line and convert it into a bird's-eye view, and extract the inner edge line of the parking space line in the bird's-eye view;

[0008] Determine the undistorted inner edge sampling points and the preset sampling points of the outer edge in the bird's-eye view, and project the inner edge sampling points and the preset sampling points of the outer edge into the fisheye view;

[0009] Search within the range between the inner edge sampling points and the preset sampling points of the outer edge in the fisheye view, and extract the undistorted inner edge sampling points based on the pixel difference between adjacent search points;

[0010] Project the undistorted inner edge sampling points into the bird's-eye view, use the method of line fitting based on RANSAC to distinguish the inliers and outliers of the undistorted inner edge sampling points, and use the inliers for line fitting to obtain the actual inner edge of the parking space line.

[0011] The second aspect of the present invention provides an optimized system for detecting parking space lines based on a fisheye view, which includes the following functional modules:

[0012] An inner edge extraction module, which is used to correct the distortion of the fisheye view of the parking space line and convert it into a bird's-eye view, and extract the inner edge of the parking space line in the bird's-eye view;

[0013] An outer edge determination module, which is used to determine the undistorted inner edge sampling points and the preset sampling points of the outer edge in the bird's-eye view, and project the inner edge sampling points and the preset sampling points of the outer edge into the fisheye view;

[0014] A sampling point extraction module, which is used to search within the range between the inner edge sampling points and the preset sampling points of the outer edge in the fisheye view, and extract the undistorted inner edge sampling points based on the pixel difference between adjacent search points;

[0015] An inlier line fitting module, which is used to project the undistorted inner edge sampling points into the bird's-eye view, use the method of line fitting based on RANSAC to distinguish the inliers and outliers of the undistorted inner edge sampling points, and use the inliers for line fitting to obtain the actual inner edge of the parking space line.

[0016] The third aspect of the present invention provides a server, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned optimized method for detecting parking space lines based on a fisheye view.

[0017] The fourth aspect of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned optimized method for detecting parking space lines based on a fisheye view.

[0018] Compared with the prior art, the optimized method for detecting parking space lines based on a fisheye image in the present invention corrects the distortion of the inner edge line of the parking space line through a fisheye camera, searches for distortion-corrected sampling points of the inner edge line according to the search range of the width of the parking space line, divides the distortion-corrected sampling points of the inner edge line into inner edge points and outer edge points through fitting correction, and uses the inner edge points to perform linear fitting to obtain the actual inner edge line of the parking space line. The optimized method for detecting parking space lines based on a fisheye image only relies on a camera and traditional algorithms, has a low recognition cost, simplifies the correction process, and only uses inner edge points for linear fitting to exclude the interference of outer points formed by other reasons such as line stains and shadows on the linear fitting of its inner edge line, so as to improve the recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flowchart of an optimized method for detecting parking space lines based on a fisheye image according to an embodiment of the present invention;

[0020] Figure 2 is a sub-step flowchart of step S2 in an optimized method for detecting parking space lines based on a fisheye image according to an embodiment of the present invention;

[0021] Figure 3 is a sub-step flowchart of step S3 in an optimized method for detecting parking space lines based on a fisheye image according to an embodiment of the present invention;

[0022] Figure 4 is a sub-step flowchart of step S4 in an optimized method for detecting parking space lines based on a fisheye image according to an embodiment of the present invention;

[0023] Figure 5 is a block diagram of a system for optimizing the detection of parking space lines based on a fisheye image according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0025] As Figures 1 to 4 shown, an embodiment of the present invention provides an optimized method for detecting parking space lines based on a fisheye image, which includes the following steps:

[0026] S1. Correct the distortion of the fisheye image of the parking space line and convert it into a bird's-eye view, and extract the inner edge line of the parking space line in the bird's-eye view.

[0027] Due to the large imaging distortion of the fisheye lens, it is necessary to rectify the fisheye image, and then convert it into a bird's-eye view for parking space detection. The inner edge line of the parking space line is extracted. The inner edge line of the parking space line is as Figure 1 shown.

