Parking space editing method and device based on data synthesis, equipment and medium

Abstract

The invention discloses a parking space editing method, device and equipment based on data synthesis and a medium, and the method comprises the steps: obtaining a parking space image and a label file thereof, and carrying out the semantic segmentation of the parking space image through a semantic segmentation model, and obtaining a parking space line mask; eliminating a parking space line in the parking space image based on the parking space line mask to obtain a target parking space image; modifying the line type or color of the parking space line mask to obtain a target parking space line mask; and performing data fusion on the target parking space line mask and the target parking space image to obtain a new parking space image, and modifying the tag file according to the attribute of the parking space line in the target parking space line mask. According to the method, the accurate parking space line contour can be obtained through the semantic segmentation technology, the parking space lines can be edited accurately, then the parking space lines are edited according to requirements to obtain different types of parking space lines, and the label of the original parking space image can be reused, so that the labeling cost and time for editing and generating new data are greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data synthesis, and in particular to a parking space editing method, device, equipment and medium based on data synthesis. Background Art

[0002] With the increasing application of artificial intelligence technology in the field of autonomous driving, the accuracy of various detection and recognition is also constantly improving. At the same time, the requirements for training data used in deep learning are also getting higher and higher. Among them, for the automatic parking system, which occupies a vital position in the autonomous driving system, the accuracy of parking space detection plays a decisive role in the performance of the system. For the parking space detection algorithm, in order to achieve accurate detection results, it is necessary to train data in a large number of different scenarios, and there are also different requirements for the parking space itself, such as the color, shape, line type of the parking space line itself, whether it is a prohibited parking space, etc.; but such rich parking space information is often not available during data collection. Therefore, it is necessary to edit the AVM (Around View Monitor) surround image in the training data through data synthesis to obtain more sufficient parking space data types.

[0003] Existing local image editing technologies mainly include two categories: traditional methods and deep learning methods. The traditional method mainly uses traditional image fusion or splicing methods to fuse the target local image block into the target area, but the disadvantage of this method is that the fusion effect is unnatural, and the difference is often more obvious when the image block and the target image have a large difference in style. The deep learning method uses models such as generative adversarial networks to learn the style of the target image in order to achieve more harmonious target fusion and modification. However, since the AVM image is spliced ​​by fisheye image projection, it is quite different from the normal image style, and for the parking line target, more detailed adjustments are required when editing, and the generative adversarial network often cannot learn better results. Summary of the invention

[0004] In view of the above technical problems, the present invention provides a parking space editing method, device, equipment and medium based on data synthesis, which can reduce the cost of data annotation.

[0005] A first aspect of the present invention provides a parking space editing method based on data synthesis, comprising: Acquire a parking space image and its label file, and use a semantic segmentation model to perform semantic segmentation on the parking space image to acquire a parking space line mask; Eliminating the parking space lines in the parking space image based on the parking space line mask to obtain a target parking space image; Modifying the line type or color of the parking space line mask to obtain a target parking space line mask; The target parking space line mask and the target parking space image are data-fused to obtain a new parking space image, and the label file is modified according to the attributes of the parking space lines in the target parking space line mask.

[0006] In an optional implementation, the parking space image is an AVM image or a plurality of fisheye images used to stitch into an AVM image; when the parking space image is a fisheye image, a plurality of masks obtained based on a single fisheye image are stitched into a parking space line mask.

[0007] In an optional implementation, after performing semantic segmentation on the parking space image using a semantic segmentation model to obtain a parking space line mask, the method further includes: The parking space lines in the parking space line mask are thickened by using a dilation algorithm.

[0008] In an optional implementation manner, eliminating the parking space lines in the parking space image based on the parking space line mask to obtain the target parking space image includes: The parking space line mask and the parking space image are input into an image restoration model to eliminate the parking space lines, so as to obtain a target parking space image.

[0009] In an optional implementation manner, modifying the line type or color of the parking space line mask to obtain a target parking space line mask includes: Modifying the line type of the parking lines in the parking line mask according to preset requirements or parking line environment, obtaining a target parking line mask, and modifying the properties of the parking lines in the target parking line mask; The color of the parking lines in the parking line mask is modified according to preset requirements or parking line environment, a target parking line mask is obtained, and the properties of the parking lines in the target parking line mask are modified.

