Method, device, equipment and storage medium for identifying lane lines in underground garage images

Abstract

The present application relates to a method, device, equipment and storage medium for identifying lane lines in an underground garage map; wherein the method comprises: classifying all lines in the underground garage map according to color and layer, and dividing lines belonging to the same layer and with the same color into the same line set; extracting at least one lane space from the underground garage map; wherein the lane space is the space between two parking spaces containing lane lines or the space between a parking space and a wall; screening out a suspected lane line set according to the number of lane spaces passed by each line in each line set; verifying each suspected lane line in the suspected lane line set, and using the suspected lane line that passes the verification as the target lane line in the underground garage map. The present application is used to solve the technical problem that the efficiency and accuracy of lane line recognition in the prior art are generally low.

Description

Technical Field

[0001] The present application relates to the field of intelligent recognition of architectural drawings, and in particular to a method, device, equipment and storage medium for recognizing lane lines in underground garage drawings. Background Art

[0002] Currently, in architectural drawings, problems involving the calculation of fire safety distances and the calculation of intersecting lanes require the identification of all lane lines.

[0003] Existing technology primarily relies on image recognition to identify lane markings in CAD architectural drawings. However, underground garage drawings involve a large area and complex design schemes. Lane markings in underground garages are mostly single lines with few features. Furthermore, the complex scenes and high levels of noise in underground garage drawings make image recognition techniques generally inefficient and inaccurate. Summary of the Invention

[0004] The present application provides a method, apparatus, device and storage medium for identifying lane lines in an underground garage map, so as to solve the technical problem that the efficiency and accuracy of lane line recognition in the prior art are generally low.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying lane lines in an underground garage image, comprising:

[0006] Classify all lines in the underground garage map according to color and layer, and group lines belonging to the same layer and with the same color into the same line set;

[0007] Extracting at least one lane space from the underground garage map; wherein the lane space is a space between two parking spaces containing lane lines or a space between a parking space containing lane lines and a wall;

[0008] Screening out suspected lane line sets based on the number of lane spaces passed by each line in each line set;

[0009] Each suspected lane line in the suspected lane line set is verified, and the suspected lane line that passes the verification is used as the target lane line in the underground garage map.

[0010] Optionally, extracting at least one lane space from the underground garage map includes:

[0011] Extract all parking spaces from the underground garage map;

[0012] For any two parallel parking spaces, if the ratio of the overlapping area after the parallel projection of any one of the two parallel parking spaces onto the other parking space exceeds a first preset ratio, the distance between the any two parallel parking spaces is calculated. If the distance is within the preset distance range and there is no other parking space between the any two parallel parking spaces, the space between the any two parallel parking spaces is extracted as the lane space.

[0013] Optionally, extracting at least one lane space from the underground garage map further includes:

[0014] Extracting walls from the underground garage image;

[0015] For any parking space, if the distance between the parking space and the wall is within a preset distance range and there is no other parking space between the parking space and the wall, the space between the parking space and the wall is extracted as the lane space.

[0016] Optionally, screening out the suspected lane line set according to the number of lane spaces passed through by each line in each line set includes:

[0017] For each of the line sets, if the ratio of the number of the lane spaces to the total number of all lane spaces exceeds a second preset ratio, the line set is used as the suspected lane line set.

[0018] Optionally, verifying each suspected lane line in the set of suspected lane lines and using the verified suspected lane line as the target lane line in the underground garage map includes:

[0019] For each suspected lane line in the suspected lane line set, if it is determined that the suspected lane line does not pass through any parking space and the suspected lane line does not pass through any wall, the suspected lane line is determined to be a target lane line.

[0020] Optionally, verifying each suspected lane line in the set of suspected lane lines and using the verified suspected lane line as the target lane line in the underground garage map includes:

[0021] For each suspected lane line in the suspected lane line set, if there is at least one parking space within a preset range of the suspected lane line, the suspected lane line is used as the target lane line.

[0022] Optionally, the preset ratio ranges from 50% to 80%.

[0023] In a second aspect, an embodiment of the present application provides a device for identifying lane lines in an underground garage image, comprising:

[0024] A classification module is used to classify all lines in the underground garage map according to color and layer, and divide lines belonging to the same layer and the same color into the same line set;

[0025] an extraction module, configured to extract at least one lane space from the underground garage map; wherein the lane space is a space between two parking spaces containing lane lines or a space between a parking space containing lane lines and a wall;

[0026] a screening module, configured to screen out suspected lane line sets based on the number of lane spaces crossed by each line in each line set;

[0027] The verification module is used to verify each of the suspected lane lines in the suspected lane line set, and use the suspected lane lines that pass the verification as the target lane lines in the underground garage map.

