Raster map quality assessment method, device, computer equipment and storage medium

Abstract

The present invention relates to the field of laser radar positioning and discloses a raster map quality assessment method, apparatus, computer equipment, and storage medium. The method comprises: obtaining a raster map to be assessed; evaluating the raster map using a first assessment method to obtain a first score, wherein the first score is negatively correlated with the number of pixels occupied by parallel line segments within the raster map; evaluating the raster map using a second assessment method to obtain a second score, wherein the second score is negatively correlated with the number of contours within the raster map; and determining a quality score for the raster map based on the first and second scores. The present invention can quickly and effectively assess the quality of raster maps, reducing the occurrence of positioning problems caused by raster map quality issues.

Description

Technical Field

[0001] The present invention relates to the field of laser radar positioning, and in particular to a grid map quality assessment method, device, computer equipment and storage medium. Background Art

[0002] Currently, indoor wheeled mobile robots often use 2D LiDAR for positioning. The positioning accuracy of 2D LiDAR relies on the grid map generated during laser mapping. Therefore, the quality of the grid map largely determines the positioning accuracy of the 2D LiDAR. A faulty grid map often causes positioning errors and loss of position during robot positioning.

[0003] Therefore, how to ensure the quality of the grid map to ensure the positioning accuracy of the 2D lidar has become a technical problem that needs to be solved urgently. Summary of the Invention

[0004] Based on this, it is necessary to provide a raster map quality assessment method, device, computer equipment and storage medium to address the above technical problems, so as to quickly and effectively assess the quality of raster maps and reduce the occurrence of positioning problems caused by raster map quality problems.

[0005] A raster map quality assessment method, comprising:

[0006] Get the raster map to be evaluated;

[0007] Evaluating the grid map using a first evaluation method to obtain a first score, wherein the first score is negatively correlated with the number of pixels occupied by a parallel line segment group in the grid map, wherein the parallel line segment group refers to a line segment group whose distance between line segments is less than a distance threshold and / or whose angle between line segments is less than an angle threshold;

[0008] evaluating the grid map using a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours within the grid map;

[0009] A quality score of the grid map is determined according to the first score and the second score.

[0010] A raster map quality assessment device, comprising:

[0011] A map acquisition module is used to obtain the raster map to be evaluated;

[0012] a first scoring module, configured to evaluate the grid map using a first evaluation method to obtain a first score, wherein the first score is negatively correlated with the number of pixels occupied by a parallel line segment group in the grid map, wherein the parallel line segment group refers to a line segment group whose distance between the line segments is less than a distance threshold and / or whose angle between the line segments is less than an angle threshold;

[0013] a second scoring module, configured to evaluate the grid map using a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours within the grid map;

[0014] A quality score determination module is configured to determine a quality score of the grid map according to the first score and the second score.

[0015] A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the above-mentioned grid map quality assessment method is implemented.

[0016] One or more readable storage media storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors execute the above-mentioned grid map quality assessment method.

[0017] The above-described raster map quality assessment method, apparatus, computer device, and storage medium obtain a raster map to be evaluated to obtain a scoring target. The raster map is evaluated using a first assessment method to obtain a first score. The first score is negatively correlated with the number of pixels occupied by parallel line segment groups within the raster map. Parallel line segment groups are groups where the distance between them is less than a distance threshold and / or the angle between them is less than an angle threshold. In this case, the first score can reflect the number of mapping errors caused by ghosting objects within the map. The raster map is evaluated using a second assessment method to obtain a second score. The second score is negatively correlated with the number of contours within the raster map. In this case, the second score can reflect the number of mapping errors caused by intersections of edge contour lines. A quality score for the raster map is determined based on the first and second scores, providing a comprehensive evaluation of the raster map and obtaining a final quality score. The present invention can quickly and effectively assess raster map quality, reducing the occurrence of positioning problems caused by raster map quality issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 This is a flow chart of a method for evaluating the quality of a grid map according to an embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram showing an error in the corner position lines (right angles) of a grid map according to one embodiment of the present invention;