[0010] In an optional implementation manner, modifying the line type or color of the parking space line mask to obtain a target parking space line mask includes: An unparked area in the parking space image is identified, and if a parking area that meets the requirements exists in the parking space image, a preset parking space line is added to the parking area that meets the requirements.

[0011] In an optional implementation, the preset parking space line and the parking space line in the target parking space line mask have different line types.

[0012] In an optional implementation, the parking space editing method further includes adding a reminder mark based on the coordinates of the target parking space line mask.

[0013] A second aspect of the present invention provides a parking space editing device based on data synthesis, comprising: An acquisition module, used to acquire a parking space image and its label file, and perform semantic segmentation on the parking space image using a semantic segmentation model to acquire a parking space line mask; an elimination module, configured to eliminate the parking space lines in the parking space image based on the parking space line mask to obtain a target parking space image; An editing module, used for modifying the line type or color of the parking space line mask to obtain a target parking space line mask; The synthesis module is used to perform data fusion on the target parking space line mask and the target parking space image to obtain a new parking space image, and to modify the label file according to the attributes of the parking space line in the target parking space line mask.

[0014] According to a third aspect of the present invention, there is provided an electronic device, comprising: At least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method described in the first aspect of the embodiment of the present invention.

[0015] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a computer, the method according to the first aspect of the embodiment of the present invention is executed.

[0016] The present invention can obtain the precise parking space line contour through semantic segmentation technology, which is convenient for accurate editing of parking space lines. The parking space lines are then edited according to needs to obtain different types of parking space lines. At the same time, since the labels of the original parking space images can also be reused, the annotation cost and time of editing and generating new data are greatly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 Schematic diagram of a flow chart of a parking space editing method based on data synthesis in an embodiment of the present invention.

[0019] Figure 2 Schematic diagram of a parking space image in an embodiment of the present invention.

[0020] Figure 3 According to the present invention Figure 2 Schematic diagram of the obtained parking space line mask.

[0021] Figure 4 For the present invention Figure 3 Schematic diagram of the center parking space line after expansion treatment.

[0022] Figure 5 In the present invention, Figure 2 Schematic diagram of the white parking space line in the middle being changed to a yellow semi-open parking space line.

[0023] Figure 6 In the present invention, Figure 2 Schematic diagram of the white parking space line in the middle being changed to a yellow open parking space line.

[0024] Figure 7 In the present invention, Figure 2 Schematic diagram of changing the middle parking space line to a semi-open parking space line.

[0025] Figure 8 In the present invention, Figure 2 Schematic diagram of the white parking space line in the middle being changed to an open parking space line.

[0026] Fig. 9 This is a schematic diagram of adding a no-parking sign to a parking space image in the present invention.

[0027] Fig.10 Schematic diagram of a module of a parking space editing device based on data synthesis in an embodiment of the present invention.

[0028] Fig.11 FIG. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0030] It should be understood that the terms "first", "second", "third", etc. in the claims, specifications and drawings of the present invention are used to distinguish different objects rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0031] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the claims, the singular forms of "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in the specification of the present invention and the claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0032] When collecting parking space data, the types of parking spaces collected in the same parking lot are often basically the same. Therefore, if you want to improve the types of parking spaces in the data, you often need to find different parking lots for data collectors, which increases the difficulty of data collection and the number and cost of data annotation. The present invention can use the collected data to edit parking spaces, and can obtain different types of parking spaces according to needs. At the same time, since the labels of the original data can also be reused, the annotation cost and time of new data are greatly reduced; the new data generated after editing can also improve the richness of parking space data.

[0033] See also Figure 1 The present invention provides a parking space editing method based on data synthesis, which includes the following steps.

[0034] S100: Acquire a parking space image and its label file, and use a semantic segmentation model to perform semantic segmentation on the parking space image to acquire a parking space line mask.

[0035] The parking space image is usually parking space data collected by a road sampling vehicle, and a label file of the parking space image can be obtained by annotating the parking space data. The label file is used to characterize the line type and color of the parking space line in the image.

[0036] In order to facilitate accurate editing of parking space lines, the present invention uses a semantic segmentation model to perform semantic segmentation on the above parking space image to obtain the parking space lines in the parking space image. The semantic segmentation model can adopt a YOLOP network model, an MRRNet (MultiResolution Refinement Network) network model, a DeepLab network model, etc.