[0028] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, and a communication bus, wherein the processor and the memory communicate with each other via the communication bus;

[0029] The memory is used to store computer programs;

[0030] The processor is used to execute the program stored in the memory to implement the method for identifying lane lines in the underground garage map described in the first aspect.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for identifying lane lines in an underground garage map described in the first aspect.

[0032] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application classifies all lines from the underground garage map according to layers and colors, and extracts at least one lane space from the underground garage map; screens out a set of suspected lane lines based on the number of lane spaces passed by each line in each line set; verifies each of the suspected lane lines in the set of suspected lane lines, and uses the suspected lane lines that pass the verification as the target lane lines in the underground garage map. In the embodiment of the present application, lane lines are identified based on the drawing characteristics of the lane lines in the underground garage map, and lane lines can be accurately identified even in a relatively complex underground garage map. Moreover, the implementation method provided by the embodiment of the present application does not require the use of an image of the underground garage map, and does not require processing of complex images. The processing method is simpler and the recognition efficiency is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0035] Figure 1 A schematic flow chart of a method for identifying lane lines in an underground garage image provided by an embodiment of the present application;

[0036] Figure 2 A schematic diagram of a lane space provided in an embodiment of the present application;

[0037] Figure 3 A schematic diagram of the structure of a device for identifying lane lines in an underground garage map provided by an embodiment of the present application;

[0038] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0040] While the underground garage map is complex and often cluttered, resulting in low-quality drawings, the lane lines are still traceable. While most layer names are meaningless, lane lines within the same frame are all drawn on the same layer and using the same standard line. From a business perspective, lane lines in underground garage maps primarily represent the median line, which is typically located near a parking space.

[0041] Based on the characteristics of lane lines in underground garage maps, this embodiment of the present application provides a method for identifying lane lines in underground garage maps to address the technical problem of generally low efficiency and accuracy in lane line recognition in the existing technology. The method for identifying lane lines in underground garage maps provided in this embodiment of the present application actually mainly identifies the median line of the lane in the underground garage map.

[0042] like Figure 1As shown, the embodiment of the present application provides a method for identifying lane lines in an underground garage image, which specifically includes the following steps:

[0043] Step 101: Classify all lines in the underground garage map according to color and layer, and group lines belonging to the same layer and having the same color into the same line set;

[0044] In the implementation, all lines in the underground garage map are traversed, including straight segments and arc segments. Then, they are classified by color and layer. Lines belonging to the same layer and the same color are classified as the same class and grouped into the same line set.

[0045] A single layer can contain lines of multiple colors. By classifying them by color and layer, we can obtain line sets of different colors for different layers. This means that a single layer can be classified into multiple line sets. For example, if we classify all the lines in an underground garage image by color and layer, we can obtain the following: for layer A, we can obtain the yellow line set and the green line set; for layer B, we can obtain the red line set and the blue line set, and so on.

[0046] Step 102: extract at least one lane space from the underground garage map; wherein the lane space is a space between two parking spaces with lane lines or a space between a parking space with lane lines and a wall;

[0047] Lane space is the space without parking lines and is consistent with the width of the road. The spacing is generally within a preset distance range. Figure 2 As shown, the space between the second row of parking spaces and the third row of parking spaces is the lane space (as shown in FIG. Figure 2 The lane space is most likely the road in the underground garage, and the lines within the lane space are most likely lane markings. In this embodiment, the lane markings primarily refer to the lane medians in the underground garage image, as only the lane medians are typically drawn in underground garage images.

[0048] The preset distance range can be set according to actual needs, for example, the preset distance range is set to 5 to 9 meters.

[0049] In a specific embodiment, the embodiment of the present application provides a method for extracting lane space, specifically including: extracting all parking spaces from the underground garage map; for any two parallel parking spaces, if the ratio of the overlapping area after any one of the any two parallel parking spaces is parallelly projected onto the other parking space exceeds a first preset ratio, then calculating the distance between the any two parallel parking spaces; if the distance is within a preset distance range and there are no other parking spaces between the any two parallel parking spaces, then extracting the space between the any two parallel parking spaces as the lane space.

[0050] by Figure 2 For example, in Figure 2 There is a first space between parking spaces A and B, and a second space between parking spaces A and C. If there is no parking space in the first space, the first space will be used as the lane space (e.g. Figure 2 and there is a parking space B in the second space, the second space is not used as a lane space.

