Parking lot-oriented lane line reconstruction method

Abstract

The invention provides a reconstruction method for basement lane lines, and belongs to the technical field of lane line reconstruction. The method comprises the following steps: acquiring a coordinate point complete set for lane line reconstruction; a preset process is circularly carried out until a preset condition is met, and the preset process comprises the steps that the distance cost from each coordinate point in the target point set to the target line segment is determined; determining an overall fitting cost corresponding to each coordinate point in the target point set, and determining a first fitting cost of the target line segment to the target point set according to each distance cost; adding the coordinate point with the minimum overall fitting cost into the control point set, and dividing the original target point set into two new target point sets based on the coordinate point with the minimum overall fitting cost; and under the condition that a preset condition is met, fitting the control point set to obtain a lane line. The method can improve the reconstruction precision of the lane line.

Description

Technical Field

[0001] This invention relates to the field of lane line reconstruction technology, and in particular to a lane line reconstruction method, apparatus, electronic device and storage medium for parking lots. Background Technology

[0002] In the fields of automatic parking and memory parking, lane line maps have a significant impact on the realization of automatic parking functions. Lane line maps are generated based on lane line reconstruction technology, and the accuracy of lane line reconstruction determines the accuracy of lane line maps, which in turn determines the accuracy of automatic parking.

[0003] Current lane line reconstruction solutions suffer from low accuracy in reconstructing lane lines, resulting in low accuracy for automatic parking. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for lane line reconstruction in parking lots, in order to solve the technical problem of low lane line reconstruction accuracy in the prior art.

[0005] This invention provides a lane line reconstruction method for parking lots, comprising:

[0006] Obtain the complete set of coordinate points used for lane line reconstruction;

[0007] The preset process is repeated cyclically until the preset condition is met. The preset process includes:

[0008] Determine the distance cost from each coordinate point in the target point set to the target line segment; the initial target point set is the entire set of coordinate points, and the target line segment is the line connecting the two endpoints of the target point set;

[0009] If the maximum distance cost is greater than or equal to a preset threshold, the overall fitting cost corresponding to each coordinate point in the target point set is determined, and the first fitting cost of the target line segment to the target point set is determined according to each distance cost.

[0010] If the minimum overall fitting cost is less than the first fitting cost, the coordinate point with the minimum overall fitting cost is added to the control point set, and the original target point set is divided into two new target point sets based on the coordinate point with the minimum overall fitting cost.

[0011] Under the condition that the preset conditions are met, the control point set is fitted to obtain the lane line;

[0012] The control point set includes the two endpoints of the entire set of coordinate points and newly added coordinate points during the algorithm operation. The preset conditions include the maximum distance cost being less than the preset threshold and the minimum overall fitting cost being greater than or equal to the first fitting cost.

[0013] According to the lane line reconstruction method for parking lots provided by the present invention, the cost of determining the distance from each coordinate point in the target point set to the target line segment includes:

[0014] Determine the distance between the coordinate points in the target point set and the target line segment, as well as the angle between the first line segment and the second line segment;

[0015] The distance cost is determined based on the distance and the included angle;

[0016] Wherein, the first line segment is the line connecting one endpoint of the target point set to the coordinate point, and the second line segment is the line connecting the other endpoint of the target point set to the coordinate point.

[0017] According to a lane line reconstruction method for parking lots provided by the present invention, the step of determining the distance cost based on the distance and the included angle includes:

[0018] Divide the distance by the included angle to obtain the distance cost.

[0019] According to the lane line reconstruction method for parking lots provided by the present invention, the determination of the overall fitting cost corresponding to each coordinate point in the target point set includes:

[0020] The target point set is divided into a first point set corresponding to the first line segment and a second point set corresponding to the second line segment based on the bisector of the included angle.

[0021] Determine the second fitting cost of the first line segment to the first point set and the third fitting cost of the second line segment to the second point set, respectively;

[0022] The sum of the second fitting cost and the third fitting cost is determined to obtain the overall fitting cost.

[0023] According to a lane line reconstruction method for parking lots provided by the present invention, the step of determining the first fitting cost of the target line segment to the target point set based on each of the distance costs includes:

[0024] The average of the sum of squares of each of the distance costs is determined to obtain the first fitting cost.

[0025] According to the present invention, a lane line reconstruction method for parking lots is provided, wherein the original target point set is divided into two new target point sets based on the coordinate point with the minimum overall fitting cost, including:

[0026] The coordinate points in the original target point set located on one side of the coordinate point with the minimum overall fitting cost are divided into a new target point set, and the coordinate points in the original target point set located on the other side of the coordinate point with the minimum overall fitting cost are divided into another new target point set.