[0021] Figure 3 In one embodiment of the present invention, a grid ground is set by a preset threshold. Figure 2 The first binary image formed after valuing;

[0022] Figure 4 is a preset morphological structure element kernel having an enlarged size of 7*7 px and not rotated in one embodiment of the present invention;

[0023] Figure 5 is a processed image formed after being processed by a morphological closing operation in one embodiment of the present invention;

[0024] Figure 6 is a raster map before binarization in one embodiment of the present invention;

[0025] Figure 7 is a second binary image binarized by the maximum inter-class variance algorithm in one embodiment of the present invention;

[0026] Figure 8 is a structural diagram of a grid map quality assessment device according to an embodiment of the present invention;

[0027] Figure 9 FIG. 1 is a schematic diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0029] In one embodiment, if Figure 1 As shown, a grid map quality assessment method is provided, comprising the following steps:

[0030] S10. Obtain a grid map to be evaluated.

[0031] The grid map to be evaluated can be the one generated by a LiDAR during laser mapping. In a correct grid map, the same object appears only once. However, when the grid map is incorrect, the same object may be reconstructed multiple times. These multiple reconstructions produce several short, parallel line segments.

[0032] For example, in one scene, a partition will form a line segment on the map. If the object is reconstructed, another line segment will be formed. These two line segments will be approximately parallel, that is, two line segments whose distance is less than a distance threshold and / or whose angle is less than an angle threshold can be considered as a parallel line segment group.

[0033] In other cases, such as Figure 2 As shown, for the corner position in the grid map, if the map is built correctly, the right angle 001 and the right angle 002 representing the corner position will completely overlap. If the map is built incorrectly, the right angle 001 and the right angle 002 will intersect, forming Figure 2 The triangular closed area in .

[0034] S20. Evaluate the grid map using a first evaluation method to obtain a first score, where the first score is negatively correlated with the number of pixels occupied by a parallel line segment group in the grid map, wherein the parallel line segment group refers to a line segment group in which a distance between line segments is less than a distance threshold and / or an angle between line segments is less than an angle threshold.

[0035] Understandably, the first evaluation method is used to evaluate the number of parallel line segment groups within a raster map. Parallel line segment groups can be extracted from the raster map through specific image processing measures, and the pixels occupied by them can be counted. These parallel line segment groups are typically short. The greater the number of parallel line segment groups (based on the pixels occupied), the more erroneous areas caused by object reconstruction within the raster map. A first score can be calculated based on the number of parallel line segment groups. In one example, the first score is inversely proportional to the number of parallel line segment groups. That is, the first score is negatively correlated with the pixels occupied by the parallel line segment groups within the raster map.

[0036] Optionally, the distance between two line segments refers to the shortest distance between the two line segments, and the angle between two line segments can be considered as the angle formed by the extension lines of the two line segments. The distance threshold and angle threshold can be set according to actual needs.

[0037] In an optional scenario, the angle threshold may specifically be 30°, that is, if the angle formed by the extension lines of two line segments is less than 30°, the two line segments may be considered to be a parallel line segment group.

[0038] In an optional scenario, if the angle formed by the extension lines of two line segments is 0° (ie, the two line segments are parallel), the two line segments may also be considered to be a parallel line segment group.

[0039] In an optional embodiment, the distance threshold may be a pixel distance or an actual distance, which is not limited here.

[0040] If the number of parallel line segments is small, it means that the reconstruction of the object in the raster map has fewer errors, and the first score is higher. Conversely, if the number of parallel line segments is large, it means that the reconstruction of the object in the raster map has more errors, and the first score is lower.

[0041] S30: Evaluate the grid map using a second evaluation method to obtain a second score, where the second score is negatively correlated with the number of contours in the grid map.

[0042] Understandably, the second evaluation method is used to assess the number of contours within the grid map. When mapping errors occur, corner locations can create several closed areas, which increase the number of contours within the grid map. A second score can be calculated based on the number of contours counted. In one example, the second score is inversely proportional to the number of contours. In other words, the second score is negatively correlated with the number of contours within the grid map.