[0028] S2. Determine the rectified inner edge line sampling points and the preset sampling points of the outer edge line in the bird's-eye view, and project the inner edge line sampling points and the preset sampling points of the outer edge line into the fisheye image.

[0029] That is, extract the inner edge line sampling points from the inner edge line, search for the preset sampling points of the outer edge line based on the inner edge line sampling points and the width of the parking line, and project the inner edge line sampling points and the preset sampling points of the outer edge line into the fisheye image.

[0030] Specifically as Figure 2 shown, the step S2 includes the following sub-steps:

[0031] S21. Divide the inner edge line of the parking space line equally to obtain the inner edge line sampling points;

[0032] S22. Set the inner edge line sampling points as the starting points for edge search, and search outward with the width of the parking line. The end points of the edge search obtained are the preset sampling points of the outer edge line;

[0033] S23. According to the camera internal parameters and the distortion coefficients of the camera, project the inner edge line sampling points and the preset sampling points of the outer edge line into the fisheye image.

[0034] S3. Search within the range between the inner edge line sampling points and the preset sampling points of the outer edge line in the fisheye image, and extract the rectified inner edge line sampling points based on the pixel difference between adjacent search points.

[0035] Specifically as Figure 3 shown, the step S3 includes the following sub-steps:

[0036] S31. Search outward from the inner edge line sampling points within the range between the inner edge line sampling points and the preset sampling points of the outer edge line in the fisheye image;

[0037] S32. Calculate the pixel difference between adjacent search points, and set the search points with a line pixel difference greater than the set threshold and being negative as the rectified inner edge line sampling points.

[0038] S4. Project the rectified inner edge line sampling points into the bird's-eye view, use the method of line fitting based on RANSAC to distinguish the inliers and outliers of the rectified inner edge line sampling points, and use the inliers for line fitting to obtain the actual inner edge line of the parking space line.

[0039] Among them, the method of using the line fitting based on RANSAC to distinguish the inliers and outliers of the rectified inner edge line sampling points specifically includes:

[0040] Take any two de - distorted sampling points on the inner edge line to calculate a straight line, and calculate the distance between the remaining de - distorted sampling points on the inner edge line and this straight line. If the distance is greater than the preset threshold distance, it is classified as an outlier; if the distance is less than the preset threshold distance, it is classified as an inlier.

[0041] As Figure 4 shown, step S4 includes the following sub - steps:

[0042] S41. Project the de - distorted sampling points on the inner edge line into the bird's - eye view. Take any two de - distorted sampling points on the inner edge line to calculate a straight line, and calculate the distance between the remaining de - distorted sampling points on the inner edge line and this straight line. If the distance is greater than the preset threshold distance, it is classified as an outlier; if the distance is less than the preset threshold distance, it is classified as an inlier.

[0043] S42. Organize the inlier point sets obtained by distinguishing each straight line, and select the point set with the largest number of inliers for straight - line fitting to obtain the vertical line of the corrected inner edge line.

[0044] S43. Set the intersection point of the horizontal line of the original inner edge line of the parking space line and the vertical line of the corrected inner edge line as the new parking space.

[0045] Among them, the number of inliers in the inlier point set selected for straight - line fitting must be greater than 2.

[0046] In the embodiment of the present invention, a method for optimizing the detection of parking space lines based on a fisheye image corrects the distortion of the inner edge line of the parking space line, derives the preset sampling points of the outer edge line according to the de - distorted sampling points of the inner edge line, and searches for the de - distorted sampling points of the inner edge line within the range between the sampling points of the inner edge line and the preset sampling points of the outer edge line; distinguishes the inner and outer points of the de - distorted sampling points of the inner edge line in the bird's - eye view, and uses the inliers for straight - line fitting to obtain the actual inner edge line of the parking space line.