[0037] For details, please refer to Figure 2 and Figure 3 , Figure 2 is the original parking space image, Figure 3 is the parking space line mask obtained after semantic segmentation of the parking space image. Figure 3It can be seen that the parking space lines in the parking space line mask are closed parking space lines, and the parking space line editing can be implemented based on the closed parking space lines, for example, the parking space lines can be edited into open or semi-closed parking space lines.

[0038] In an embodiment of the present invention, the parking space image is an AVM image, or a plurality of fisheye images stitched into an AVM image.

[0039] When the parking space image is four fisheye images, four masks obtained based on a single fisheye image are spliced ​​into a parking space line mask. Usually, four fisheye images are spliced ​​into an AVM image. This method can reduce the impact of distortion caused by stretching of the AVM image.

[0040] S200: Eliminating the parking space lines in the parking space image based on the parking space line mask to obtain a target parking space image.

[0041] After obtaining the parking space line mask through semantic segmentation technology, it is known that the parking space line is in the parking space image area, and the image restoration model can be used to completely or partially eliminate the parking space line in the parking space image. To completely eliminate the parking space line, it is necessary to use a new parking space line and the parking space image to synthesize a new image. To partially eliminate the parking space line, the parking space line in the parking space image can be modified to obtain a new image after modification.

[0042] S300: modifying the line type or color of the parking space line mask to obtain a target parking space line mask.

[0043] like Figure 4 As shown, the parking space line mask is formed by removing the parking space line part in the parking space line mask. It should be understood that in the present invention, other image contents of the parking space image are retained, and only the parking space lines in the parking space image are modified to meet the requirement of data enrichment.

[0044] If the color of the parking space line needs to be modified, for example, the color of the parking space line needs to be changed from white to yellow, then all the original parking space lines in the parking space image need to be eliminated, and then the color of the parking space line mask needs to be edited to change the white to yellow. Figure 5 and Figure 6 As shown, it is a parking space image after color editing, and the yellow parking space line in the figure is the parking space line in the target parking space line mask.

[0045] The present invention utilizes the above method to completely eliminate the parking space lines and resynthesize them, or partially eliminate them to achieve line type conversion, or add new lines thereon, which can fully meet different needs and has the advantage of more flexible processing methods; also because of the flexibility, the data of the parking space image can be reused, and the same image can be edited for different types of data to obtain more new parking spaces, thereby enriching the image data.

[0046] S400: fusing the target parking space line mask with the target parking space image to obtain a new parking space image, and modifying the label file according to the attributes of the parking space line in the target parking space line mask.

[0047] Since the parking space line mask obtained after semantic segmentation does not change in size, only the parking space lines in the parking space line mask are edited, the target parking space line mask has the same size as the parking space line mask obtained by the semantic segmentation. When the target parking space line mask is fused with the target parking space image, image fusion can be performed directly without complex positioning. The specific data fusion method is an existing technology and will not be described in detail.

[0048] The same parking space image can be edited in different ways, multiple image data can be obtained, and large-scale synthesis can be performed. For example, Figure 2 The closed parking lines can be edited into semi-closed parking lines and open parking lines; combined with color editing, you can get yellow closed parking lines, yellow semi-closed parking lines, yellow open parking lines; white semi-closed parking lines, white open parking lines.

[0049] The present invention will be further described below with reference to specific examples.

[0050] In the above step S100, after the semantic segmentation of the parking space image is performed using the semantic segmentation model to obtain the parking space line mask, the method further includes: thickening the parking space lines in the parking space line mask using a dilation algorithm.

[0051] In order to completely eliminate the parking lines in the future, the parking line mask needs to cover the parking line range more completely, and the lane lines in the parking line mask need to be thickened; the present invention uses an expansion algorithm to process the lane lines. Figure 7 For the general Figure 2 The parking space line mask after the parking space line in the image is expanded.

[0052] After editing the parking space line, the parking space line can be processed by the inverse expansion algorithm to make the parking space line conform to the size of the parking space line in the original parking space image. Common inverse expansion algorithms include corrosion algorithm, opening operation, closing operation, etc.

[0053] It should be understood that the expansion algorithm and the inverse expansion algorithm are complementary, and the expansion process will be followed by the inverse expansion process, so the expansion algorithm includes two methods: expansion and inverse expansion.

[0054] In the above step S200, the parking space lines in the parking space image are eliminated based on the parking space line mask, and the parking space line mask and the parking space image are input into an image restoration model to eliminate the parking space lines. The image restoration model includes a model based on a generative adversarial network, a model based on a traditional convolutional neural network, and a Transformer-based model, such as GAN-based models, Globally and Locally Consistent.