[0051] For distance calculation, the distance between the two is first calculated in the diagram, and then the actual distance value is calculated based on the scale of the underground garage diagram. In addition, in a specific implementation, the first preset ratio can be set as needed, for example, the first preset ratio is set to 50%.

[0052] Step 103: screening out suspected lane line sets based on the number of lane spaces crossed by each line in each line set;

[0053] In the underground garage image, the lane space represents the roadway within the underground garage, with a lane centerline drawn in the middle. Based on this business characteristic, a set of suspected lane lines is selected from each set of lines. Lines in the set of suspected lane lines are considered suspected lane lines.

[0054] The suspected lane line set is screened out based on the number of lane spaces passed through by each line in each line set, including:

[0055] For each of the line sets, if the ratio of the number of the lane spaces to the total number of all lane spaces exceeds a second preset ratio, the line set is used as the suspected lane line set.

[0056] For ease of understanding, here is an example: if 500 lane spaces are determined according to step 102, the number of lane spaces passed by the lines of each line set is counted. The layer corresponding to the line set with the largest number of lane spaces is most likely the layer where the parking lines are located. At the same time, the line color that appears most frequently is most likely the color of the parking lines.

[0057] For example, if we count lines that fall within 500 lane spaces, the blue line segments in layer A cross 480 spaces, the red line segments in layer A cross 30 spaces, the yellow line segments in layer B cross 250 spaces, and the green line segments in layer B cross 350 spaces. For the blue line segments in layer A, the ratio is 480 / 500 = 96%; for the red line segments in layer A, the ratio is 30 / 500 = 6%; for the yellow line segments in layer B, the ratio is 250 / 500 = 50%; and for the green line segments in layer B, the ratio is 350 / 500 = 70%. Assuming the preset ratio is 50%, the blue line set in layer A, the yellow line set in layer B, and the green line set in layer B will all be filtered out, and the blue line set in layer A, the yellow line set in layer B, and the green line set in layer B will be the suspected lane line set. If the preset ratio is set to 80%, only the blue line set of layer A will be filtered out, and the blue line set of layer A is the suspected lane line set.

[0058] In specific implementation, the second preset ratio can be selected according to actual conditions. Generally, the second preset ratio is greater than 50%. Optionally, the second preset ratio has a value range of 50% to 80%. Preferably, the second preset ratio is 80%.

[0059] Step 104 : Verify each of the suspected lane lines in the suspected lane line set, and use the suspected lane lines that pass the verification as target lane lines in the underground garage map.

[0060] In the specific implementation, verification is performed based on the characteristics of underground garage lane lines. The characteristics of underground garage lane lines include: 1. Not passing through any parking space; 2. Not passing through any wall.

[0061] Based on the business characteristics of the above-mentioned underground garage lane lines, for each suspected lane line in the suspected lane line set, if it is determined that the suspected lane line does not pass through any parking space and the suspected lane line does not pass through any wall, the suspected lane line is determined to be the target lane line.

[0062] Furthermore, if lane lines in the underground garage map are within a certain range of parking spaces, the verification process can also use this characteristic to identify suspected lane lines. Specifically, for each suspected lane line in the set of suspected lane lines, if there is at least one parking space within the preset range of the suspected lane line, the suspected lane line is used as the target lane line.

[0063] In addition, it should be noted that, in a specific implementation, in order to make the identified lane line more accurate, the above-mentioned multiple conditions can be checked at the same time. Only when multiple conditions are met at the same time, the suspected lane line is determined to be the target lane line.

[0064] In an embodiment of the present application, all lines in the underground garage map are classified according to layer and color, and at least one lane space is extracted from the underground garage map; a set of suspected lane lines is screened out based on the number of lane spaces passed by each line in each line set; each of the suspected lane lines in the set of suspected lane lines is verified, and the suspected lane lines that pass the verification are used as target lane lines in the underground garage map. In an embodiment of the present application, lane lines are identified based on their drawing characteristics in the underground garage map, and lane lines can be accurately identified even in a relatively complex underground garage map. Moreover, the implementation method provided in the embodiment of the present application does not require the use of an image of the underground garage map, and does not require processing of complex images. The processing method is simpler and the recognition efficiency is higher.