[0027] The present invention also provides a lane line reconstruction device for parking lots, comprising:

[0028] The acquisition module is used to obtain the complete set of coordinate points for lane line reconstruction;

[0029] An iterative module is used to repeatedly perform a preset process until a preset condition is met. The preset process includes:

[0030] Determine the distance cost from each coordinate point in the target point set to the target line segment; the initial target point set is the entire set of coordinate points, and the target line segment is the line connecting the two endpoints of the target point set;

[0031] If the maximum distance cost is greater than or equal to a preset threshold, the overall fitting cost corresponding to each coordinate point in the target point set is determined, and the first fitting cost of the target line segment to the target point set is determined according to each distance cost.

[0032] If the minimum overall fitting cost is less than the first fitting cost, the coordinate point with the minimum overall fitting cost is added to the control point set, and the original target point set is divided into two new target point sets based on the coordinate point with the minimum overall fitting cost.

[0033] The fitting module is used to fit the control point set under the preset conditions to obtain the lane line;

[0034] The control point set includes the two endpoints of the entire set of coordinate points and newly added coordinate points during the algorithm operation. The preset conditions include the maximum distance cost being less than the preset threshold and the minimum overall fitting cost being greater than or equal to the first fitting cost.

[0035] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the lane line reconstruction method for parking lots as described above.

[0036] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the lane line reconstruction method for parking lots as described above.

[0037] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the lane line reconstruction method for parking lots as described above.

[0038] The lane line reconstruction method, apparatus, electronic device, and storage medium provided by this invention for parking lots, based on the principle of minimizing lane line fitting costs, refines the extraction of lane line control points, reconstructs lane line trends, and improves lane line reconstruction accuracy. Furthermore, by selecting different preset threshold values, the lane line accuracy can achieve different error levels. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating the lane line reconstruction method for parking lots provided by the present invention.

[0041] Figure 2 This is a schematic diagram of the complete set of coordinate points provided by the present invention.

[0042] Figure 3 This is one of the schematic diagrams illustrating the principle of the lane line reconstruction method for parking lots provided by this invention.

[0043] Figure 4 This is the second schematic diagram of the principle of the lane line reconstruction method for parking lots provided by the present invention.

[0044] Figure 5 This is a schematic diagram of the control point set provided by the present invention.

[0045] Figure 6 This is a schematic diagram of the lane lines provided by the present invention.

[0046] Figure 7 This is a schematic diagram of the lane line reconstruction device for parking lots provided by the present invention.

[0047] Figure 8 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0049] Lane line reconstruction techniques can be divided into fitting based on ordered points and fitting based on unordered points.

[0050] For fitting ordered points, the common approach is to first sample control points and then fit the curve based on spline curves to generate a smooth curve. This type of method requires that the point set be ordered and that the selection of control points be carefully considered. When some control points are noise points or the sampling of control points is uneven, the accuracy of curve fitting will decrease significantly or even fail.

[0051] There are currently two types of methods for fitting unordered points. One is the fitting method based on a prior model, which fits the point set into a straight line, quadratic curve, cubic curve, etc. This type of method is computationally simple, but the disadvantage is that the curve model must be known first. The second is the Douglas-Puk algorithm, which simplifies the curve representation by iteratively finding the point with the largest distance from the current line segment until the fitting error reaches a threshold range. This method is simple to implement, but is greatly affected by noise.

[0052] In certain driving environments, such as underground parking garages, lane line detection often suffers from noise and missing data due to issues like lighting and occlusion. Overlaying time-series data can help improve the precision and recall of lane line detection. However, in situations with high noise, missing data, and high point cloud density, point cloud sorting itself becomes a complex problem. Therefore, lane line reconstruction in underground parking garages is not suitable for fitting methods based on ordered points. Similarly, existing fitting methods based on unordered points are also unsuitable for lane line reconstruction in underground parking garages, as lane lines may be combinations of various line types, making fitting methods based on prior models unsuitable, and the Douglas-Puk algorithm also struggles to guarantee accuracy.