[0043] A smaller number of contours indicates that the corners generate fewer closed areas, and the second score is higher. Conversely, a larger number of contours indicates that the corners generate more closed areas, and the second score is lower.

[0044] S40: Determine a quality score of the grid map according to the first score and the second score.

[0045] Understandably, the quality score of the raster map can be determined based on the first score and the second score. In one example, the weighting factor of the first score and the weighting factor of the second score can be adjusted according to actual needs to obtain a more suitable quality score. The obtained quality score can, to a certain extent, reflect the number of errors in the raster map (including object ghosting errors caused by object reconstruction and errors at the edges of idle areas (such as right-angle intersections in wall corners)). The higher the score, the fewer errors. The installer can decide whether to use the raster map or reconstruct the map based on the quality score.

[0046] In steps S10-S40, a raster map to be evaluated is obtained to obtain a scoring object. The raster map is evaluated using a first evaluation method to obtain a first score. The first score is negatively correlated with the number of pixels occupied by parallel line segment groups within the raster map. Parallel line segment groups are groups of line segments whose distance between them is less than a distance threshold and / or whose angle is less than an angle threshold. In this case, the first score can reflect the number of map errors caused by ghosting objects within the map. The raster map is evaluated using a second evaluation method to obtain a second score. The second score is negatively correlated with the number of contours within the raster map. In this case, the second score can reflect the number of map errors caused by intersections of edge contour lines. The quality score of the raster map is determined based on the first and second scores to comprehensively evaluate the raster map and obtain a final quality score.

[0047] Optionally, step S20, i.e., evaluating the grid map using a first evaluation method to obtain a first score, wherein the first score is negatively correlated with the number of pixels occupied by parallel line segment groups in the grid map, includes:

[0048] S201, the grid is divided into Figure 2 valorization to form a first binary image;

[0049] S202, performing a morphological closing operation on the first binary image using a plurality of preset morphological structuring element cores to obtain a corresponding plurality of processed images containing parallel line segment groups, wherein one preset morphological structuring element core corresponds to one processed image;

[0050] S203, counting the total number of pixels of all parallel line segment groups in the processed images without repetition;

[0051] S204: Determine the first score according to a ratio of the total pixels of the grid map to the total number of pixels of the parallel line segment group.

[0052] It is understandable that the preset threshold can be set according to actual needs. The range of the preset threshold can be 80-150. In one example, the preset threshold can be set to 120. That is, the grayscale value of pixels with a grayscale value less than or equal to 120 is set to 0 (black), and the grayscale value of pixels with a grayscale value greater than 120 is set to 255 (white). If there are unknown grids in the grid map, the grayscale value of the unknown grid can be set to 0 (consistent with the grayscale of the idle area). Figure 2 After valuing, the first binary image can be formed. Figure 3 As shown, Figure 3 is the first binary image of an example.

[0053] The preset morphological structure element kernel can be a unit image used for image processing. Figure 4 As shown, Figure 4 It is a preset morphological structure element kernel with an enlarged size of 7*7px and no rotation (the surrounding black is the background. If the black background is not added, the parallel white line segments are not easy to observe). Morphological closing operation (Closing Openration) is an image morphological operation, and its processing logic is to expand first and then corrode. Using a preset morphological structure element kernel to perform morphological closing operation on the raster map can obtain a processed image containing a group of parallel line segments. Using multiple preset morphological structure element kernels to perform morphological closing operation on the raster map can obtain corresponding multiple processed images containing a group of parallel line segments. Figure 5 As shown, Figure 5 This is a processed image formed after an example is processed by morphological closing operation.

[0054] The total number of pixels occupied by parallel line segments (i.e., pixels with a grayscale value of 255) in all processed images is counted without duplication. If the grayscale value of the pixel at the same position in different processed images is 255, it is counted only once.

[0055] After obtaining the total number of pixels, the first score can be calculated by the following formula:

[0056] S1=N / M

[0057] Where S1 is the first score, N is the total number of pixels in the grid map, and M is the total number of pixels in the parallel line segment group.