[0065] Based on the same concept, the embodiment of the present application provides a device for identifying lane lines in an underground garage map. The specific implementation of the device can be found in the description of the method embodiment part, and the repeated parts will not be repeated. Figure 3 As shown, the device mainly includes:

[0066] The classification module 301 is used to classify all lines in the underground garage map according to color and layer, and divide the lines belonging to the same layer and the same color into the same line set;

[0067] An extraction module 302 is configured to extract at least one lane space from the underground garage map; wherein the lane space is a space between two parking spaces having lane lines or a space between a parking space having lane lines and a wall;

[0068] A screening module 303 is configured to screen out suspected lane line sets based on the number of lane spaces passed through by each line in each line set;

[0069] The verification module 304 is configured to verify each of the suspected lane lines in the suspected lane line set, and use the suspected lane lines that pass the verification as target lane lines in the underground garage map.

[0070] In a specific embodiment, the extraction module 302 is used to extract all parking spaces from the underground garage map; for any two parallel parking spaces, if the ratio of the overlapping area after any one of the any two parallel parking spaces is parallelly projected onto the other parking space exceeds a first preset ratio, then the distance between the any two parallel parking spaces is calculated; if the distance is within the preset distance range and there is no other parking space between the any two parallel parking spaces, then the space between the any two parallel parking spaces is extracted as the lane space.

[0071] In the underground garage image, the lane space is the underground road, with a lane centerline drawn in the middle of the road. Based on this business characteristic, we filter out suspected lane lines from each line set.

[0072] In a specific embodiment, the extraction module 302 is used to extract walls from the underground garage map; for any parking space, if the distance between the parking space and the wall is within a preset distance range and there is no other parking space between the parking space and the wall, the space between the parking space and the wall is extracted as the lane space.

[0073] In a specific embodiment, the screening module 303 is configured to, for each of the line sets, consider the line set as the suspected lane line set if the ratio of the number of lane spaces to the total number of all lane spaces exceeds a second preset ratio.

[0074] In a specific implementation, verification is performed based on the characteristics of underground garage lane lines. These characteristics include: 1. not passing through any parking space; 2. not passing through any wall. Specifically, in one embodiment, verification module 304 is configured to, for each suspected lane line in the set of suspected lane lines, determine that the suspected lane line is the target lane line if it is determined that the suspected lane line does not pass through any parking space and does not pass through any wall.

[0075] In addition, if the lane lines in the underground garage map are adjacent to parking spaces within a certain range, the suspected lane lines can be verified based on the business characteristics of the lane lines in the underground garage map. Specifically, if there is at least one parking space within the preset range of the suspected lane line, the suspected lane line is used as the target lane line. Specifically, in a specific embodiment, the verification module 304 is configured to, for each suspected lane line in the suspected lane line set, use the suspected lane line as the target lane line if there is at least one parking space within the preset range of the suspected lane line.

[0076] In addition, it should be noted that, in a specific implementation, in order to make the identified lane line more accurate, the above-mentioned multiple conditions can be checked at the same time. Only when multiple conditions are met at the same time, the suspected lane line is determined to be the target lane line.

[0077] In a specific embodiment, the second preset ratio ranges from 50% to 80%.

[0078] In an embodiment of the present application, all lines in the underground garage map are classified according to layer and color, and at least one lane space is extracted from the underground garage map; a set of suspected lane lines is screened out based on the number of lane spaces passed by each line in each line set; each of the suspected lane lines in the set of suspected lane lines is verified, and the suspected lane lines that pass the verification are used as target lane lines in the underground garage map. In an embodiment of the present application, lane lines are identified based on their drawing characteristics in the underground garage map, and lane lines can be accurately identified even in a relatively complex underground garage map. Moreover, the implementation method provided in the embodiment of the present application does not require the use of an image of the underground garage map, and does not require processing of complex images. The processing method is simpler and the recognition efficiency is higher.

[0079] Based on the same concept, an electronic device is also provided in the embodiment of the present application, such as Figure 4 As shown, the electronic device mainly includes: a processor 401, a memory 402 and a communication bus 403, wherein the processor 401 and the memory 402 communicate with each other via the communication bus 403. The memory 402 stores a program that can be executed by the processor 401, and the processor 401 executes the program stored in the memory 402 to implement the following steps:

[0080] Classify all lines in the underground garage map according to color and layer, and group lines belonging to the same layer and with the same color into the same line set;

[0081] Extracting at least one lane space from the underground garage map; wherein the lane space is a space between two parking spaces containing lane lines or a space between a parking space containing lane lines and a wall;

[0082] Screening out suspected lane line sets based on the number of lane spaces passed by each line in each line set;

[0083] Each suspected lane line in the suspected lane line set is verified, and the suspected lane line that passes the verification is used as the target lane line in the underground garage map.