[0053] For curve fitting of unordered point sets, when the curve model is unknown, the key issue is to extract high-precision control points from the curve and order them, then fit the curve trend based on these ordered control points. Furthermore, the curve can be fitted again using the first type of curve fitting method to obtain a continuous and smooth curve. To address the problem of extracting ordered control points from unordered point sets, the Douglas-Puk algorithm proposes a method that refines the curve representation by iteratively finding the point with the largest distance from the current line segment. This method, by eliminating the point with the largest fitting error and adding it to the control point set, is actually a local optimum method and cannot guarantee overall optimal curve fitting. Furthermore, this point selection strategy cannot eliminate the influence of noise points, easily including them in the control point set.

[0054] The following is combined with Figures 1-8 The present invention describes a method, apparatus, electronic device, and storage medium for lane line reconstruction in parking lots.

[0055] like Figure 1 As shown, the lane line reconstruction method for parking lots provided by the present invention includes steps S1-S3.

[0056] Step S1: Obtain the complete set of coordinate points for lane line reconstruction.

[0057] The complete set of coordinate points can be like Figure 2 As shown, it can be seen that the coordinate points in the universal set of coordinate points are unordered.

[0058] Step S2: Repeat the preset process until the preset conditions are met. The preset process includes:

[0059] Determine the distance cost from each coordinate point in the target point set to the target line segment; the initial target point set is the entire set of coordinate points, and the target line segment is the line connecting the two endpoints of the target point set;

[0060] If the maximum distance cost is greater than or equal to a preset threshold, determine the overall fitting cost corresponding to each coordinate point in the target point set, and determine the first fitting cost of the target line segment to the target point set based on each distance cost.

[0061] If the minimum overall fitting cost is less than the first fitting cost, add the coordinate point with the minimum overall fitting cost to the control point set, and divide the original target point set into two new target point sets based on the coordinate point with the minimum overall fitting cost.

[0062] The control point set includes the two endpoints of the entire set of coordinate points and newly added coordinate points during the algorithm operation. The preset conditions include that the maximum first distance cost is less than a preset threshold and the minimum overall fitting cost is greater than or equal to the first fitting cost.

[0063] In some implementations, step S2, determining the distance cost from each coordinate point in the target point set to the target line segment, may further include:

[0064] Determine the distance between the coordinate points in the target point set and the target line segment, as well as the angle between the first line segment and the second line segment;

[0065] Determine the distance cost based on the distance and the included angle;

[0066] The first line segment is the line connecting one endpoint of the target point set to the coordinate point, and the second line segment is the line connecting the other endpoint of the target point set to the coordinate point.

[0067] like Figure 3 As shown, Pi is the i-th coordinate point in the target point set P, and Pa and Pb are the two endpoints of the target point set. Let d be the target line segment, and d be the line segment between Pi and Pi. The distance between them The first line segment, Let θ be the second line segment, and let θ be the angle between the first and second line segments.

[0068] In some implementations, step S2, determining the distance cost based on the distance d and the included angle θ, may further include:

[0069] Divide the distance d by the included angle θ to obtain the distance cost.

[0070] That is, distance cost It can be seen that the distance cost is directly proportional to the distance from the coordinate point to the line segment and inversely proportional to the angle formed by the coordinate point and the endpoint of the line segment.

[0071] In this way, the distance cost from each coordinate point to the line segment can be determined by the distance from the coordinate point to the line segment and the angle formed by the coordinate point and the endpoint of the line segment.

[0072] The maximum distance cost is Cost MAX The preset threshold is ∈, if Cost MAX If <∈, then the loop ends.

[0073] In some embodiments, the present invention determines the overall fitting cost corresponding to each coordinate point in the target point set, which may further include:

[0074] The bisector of the included angle θ divides the target point set into a first point set corresponding to the first line segment and a second point set corresponding to the second line segment;

[0075] Determine the second fitting cost of the first line segment to the first point set and the third fitting cost of the second line segment to the second point set, respectively;

[0076] The sum of the second and third fitting costs is determined to obtain the overall fitting cost.

[0077] Using the k-th coordinate point P in the target point set P k For example, Figure 4 As shown, the included angle θ is ∠P a P k P b , The first line segment, The second line segment, The corresponding first point set is P 1,k , The corresponding second point set is P 2,k P 1,k +P 2,k =P.

[0078] The second fitting cost can be calculated based on the calculation principle of the first fitting cost. and the third fitting cost Then the overall fitting cost X =

[0079]

[0080] In some implementations, step S2, determining the first fitting cost of the target line segment to the target point set based on each first distance cost, may further include:

[0081] The average of the sum of squares of each distance cost is determined to obtain the first fitted cost.

[0082] Specifically, the first fitting cost N is the number of coordinate points in the target point set.