[0047] In the embodiment of the present invention, a method for optimizing the detection of parking space lines based on a fisheye image corrects the distortion of the inner edge line of the parking space line through a fisheye camera, searches for the de - distorted sampling points of the inner edge line according to the search range of the parking space line width based on the corrected inner edge line, divides the de - distorted sampling points of the inner edge line into inner edge points and outer edge points through fitting correction, and uses the inner edge points for straight - line fitting to obtain the actual inner edge line of the parking space line. The method for optimizing the detection of parking space lines based on a fisheye image only depends on the camera and traditional algorithms, has a low recognition cost, simplifies the correction process, and only uses the inner edge points for straight - line fitting to exclude the interference of outliers formed by other reasons such as line stains and shadows on the straight - line fitting of its inner edge line, so as to improve the recognition accuracy.

[0048] As Figure 5 shown, the embodiment of the present invention also discloses a system for optimizing the detection of parking space lines based on a fisheye image, which includes the following functional modules:

[0049] The inner edge line extraction module 10 is used to correct the distortion of the fisheye image of the parking space line and convert it into a bird's-eye view image, and extract the inner edge line of the parking space line in the bird's-eye view image;

[0050] The outer edge line determination module 20 is used to determine the sampling points of the undistorted inner edge line and the preset sampling points of the outer edge line in the bird's-eye view image, and project the sampling points of the inner edge line and the preset sampling points of the outer edge line into the fisheye image;

[0051] The sampling point extraction module 30 is used to search within the range between the sampling points of the inner edge line and the preset sampling points of the outer edge line in the fisheye image, and extract the undistorted sampling points of the inner edge line based on the pixel difference between adjacent search points;

[0052] The inner point straight line fitting module 40 is used to project the undistorted sampling points of the inner edge line into the bird's-eye view image, use the method of straight line fitting based on ransac to distinguish the inner and outer points of the undistorted sampling points of the inner edge line, and use the inner points to perform straight line fitting to obtain the actual inner edge line of the parking space line.

[0053] The execution manner of the parking space line detection and optimization system based on the fisheye image in this embodiment is basically the same as the above-mentioned parking space line detection and optimization method based on the fisheye image, so it will not be elaborated in detail.

[0054] The server in this embodiment is a device that provides computing services, usually referring to a computer with relatively high computing power and provided to multiple consumers through a network. The server of this embodiment includes: a memory, a processor, and a system bus. The memory includes a program that can run stored thereon. Those skilled in the art can understand that the structure of the terminal device in this embodiment does not constitute a limitation on the terminal device, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0055] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing of the terminal by running the software programs and modules stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, applications required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the terminal (such as audio data, phone book, etc.). In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0056] A runnable program containing an optimized method for detecting parking space lines based on a fisheye image is stored in a memory. The runnable program can be divided into one or more modules / units, which are stored in the memory and executed by a processor to complete the acquisition of information and the implementation process. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the server. For example, the computer program can be divided into an inner edge extraction module 10, an outer edge determination module 20, a sampling point extraction module 30, and an inner point straight line fitting module 40.

[0057] The processor is the control center of the server, connecting various parts of the entire terminal device through various interfaces and lines. By running or executing software programs and / or modules stored in the memory, and by invoking data stored in the memory, it executes various functions of the terminal and processes data, thereby monitoring the terminal as a whole. Optionally, the processor may include one or more processing units; preferably, the processor may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor.

[0058] The system bus is used to connect various functional components inside the computer, and can transmit data information, address information, and control information. Its types can be, for example, PCI bus, ISA bus, VESA bus, etc. The instructions of the processor are transmitted to the memory through the bus, and the memory feeds back data to the processor. The system bus is responsible for the data and instruction interaction between the processor and the memory. Of course, the system bus can also be connected to other devices, such as network interfaces, display devices, etc.

[0059] The server should at least include a CPU, a chipset, a memory, a disk system, etc. Other components will not be elaborated here.