[0058] Optionally, the preset morphological structure element kernel is a binary image of a preset size, and the binary image includes a pair of parallel line segments with a width of 1 pixel.

[0059] It is understandable that the preset morphological structure element kernel can be a binary image of a preset size. The preset sizes include but are not limited to 3*7px, 5*7px, 7*7px, 9*7px, and 11*11px. The binary image contains a pair of parallel line segments. Figure 4 As shown, in a pair of parallel line segment groups, the width of the upper parallel line segment group is 1 pixel, and the width of the lower parallel line segment group is 1 pixel.

[0060] A preset morphological structuring element kernel of a certain size can be rotated by a certain angle to obtain a new morphological structuring element kernel. For example, the rotation angles can be 30°, 45°, 60°, 90°, 120°, 135°, and 150°. In other words, in the preset morphological structuring element kernel, the angle between the parallel line segments and the horizontal line ranges from 0° to 180°.

[0061] Binary images of various sizes can be selected as needed. The parallel line segment groups in each processed image are identical in shape (including size and angle) to the parallel line segment groups in the corresponding preset morphological structuring element kernel. Therefore, selecting several binary images of varying sizes and angles can help improve the extraction rate of parallel line segment groups from the raster map. A higher extraction rate for parallel line segment groups more accurately reflects the number of times objects within the raster map have been reconstructed, resulting in a more accurate quality score.

[0062] Optionally, step S30, i.e., evaluating the grid map using a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours in the grid map, includes:

[0063] S301, the grid is divided into Figure 2 valorization to form a second binary image;

[0064] S302, detecting the number of contours of the second binary image using a preset contour detection algorithm;

[0065] S303: Determine the second score according to the area of ​​the grid map and the number of contours.

[0066] Understandably, the maximum inter-class variance algorithm, also known as the Otsu method (OTSU), is an algorithm for determining the image binarization segmentation threshold. Before binarization, if there are unknown grids in the raster map, the grayscale value of the unknown grid can be modified to 0. Figure 2 The second binary image can be formed by valuing. Figure 6 and Figure 7 As shown, Figure 6 is the raster map before binarization, Figure 7 It is the second binary image after binarization by the maximum inter-class variance algorithm.

[0067] The preset contour detection algorithm may be a Suzuki contour tracking algorithm. The preset contour detection algorithm may detect all contours in the second binary image, including inner contours and outer contours. The number of contours refers to the total number of all contours.

[0068] After obtaining the number of contours, the second score can be calculated using the following formula:

[0069] S2=S / C

[0070] Among them, S2 is the second score, S is the area of ​​the grid map, and C is the number of contours.

[0071] Optionally, the quality score is a weighted average of the first score and the second score, the weight factor of the first score is 0.2 to 0.8, and the sum of the weight factor of the first score and the weight factor of the second score is 1.

[0072] Understandably, the quality score can be calculated by the following formula:

[0073] Score=w1*S1+w2*S2

[0074] Among them, Score is the quality score, w1 is the weight factor of the first score, S1 is the first score, w2 is the weight factor of the second score, S2 is the second score, and w1+w2=1.

[0075] The weight factor w1 of the first score is 0.2 to 0.8, and the weight factor w2 of the second score is 0.2 to 0.8. In one example, w1 = 0.7, and in this case, w2 = 0.3.

[0076] Optionally, after step S40, i.e., determining the quality score of the grid map according to the first score and the second score, the step further includes:

[0077] S50: Determine whether the quality score is not less than a preset score threshold;

[0078] S60: If the quality score is not less than a preset score threshold, the quality of the grid map is determined to be qualified.

[0079] It is understood that the preset scoring threshold can be set according to actual needs. In one example, the preset scoring threshold can be set to 2000. If the quality score is not less than the preset scoring threshold, the quality of the raster map is determined to be acceptable and the raster map can be used. If the quality score is less than the preset scoring threshold, the quality of the raster map is determined to be unacceptable and a new raster map needs to be created.