[0083] Assume coordinates point P k The corresponding overall fitting cost X is minimized if Then the coordinates of point P k Add to the control point set; if Then the loop ends.

[0084] In some implementations, step S2, which divides the original target point set into two new target point sets based on the coordinate point with the minimum overall fitting cost, may further include:

[0085] The coordinate points in the original target point set that are located on one side of the coordinate point with the minimum overall fitting cost are divided into a new target point set, and the coordinate points in the original target point set that are located on the other side of the coordinate point with the minimum overall fitting cost are divided into another new target point set.

[0086] For example, if coordinate point P kThe corresponding overall fitting cost X is minimized, and Then according to Figure 4 The principle shown divides the original target point set P into two new target point sets Pi. 1,k and P 2,k For the target point set P 1,k and P 2,k Perform the preset process for each step. Continue in this manner until the preset conditions are met, at which point the loop ends.

[0087] Through the iterative process of step S2, this invention can extract all control points from the complete set of coordinate points and add them to the control point set, ultimately yielding the following result: Figure 5 The set of control points shown (white dots).

[0088] Step S3: Under the condition of meeting the preset conditions, the control point set is fitted to obtain the lane line.

[0089] right Figure 5 Fitting the control point set shown, we obtain the following: Figure 6 The lane lines shown.

[0090] As described above, the lane line reconstruction method for parking lots of this invention is based on the principle of minimizing lane line fitting costs. It refines the extraction of lane line control points, restores the lane line trend, and improves the lane line reconstruction accuracy. Furthermore, by selecting different preset threshold values, the lane line accuracy can achieve different error levels.

[0091] like Figure 7 As shown, the present invention also provides a lane line reconstruction device for parking lots, comprising:

[0092] The acquisition module is used to obtain the complete set of coordinate points for lane line reconstruction;

[0093] The iteration module is used to repeatedly perform a preset process until a preset condition is met. The preset process includes:

[0094] Determine the first distance cost from each coordinate point in the target point set to the target line segment; the initial target point set is the entire set of coordinate points, and the target line segment is the line connecting the two endpoints of the target point set;

[0095] If the maximum first distance cost is greater than or equal to a preset threshold, determine the overall fitting cost corresponding to each coordinate point in the target point set, and determine the first fitting cost of the target line segment to the target point set based on each first distance cost.

[0096] If the minimum overall fitting cost is less than the first fitting cost, add the coordinate point with the minimum overall fitting cost to the control point set, and divide the original target point set into two new target point sets based on the coordinate point with the minimum overall fitting cost.

[0097] The fitting module is used to fit the control point set under preset conditions to obtain the lane lines;

[0098] The control point set includes the two endpoints of the entire set of coordinate points and newly added coordinate points during the algorithm operation. The preset conditions include that the maximum first distance cost is less than a preset threshold and the minimum overall fitting cost is greater than or equal to the first fitting cost.

[0099] In some implementations, the iteration module can also be used for:

[0100] Determine the distance between the coordinate points in the target point set and the target line segment, as well as the angle between the first line segment and the second line segment;

[0101] Determine the distance cost based on the distance and the included angle;

[0102] The first line segment is the line connecting one endpoint of the target point set to the coordinate point, and the second line segment is the line connecting the other endpoint of the target point set to the coordinate point.

[0103] In some implementations, the iteration module can also be used for:

[0104] Divide the distance by the included angle to get the distance cost.

[0105] In some implementations, the iteration module can also be used for:

[0106] The target point set is divided into a first point set corresponding to the first line segment and a second point set corresponding to the second line segment based on the angle bisector.

[0107] Determine the second fitting cost of the first line segment to the first point set and the third fitting cost of the second line segment to the second point set, respectively;

[0108] The sum of the second and third fitting costs is determined to obtain the overall fitting cost.

[0109] In some implementations, the iteration module can also be used for:

[0110] The average of the sum of squares of each distance cost is determined to obtain the first fitted cost.

[0111] In some implementations, the iteration module can also be used for:

[0112] The coordinate points in the original target point set that are located on one side of the coordinate point with the minimum overall fitting cost are divided into a new target point set, and the coordinate points in the original target point set that are located on the other side of the coordinate point with the minimum overall fitting cost are divided into another new target point set.

[0113] Figure 8This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 8 As shown, the electronic device may include a processor, a communication interface, a memory, and a communication bus, wherein the processor, communication interface, and memory communicate with each other via the communication bus. The processor can call logical instructions in the memory to execute a lane line reconstruction method for parking lots.