[0055] In some embodiments, a semantic segmentation model and an image restoration model may be deployed in the cloud. For example, the data collected by the road collection vehicle that needs to be synthesized for parking spaces is obtained from the cloud data lake, mainly including the AVM map and its label file. The AVM map is then segmented using the semantic segmentation model deployed in the cloud to obtain a semantic segmentation mask for parking lines. The parking line portion is then enhanced, and the enhanced parking line mask is edited as required to determine the portion that needs to be eliminated. The image restoration model deployed in the cloud is then called, and the original AVM map and the edited parking line mask are simultaneously input into the model to eliminate the parking lines, and then data synthesis (such as color addition, etc.) is performed based on whether partial addition is required to obtain new parking lines.

[0056] Furthermore, since data labels are required for training the automatic parking system, the present invention can modify the label file when completing data synthesis to change the properties of the parking space lines.

[0057] Therefore, the properties of the parking space lines in the target parking space line mask may be modified after the line type or color of the parking space line mask is modified in the following manner.

[0058] In one embodiment, the parking lines in the parking line mask are modified in line type according to preset requirements or parking line environment, a target parking line mask is obtained, and the properties of the parking lines in the target parking line mask are modified.

[0059] For example, the preset requirement is to convert the closed parking space line into an open or semi-closed parking space line, which can be modified using the image restoration model. Figure 2 The parking space line in is changed to Figure 7 Semi-closed parking space line or Figure 8 The opening parking space line in the middle.

[0060] Alternatively, in some scenarios, the parking space line environment in the parking space image is more suitable for adding parking space lines of other line types, and parking space lines of other line types can be added to the parking space image. Figure 2 The parking spaces in the image are all full of parked vehicles. Figure 2If the middle parking space is empty, it is considered that the parking space line environment meets the requirements, and the unparked area in the parking space image is identified. If there is a parking area that meets the requirements in the parking space image, a preset parking space line is added to the parking area that meets the requirements.

[0061] For example, the parking line types include parallel parking lines, vertical parking lines, inclined parking lines, mixed parking lines, open parking lines, semi-open parking lines, exclusive parking lines, time-limited parking lines, taxi parking lines, and large vehicle parking lines.

[0062] Therefore, any of the above parking space lines can be added to the unparked area in the parking space image. In the present invention, the preset parking space lines are different in line type from the parking space lines in the target parking space line mask to enrich the parking space image data.

[0063] In another embodiment, the color of the parking lines in the parking line mask is modified according to preset requirements or parking line environment, a target parking line mask is obtained, and the properties of the parking lines in the target parking line mask are modified.

[0064] For example, the preset requirement is to change the white parking space line to a yellow parking space line, which can be modified using the image restoration model. Figure 2 The white parking space line in the image is changed to Figure 5 Medium yellow semi-closed parking space line or Figure 6 Medium yellow open parking space line.

[0065] Alternatively, in some scenarios, the color of the parking space line in the parking space line mask is modified according to preset requirements or parking space line environment. Figure 2 If some parking spaces in the middle are empty, it is considered that the parking space line environment meets the requirements, and the unparked area in the parking space image is identified, and the parking space line color is changed to yellow as a dedicated parking line. Of course, in some other scenarios, the parking space line color can also be modified in batches according to preset requirements, such as the preset requirement is to change the parking space lines in batches to yellow.

[0066] Furthermore, the parking space editing method provided by the present invention further includes adding a reminder mark based on the coordinates of the target parking space line mask. Fig. 9 As shown, a no-parking sign is added to the parking space line, see the yellow "X" symbol in the figure. For adding reminder signs, please refer to the existing technology: the application date is July 31, 2023, the publication number is CN117078799B, and the patent name is a special parking space synthesis method and device based on BEV image, which will not be described in detail.

[0067] See also Fig.10The present invention provides a parking space editing device based on data synthesis, comprising: an acquisition module 11, an elimination module 12, an editing module 13, and a synthesis module 14. An acquisition module 11 is used to acquire a parking space image and its label file, and perform semantic segmentation on the parking space image using a semantic segmentation model to acquire a parking space line mask; An elimination module 12, configured to eliminate the parking space lines in the parking space image based on the parking space line mask to obtain a target parking space image; An editing module 13, used for modifying the line type or color of the parking space line mask to obtain a target parking space line mask; The synthesis module 14 is used to perform data fusion on the target parking space line mask and the target parking space image to obtain a new parking space image, and to modify the label file according to the attributes of the parking space line in the target parking space line mask.