[0080] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0081] In one embodiment, a grid map quality assessment device is provided, which corresponds to the grid map quality assessment method in the above embodiment. Figure 8 As shown, the grid map quality assessment device includes a map acquisition module 10, a first scoring module 20, a second scoring module 30 and a quality score determination module 40. The functional modules are described in detail as follows:

[0082] A map acquisition module 10 is used to acquire a grid map to be evaluated;

[0083] A first scoring module 20 is configured to evaluate the grid map using a first evaluation method to obtain a first score, wherein the first score is negatively correlated with the number of pixels occupied by parallel line segment groups in the grid map;

[0084] A second scoring module 30 is configured to evaluate the grid map using a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours within the grid map;

[0085] The quality score determination module 40 is configured to determine a quality score of the grid map according to the first score and the second score.

[0086] Optionally, the first scoring module 20 includes:

[0087] The first binarization unit is used to binarize the grid area by a preset threshold. Figure 2 valuate to form a first binary image;

[0088] a closing operation unit, configured to perform a morphological closing operation on the first binary image using a plurality of preset morphological structuring element cores to obtain a corresponding plurality of processed images containing parallel line segment groups, wherein one of the preset morphological structuring element cores corresponds to one of the processed images;

[0089] a pixel counting unit, configured to count the total number of pixels of all parallel line segment groups in the processed images without repetition;

[0090] A first scoring unit is obtained, configured to determine the first score according to a ratio of the total pixels of the grid map to the total number of pixels of the parallel line segment group.

[0091] Optionally, the preset morphological structure element kernel is a binary image of a preset size, and the binary image includes a pair of parallel line segments with a width of 1 pixel.

[0092] Optionally, the preset sizes include 3*7px, 5*7px, 7*7px, 9*7px, and 11*11px, and the angle formed by the group of parallel line segments in the binary image and the horizontal line ranges from 0° to 180°.

[0093] Optionally, the second scoring module 30 includes:

[0094] The second binarization unit is used to convert the grid area into Figure 2 valorization to form a second binary image;

[0095] a contour counting unit, configured to detect the number of contours of the second binary image using a preset contour detection algorithm;

[0096] A second scoring unit is obtained, configured to determine the second score according to the area of ​​the grid map and the number of contours.

[0097] Optionally, the quality score is a weighted average of the first score and the second score, the weight factor of the first score is 0.2 to 0.8, and the sum of the weight factor of the first score and the weight factor of the second score is 1.

[0098] Optionally, the grid map quality assessment device further includes:

[0099] A threshold judgment module is used to judge whether the quality score is not less than a preset score threshold;

[0100] The quality determination module is configured to determine that the quality of the grid map is qualified if the quality score is not less than a preset score threshold.

[0101] The specific definition of the raster map quality assessment device can be found in the definition of the raster map quality assessment method above and will not be repeated here. The various modules in the above-mentioned raster map quality assessment device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0102] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 9 As shown. The computer device includes a processor, memory, network interface, display screen and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer-readable instructions. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer-readable instructions are executed by the processor, a raster map quality assessment method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0103] In one embodiment, a computer device is provided, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the following steps are implemented:

[0104] Get the raster map to be evaluated;

[0105] Evaluating the grid map using a first evaluation method to obtain a first score, wherein the first score is negatively correlated with the number of pixels occupied by a parallel line segment group in the grid map, wherein the parallel line segment group refers to a line segment group whose distance between the line segments is less than a distance threshold and / or whose angle between the line segments is less than an angle threshold;

[0106] evaluating the grid map using a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours within the grid map;

[0107] A quality score of the grid map is determined according to the first score and the second score.

[0108] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The computer-readable storage media provided in this embodiment include non-volatile computer-readable storage media and volatile computer-readable storage media. The computer-readable storage media store computer-readable instructions that, when executed by one or more processors, implement the following steps:

[0109] Get the raster map to be evaluated;

[0110] Evaluating the grid map using a first evaluation method to obtain a first score, wherein the first score is negatively correlated with the number of pixels occupied by a parallel line segment group in the grid map, wherein the parallel line segment group refers to a line segment group whose distance between line segments is less than a distance threshold and / or whose angle between line segments is less than an angle threshold;

[0111] evaluating the grid map using a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours within the grid map;

[0112] A quality score of the grid map is determined according to the first score and the second score.