[0060] In the embodiment of the present invention, the runnable program executed by the processor included in the terminal is specifically: an optimized method for detecting parking space lines based on a fisheye image, which includes the following steps:

[0061] Perform distortion correction on the fisheye image of the parking space line and convert it into a bird's-eye view, and extract the inner edge of the parking space line in the bird's-eye view;

[0062] Determine the undistorted inner edge sampling points and the preset outer edge sampling points in the bird's-eye view, and project the inner edge sampling points and the preset outer edge sampling points onto the fisheye image;

[0063] Search within the range between the sampling points on the inner boundary line of the fisheye image and the preset sampling points on the outer boundary line, and extract the undistorted sampling points of the inner boundary line based on the pixel differences between adjacent search points.

[0064] Project the undistorted sampling points of the inner boundary line into the bird's-eye view, use the method of line fitting based on RANSAC to distinguish the inliers and outliers of the undistorted sampling points of the inner boundary line, and use the inliers to perform line fitting to obtain the actual inner boundary line of the parking space.

[0065] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0066] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0067] Those of ordinary skill in the art can realize that the modules, units, and / or method steps of the various embodiments described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0068] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An optimized method for detecting parking space lines based on fisheye images, characterized in that, It includes the following steps: Perform distortion correction on the fisheye image of the parking line and convert it into a bird's-eye view image, and extract the inner edge line of the parking line in the bird's-eye view image; Determine the undistorted inner edge line sampling points and the preset sampling points of the outer edge line in the bird's-eye view image, and project the inner edge line sampling points and the preset sampling points of the outer edge line into the fisheye image; Search within the range between the inner edge line sampling points and the preset sampling points of the outer edge line in the fisheye image, and extract the undistorted inner edge line sampling points based on the pixel difference between adjacent search points; Project the undistorted inner edge line sampling points into the bird's-eye view image, use the method of line fitting based on ransac to distinguish the inliers and outliers of the undistorted inner edge line sampling points, and use the inliers for line fitting to obtain the actual inner edge line of the parking line; The method of using the line fitting based on ransac to distinguish the inliers and outliers of the undistorted inner edge line sampling points specifically includes: Take any two undistorted inner edge line sampling points to calculate a straight line, calculate the distance between the remaining undistorted inner edge line sampling points and this straight line. If the distance is greater than the preset threshold distance, it is classified as an outlier. If the distance is less than the preset threshold distance, it is classified as an inlier; The method of projecting the undistorted inner edge line sampling points into the bird's-eye view image, using the method of line fitting based on ransac to distinguish the inliers and outliers of the undistorted inner edge line sampling points, and using the inliers for line fitting to obtain the actual inner edge line of the parking line specifically includes: Project the undistorted inner edge line sampling points into the bird's-eye view image, take any two undistorted inner edge line sampling points to calculate a straight line, calculate the distance between the remaining undistorted inner edge line sampling points and this straight line. If the distance is greater than the preset threshold distance, it is classified as an outlier. If the distance is less than the preset threshold distance, it is classified as an inlier; Sort out the inlier point sets obtained by distinguishing each straight line, and select the point set with the largest number of inliers for line fitting to obtain the vertical line of the corrected inner edge line; Set the intersection point of the horizontal line of the original inner edge line of the parking line and the vertical line of the corrected inner edge line as the new parking space.

2. The optimized method for detecting parking space lines based on a fisheye image according to claim 1, wherein The step of determining the undistorted inner edge line sampling points and the preset sampling points of the outer edge line in the bird's-eye view image, and projecting the inner edge line sampling points and the preset sampling points of the outer edge line into the fisheye image includes: Extract the inner edge line sampling points from the inner edge line, search for the preset sampling points of the outer edge line based on the inner edge line sampling points and the width of the parking line, and project the inner edge line sampling points and the preset sampling points of the outer edge line into the fisheye image.