[0084] The communication bus 403 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 403 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0085] The memory 402 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor 401.

[0086] The above-mentioned processor 401 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., and can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0087] In another embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program runs on a computer, the computer executes the method for identifying lane lines in an underground garage map described in the above embodiment.

[0088] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instruction is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instruction can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instruction is transmitted from a website, computer, server or data center to another website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (such as a floppy disk, hard disk, tape, etc.), an optical medium (such as a DVD) or a semiconductor medium (such as a solid-state hard disk), etc.

[0089] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0090] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is intended to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for identifying lane lines in an underground garage map, characterized in that: include: Classifying all the lines in the underground garage map according to color and layer, and dividing the lines belonging to the same layer and having the same color into the same line set; Extracting at least one lane space from the underground garage map; wherein the lane space is a space between two parking spaces including lane lines or a space between a parking space including lane lines and a wall; Filtering out suspected lane line sets according to the number of lane spaces crossed by each line in each of the line sets; Verifying each suspected lane line in the suspected lane line set, and using the suspected lane line that passes the verification as the target lane line in the underground garage map; The method of screening out a suspected lane line set according to the number of lane spaces passed by each line in each line set includes: For each of the line sets, if the ratio of the number of the lane spaces to the total number of all lane spaces exceeds a second preset ratio, the line set is used as the suspected lane line set.

2. The method for identifying lane lines in an underground garage image according to claim 1, characterized in that: The step of extracting at least one lane space from the underground garage map comprises: Extract all parking spaces from the underground garage map; For any two parallel parking spaces, if the ratio of the overlapping area after any one of the two parallel parking spaces is parallelly projected onto the other parking space exceeds a first preset ratio, the distance between the any two parallel parking spaces is calculated; if the distance is within a preset distance range and there are no other parking spaces between the any two parallel parking spaces, the space between the any two parallel parking spaces is extracted as the lane space.

3. The method for identifying lane lines in an underground garage image according to claim 2, characterized in that: The step of extracting at least one lane space from the underground garage map comprises: Extracting a wall from the underground garage map; For any one of the parking spaces, if the distance between the parking space and the wall is within a preset distance range and there is no other parking space between the parking space and the wall, the space between the parking space and the wall is extracted as the lane space.

4. The method for identifying lane lines in an underground garage map according to claim 1, characterized in that: The checking of each suspected lane line in the suspected lane line set and taking the suspected lane line that passes the check as the target lane line in the underground garage map includes: For each suspected lane line in the suspected lane line set, if it is determined that the suspected lane line does not pass through any parking space and the suspected lane line does not pass through any wall, the suspected lane line is determined to be a target lane line.

5. The method for identifying lane lines in an underground garage image according to claim 1, characterized in that: The checking of each suspected lane line in the suspected lane line set and taking the suspected lane line that passes the check as the target lane line in the underground garage map includes: For each suspected lane line in the suspected lane line set, if there is at least one parking space within a preset range of the suspected lane line, the suspected lane line is used as the target lane line.

6. The method for identifying lane lines in an underground garage map according to claim 1, characterized in that: The second preset ratio has a value range of 50% to 80%.

7. A device for identifying lane lines in an underground garage map, characterized in that: include: A classification module is used to classify all the lines in the underground garage map according to color and layer, and divide the lines belonging to the same layer and the same color into the same line set; An extraction module, configured to extract at least one lane space from the underground garage map; wherein the lane space is a space between two parking spaces including lane lines or a space between a parking space including lane lines and a wall; A screening module, used for screening out suspected lane line sets according to the number of lane spaces crossed by each line in each of the line sets; A verification module, configured to verify each of the suspected lane lines in the suspected lane line set, and use the suspected lane lines that pass the verification as the target lane lines in the underground garage map; The screening out of the suspected lane line set according to the number of lane spaces passed by each line in each line set includes: For each of the line sets, if the ratio of the number of the lane spaces to the total number of all lane spaces exceeds a second preset ratio, the line set is used as the suspected lane line set.

8. An electronic device, characterized in that: include: A processor, a memory and a communication bus, wherein the processor and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is used to execute the program stored in the memory to implement the method for recognizing lane lines in an underground garage map according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for recognizing lane lines in an underground garage map according to any one of claims 1 to 6 is implemented.

Images