[0113] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0114] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0115] The embodiments described above 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 they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for evaluating the quality of a raster map, characterized in that: include: Get the raster map to be evaluated; Evaluating the grid map using a first evaluation method to obtain a first score, wherein the first evaluation method is used to evaluate the number of parallel line segment groups in the grid map, and the first score is negatively correlated with the number of pixels occupied by the parallel line segment groups in the grid map, wherein the parallel line segment groups are line segment groups whose distance between the line segments is less than a distance threshold and / or whose angle between the line segments is less than an angle threshold; evaluating the grid map using a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours within the grid map; A quality score of the grid map is determined according to the first score and the second score.

2. The grid map quality assessment method according to claim 1, wherein: The first evaluation method is used to evaluate the grid map to obtain a first score, wherein the first evaluation method is used to evaluate the number of parallel line segment groups in the grid map, and the first score is negatively correlated with the number of pixels occupied by the parallel line segment groups in the grid map, including: Binarizing the grid map using a preset threshold to form a first binary map; Performing a morphological closing operation on the first binary image using a plurality of preset morphological structure element cores to obtain a corresponding plurality of processed images containing parallel line segment groups, wherein one of the preset morphological structure element cores corresponds to one of the processed images; Counting the total number of pixels of the parallel line segment groups in all the processed images without repetition; The first score is determined according to a ratio of the total pixels of the grid map to the total number of pixels of the parallel line segment group.

3. The grid map quality assessment method according to claim 2, wherein: The preset morphological structure element kernel is a binary image of a preset size, and the binary image includes a pair of parallel line segments with a width of 1 pixel.

4. The grid map quality assessment method according to claim 3, wherein: The preset sizes include 3*7px, 5*7px, 7*7px, 9*7px, and 11*11px, and the angle between the parallel line segment group in the binary image and the horizontal line ranges from 0 to 180 degrees.

5. The grid map quality assessment method according to claim 1, wherein: The step of evaluating the grid map by a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours in the grid map, includes: Binarizing the grid map using a maximum inter-class variance algorithm to form a second binary map; Detecting the number of contours in the second binary image using a preset contour detection algorithm; The second score is determined according to the area of ​​the grid map and the number of contours.

6. The grid map quality assessment method according to claim 1, wherein: The quality score is a weighted average of the first score and the second score, the weight factor of the first score is 0.2-0.8, and the sum of the weight factor of the first score and the weight factor of the second score is 1.

7. The grid map quality assessment method according to claim 1, wherein: After determining the quality score of the grid map according to the first score and the second score, the method further includes: Determining whether the quality score is not less than a preset score threshold; If the quality score is not less than a preset score threshold, the quality of the grid map is determined to be qualified.

8. A grid map quality assessment device, characterized in that: include: A map acquisition module is used to obtain the raster map to be evaluated; a first scoring module, configured to evaluate the grid map using a first evaluation method to obtain a first score, wherein the first evaluation method is configured to evaluate the number of parallel line segment groups within the grid map, the first score being negatively correlated with the number of pixels occupied by the parallel line segment groups within the grid map, wherein the parallel line segment groups are line segment groups whose distance between the line segments is less than a distance threshold and / or whose angle between the line segments is less than an angle threshold; a second scoring module, configured to evaluate the grid map using a second evaluation method to obtain a second score, wherein the second score is negatively correlated with the number of contours within the grid map; A quality score determination module is configured to determine a quality score of the grid map according to the first score and the second score.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein: When the processor executes the computer-readable instructions, the grid map quality assessment method according to any one of claims 1 to 7 is implemented.

10. One or more readable storage media storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors execute the grid map quality assessment method according to any one of claims 1 to 7.

Images