[0114] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0115] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, and when the program instructions are executed by a computer, the computer is able to execute the lane line reconstruction method for parking lots provided in the above embodiments.

[0116] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the lane line reconstruction method for parking lots provided in the above embodiments.

[0117] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0118] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A lane line reconstruction method for parking lots, characterized in that, include: Obtain the complete set of coordinate points used for lane line reconstruction; The preset process is repeated cyclically until the preset condition is met. The preset process includes: Determine the distance cost from each coordinate point in the target point set to the target line segment; the initial target point set is the entire set of coordinate points, and the target line segment is the line connecting the two endpoints of the target point set; If the maximum distance cost is greater than or equal to a preset threshold, the overall fitting cost corresponding to each coordinate point in the target point set is determined, and the first fitting cost of the target line segment to the target point set is determined according to each distance cost. If the minimum overall fitting cost is less than the first fitting cost, the coordinate point with the minimum overall fitting cost is added to the control point set, and the original target point set is divided into two new target point sets based on the coordinate point with the minimum overall fitting cost. Under the condition that the preset conditions are met, the control point set is fitted to obtain the lane line; The control point set includes the two endpoints of the entire set of coordinate points and newly added coordinate points during the algorithm operation. The preset conditions include the maximum distance cost being less than the preset threshold and the minimum overall fitting cost being greater than or equal to the first fitting cost.

2. The lane line reconstruction method for parking lots according to claim 1, characterized in that, The cost of determining the distance from each coordinate point in the target point set to the target line segment includes: Determine the distance between the coordinate points in the target point set and the target line segment, as well as the angle between the first line segment and the second line segment; The distance cost is determined based on the distance and the included angle; Wherein, the first line segment is the line connecting one endpoint of the target point set to the coordinate point, and the second line segment is the line connecting the other endpoint of the target point set to the coordinate point.

3. The lane line reconstruction method for parking lots according to claim 2, characterized in that, Determining the distance cost based on the distance and the included angle includes: Divide the distance by the included angle to obtain the distance cost.

4. The lane line reconstruction method for parking lots according to claim 2, characterized in that, The determination of the overall fitting cost corresponding to each coordinate point in the target point set includes: The target point set is divided into a first point set corresponding to the first line segment and a second point set corresponding to the second line segment based on the bisector of the included angle. Determine the second fitting cost of the first line segment to the first point set and the third fitting cost of the second line segment to the second point set, respectively; The sum of the second fitting cost and the third fitting cost is determined to obtain the overall fitting cost.

5. The lane line reconstruction method for parking lots according to claim 1, characterized in that, Determining the first fitting cost of the target line segment to the target point set based on each of the distance costs includes: The average of the sum of squares of each of the distance costs is determined to obtain the first fitting cost.

6. The lane line reconstruction method for parking lots according to claim 1, characterized in that, The original target point set is divided into two new target point sets based on the coordinate point with the minimum overall fitting cost, including: The coordinate points in the original target point set located on one side of the coordinate point with the minimum overall fitting cost are divided into a new target point set, and the coordinate points in the original target point set located on the other side of the coordinate point with the minimum overall fitting cost are divided into another new target point set.

7. A lane line reconstruction device for parking lots, characterized in that, include: The acquisition module is used to obtain the complete set of coordinate points for lane line reconstruction; An iterative module is used to repeatedly perform a preset process until a preset condition is met. The preset process includes: Determine the distance cost from each coordinate point in the target point set to the target line segment; the initial target point set is the entire set of coordinate points, and the target line segment is the line connecting the two endpoints of the target point set; If the maximum distance cost is greater than or equal to a preset threshold, the overall fitting cost corresponding to each coordinate point in the target point set is determined, and the first fitting cost of the target line segment to the target point set is determined according to each distance cost. If the minimum overall fitting cost is less than the first fitting cost, the coordinate point with the minimum overall fitting cost is added to the control point set, and the original target point set is divided into two new target point sets based on the coordinate point with the minimum overall fitting cost. The fitting module is used to fit the control point set under the preset conditions to obtain the lane line; The control point set includes the two endpoints of the entire set of coordinate points and newly added coordinate points during the algorithm operation. The preset conditions include the maximum distance cost being less than the preset threshold and the minimum overall fitting cost being greater than or equal to the first fitting cost.

8. An electronic device 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 lane line reconstruction method for parking lots as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the lane line reconstruction method for parking lots as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the lane line reconstruction method for parking lots as described in any one of claims 1 to 6.

Images