3. The optimized method for detecting parking space lines based on fisheye images according to claim 2, characterized in that, The step of extracting the inner edge line sampling points from the inner edge line, searching for the preset sampling points of the outer edge line based on the inner edge line sampling points and the width of the parking line, and projecting the inner edge line sampling points and the preset sampling points of the outer edge line into the fisheye image specifically includes: Equally divide the inner edge line of the parking line to obtain the inner edge line sampling points; Set the inner edge line sampling points as the starting points of edge search, and search outward with the width of the parking line. The ending points of edge search obtained are the preset sampling points of the outer edge line; According to the camera internal parameters and the distortion coefficients of the camera, project the inner edge line sampling points and the preset sampling points of the outer edge line into the fisheye image.

4. A method for optimizing the detection of parking space lines based on fisheye images according to claim 1, characterized in that, Search within the range between the sampling points on the inner boundary line of the fisheye image and the preset sampling points on the outer boundary line, and extract the undistorted sampling points of the inner boundary line based on the pixel difference between adjacent search points. Specifically, it includes: Search outward from the sampling points on the inner boundary line of the fisheye image within the range between the sampling points on the inner boundary line and the preset sampling points on the outer boundary line; Calculate the pixel difference between adjacent search points, and set the search points where the line pixel difference is greater than the set threshold and is negative as the undistorted sampling points of the inner boundary line.

5. The optimized method for detecting parking space lines based on a fish-eye image according to claim 1, wherein The number of inliers in the inlier point set selected for line fitting must be greater than 2.

6. An optimized system for detecting parking space lines based on fisheye images, characterized in that, It includes the following functional modules: Inner boundary line extraction module, used to correct the distortion of the fisheye image of the parking space line and convert it into a bird's-eye view, and extract the inner boundary line of the parking space line in the bird's-eye view; Outer boundary line determination module, used to determine the undistorted sampling points of the inner boundary line and the preset sampling points of the outer boundary line in the bird's-eye view, and project the sampling points of the inner boundary line and the preset sampling points of the outer boundary line onto the fisheye image; Sampling point extraction module, used to search within the range between the sampling points on the inner boundary line of the fisheye image and the preset sampling points on the outer boundary line, and extract the undistorted sampling points of the inner boundary line based on the pixel difference between adjacent search points; Inlier line fitting module, used to project the undistorted sampling points of the inner boundary line onto the bird's-eye view, use the method of line fitting based on ransac to distinguish inliers and outliers from the undistorted sampling points of the inner boundary line, and use the inliers to perform line fitting to obtain the actual inner boundary line of the parking space line; The method of using the line fitting based on ransac to distinguish inliers and outliers from the undistorted sampling points of the inner boundary line specifically includes: Take any two undistorted sampling points of the inner boundary line to calculate a straight line, calculate the distance between the remaining undistorted sampling points of the inner boundary line and this straight line. If the distance is greater than the preset threshold distance, it is classified as an outlier. If the distance is less than the preset threshold distance, it is classified as an inlier; The method of projecting the undistorted sampling points of the inner boundary line onto the bird's-eye view, using the method of line fitting based on ransac to distinguish inliers and outliers from the undistorted sampling points of the inner boundary line, and using the inliers to perform line fitting to obtain the actual inner boundary line of the parking space line specifically includes: Project the undistorted sampling points of the inner boundary line onto the bird's-eye view, take any two undistorted sampling points of the inner boundary line to calculate a straight line, calculate the distance between the remaining undistorted sampling points of the inner boundary line and this straight line. If the distance is greater than the preset threshold distance, it is classified as an outlier. If the distance is less than the preset threshold distance, it is classified as an inlier; Sort out the inlier point sets obtained by distinguishing each straight line, and select the point set with the largest number of inliers to perform line fitting to obtain the vertical line of the corrected inner boundary line; Set the intersection point of the horizontal line of the original inner boundary line of the parking space line and the vertical line of the corrected inner boundary line as the new parking space.

7. A server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the optimized method for detecting parking space lines based on fisheye images as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements the optimized method for detecting parking space lines based on fisheye images as described in any one of claims 1 to 5.

Images