[0068] For the description of the parking space editing device based on data synthesis, reference may be made to the description of the parking space editing method based on data synthesis, which will not be repeated here.

[0069] like Fig.11 As shown, the present invention also provides an electronic device, including: At least one processor; and at least one memory in communication with the processor, wherein: the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the above-mentioned parking space editing method based on data synthesis.

[0070] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the parking space editing method based on data synthesis is implemented.

[0071] It can be understood that computer-readable storage media may include: any entity or device capable of carrying a computer program, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc. A computer program includes a computer program code. The computer program code may be in source code form, object code form, an executable file, or some intermediate form, etc. A computer-readable storage medium may include: any entity or device capable of carrying a computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc.

[0072] In certain embodiments of the present invention, the electronic device may include a controller or a processor, and the controller is a single-chip microcomputer chip that integrates a processor, a memory, a communication module, etc. The processor may refer to a processor included in the controller. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.

[0073] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0074] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0075] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A parking space editing method based on data synthesis, characterized in that: include: Acquire a parking space image and its label file, and use a semantic segmentation model to perform semantic segmentation on the parking space image to acquire a parking space line mask; Eliminating the parking space lines in the parking space image based on the parking space line mask to obtain a target parking space image; Modifying the line type or color of the parking space line mask to obtain a target parking space line mask; The target parking space line mask and the target parking space image are data-fused to obtain a new parking space image, and the label file is modified according to the attributes of the parking space lines in the target parking space line mask.

2. The parking space editing method based on data synthesis according to claim 1, characterized in that: The parking space image is an AVM image or a plurality of fisheye images used to stitch into an AVM image; when the parking space image is a fisheye image, a plurality of masks obtained based on a single fisheye image are stitched into a parking space line mask.

3. The parking space editing method based on data synthesis according to claim 1, characterized in that: After the semantic segmentation of the parking space image is performed using the semantic segmentation model to obtain the parking space line mask, the method further includes: The parking space lines in the parking space line mask are thickened by using a dilation algorithm.

4. The parking space editing method based on data synthesis according to claim 1, characterized in that: Eliminating the parking space lines in the parking space image based on the parking space line mask to obtain a target parking space image includes: The parking space line mask and the parking space image are input into an image restoration model to eliminate the parking space lines, so as to obtain a target parking space image.

5. The parking space editing method based on data synthesis according to claim 1, characterized in that: The modifying the line type or color of the parking space line mask to obtain the target parking space line mask includes: Modifying the line type of the parking lines in the parking line mask according to preset requirements or parking line environment, obtaining a target parking line mask, and modifying the properties of the parking lines in the target parking line mask; The color of the parking lines in the parking line mask is modified according to preset requirements or parking line environment, a target parking line mask is obtained, and the properties of the parking lines in the target parking line mask are modified.

6. The parking space editing method based on data synthesis according to claim 5, characterized in that: The modifying the line type or color of the parking space line mask to obtain a target parking space line mask includes: An unparked area in the parking space image is identified, and if a parking area that meets the requirements exists in the parking space image, a preset parking space line is added to the parking area that meets the requirements.

7. The parking space editing method based on data synthesis according to claim 6, characterized in that: The preset parking space line is different from the parking space line in the target parking space line mask in line type.

8. The parking space editing method based on data synthesis according to claim 1, characterized in that: The parking space editing method further includes adding a reminder mark based on the coordinates of the target parking space line mask.

9. A parking space editing device based on data synthesis, characterized in that: include: An acquisition module, used to acquire a parking space image and its label file, and perform semantic segmentation on the parking space image using a semantic segmentation model to acquire a parking space line mask; an elimination module, configured to eliminate the parking space lines in the parking space image based on the parking space line mask to obtain a target parking space image; An editing module, used for modifying the line type or color of the parking space line mask to obtain a target parking space line mask; The synthesis module is used to perform data fusion on the target parking space line mask and the target parking space image to obtain a new parking space image, and to modify the label file according to the attributes of the parking space line in the target parking space line mask.

10. An electronic device, characterized in that: include: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the parking space editing method based on data synthesis as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a computer, the parking space editing method based on data synthesis as claimed in any one of claims 1 to 8 is executed.

Images