Road surface well lid detection method and device based on precise three-dimensional image

Abstract

The invention relates to the technical field of pavement detection, and provides a pavement manhole cover detection method and device based on a precise three-dimensional image. The method comprises the following steps: based on a preset knowledge graph, obtaining a plurality of initial well lid areas in an elevation three-dimensional modeling image of a to-be-measured road surface; taking the central position of the initial well lid area as a reference point, and obtaining an initial representative edge position based on a plurality of preset standard well lid edge positions; expanding the initial representative edge position into a target representative edge position; determining an area between the center position and the target representative edge position as a target manhole cover area; and based on the representative planes inside and outside the target well lid area and the plurality of data points in the target well lid area, determining whether the road surface well lid is defective and determining the target well frame difference. According to the method, rich road surface information is included, and adverse effects of environmental factors on data can be eliminated, so that the integrity and accuracy of road surface well lid detection information are ensured, and the well frame difference and defect conditions of the road surface well lid can be detected completely and correctly.

Description

Technical Field

[0001] The present application relates to the technical field of road surface detection, and in particular to a method and device for detecting road manhole covers based on precise three-dimensional images. Background Art

[0002] The rapid detection and positioning of manhole covers on urban roads is one of the key issues in the municipal department's pavement asset management. The relative height difference between the manhole cover frame and the road surface, i.e. the manhole frame difference, and the defects of the manhole cover directly affect the comfort and safety of vehicles and pedestrians, and are a must-check item for the quality inspection of municipal road projects.

[0003] The road manhole cover detection method currently widely used is a detection technology based on visual images. The road image of this method is easily affected by ambient light and complex measurement scenes during the acquisition process, and the road information contained in the two-dimensional road image is relatively limited. It is impossible to ensure the integrity and accuracy of the road manhole cover detection information, and thus it is impossible to ensure that the manhole cover frame difference and defects can be detected completely and accurately. Summary of the invention

[0004] The embodiments of the present application provide a road manhole cover detection method and device based on precise three-dimensional images, so as to solve the technical problem that the road surface images of the currently widely used road manhole cover detection method are easily affected by ambient light and complex measurement scenes during the acquisition process, and the two-dimensional road surface images contain relatively limited road surface information, and cannot ensure the integrity and accuracy of the road manhole cover detection information, thereby failing to ensure that the manhole cover frame differences and defects can be detected completely and accurately.

[0005] In a first aspect, an embodiment of the present application provides a road manhole cover detection method based on a precise three-dimensional image, comprising: Based on the preset knowledge graph of the manhole cover area, multiple initial manhole cover areas are obtained in the elevation 3D modeling image of the road surface to be tested; For each initial manhole cover area among the multiple initial manhole cover areas, obtaining the center position thereof; Taking the center position as a reference point, based on a plurality of preset standard manhole cover edge positions, an initial representative edge position of the initial manhole cover area is obtained; the plurality of preset standard manhole cover edge positions are obtained based on a plurality of preset standard manhole cover sizes and taking the center position as a reference point; Based on preset expansion operation parameters, the initial representative edge position is expanded to obtain a target representative edge position; Determine the area between the center position and the target representative edge position as the target manhole cover area; Determine a non-manhole cover area adjacent to the target representative edge position as a nearby road surface area; Acquire a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; Determining whether a road manhole cover is defective based on elevation deviations between a plurality of data points in the target manhole cover area and the representative manhole cover plane; Based on the elevation deviation between the representative manhole cover plane and the representative road surface plane, a target manhole frame difference of the road surface manhole cover is obtained.

[0006] In one embodiment, taking the center position as a reference point and based on a plurality of preset standard manhole cover edge positions, obtaining the initial representative edge position of the initial manhole cover area includes: According to the sampling interval of each data point in the elevation three-dimensional modeling image, the elevation mutation data points are acquired from the central position outward, and the positions of the elevation mutation data points are determined as the potential manhole cover edge positions of the initial manhole cover area; For each preset standard manhole cover edge position of the plurality of preset standard manhole cover edge positions, calculating the cumulative distance error between the potential manhole cover edge position and the preset standard manhole cover edge position to obtain a cumulative distance error set; The preset standard manhole cover edge position corresponding to the minimum cumulative distance error in the cumulative distance error set is determined as the initial representative edge position of the initial manhole cover area.

[0007] In one embodiment, obtaining the representative manhole cover plane of the target manhole cover area and the representative road surface plane of the nearby road surface area includes: Performing plane fitting on each data point in the target manhole cover area to obtain the representative manhole cover plane; Performing plane fitting on each data point in the nearby road surface area to obtain the representative road surface plane.

[0008] In one embodiment, determining whether a road manhole cover is defective based on the elevation deviation between a plurality of data points in the target manhole cover area and the representative manhole cover plane includes: For each data point in the target manhole cover area, calculating the elevation difference between the data point and the representative manhole cover plane to obtain a manhole cover deviation set; Calculating the absolute value of each manhole cover deviation in the manhole cover deviation set to obtain a manhole cover absolute deviation set; Calculate the proportion of absolute deviations of manhole covers greater than a preset manhole cover deviation threshold in the manhole cover absolute deviation set; If the number ratio is greater than a preset ratio threshold, it is determined that the road surface manhole cover corresponding to the target manhole cover area is defective; If the number ratio is less than or equal to the preset ratio threshold, it is determined that the road manhole covers corresponding to the target manhole cover area are intact.

[0009] In one embodiment, obtaining a target manhole frame difference of a road manhole cover based on an elevation deviation between the representative manhole cover plane and the representative road surface plane includes: For each data point in the representative manhole cover plane, obtaining a target data point in the representative road surface plane that is adjacent to the data point; Calculate the elevation difference between each data point in the representative manhole cover plane and its corresponding target data point to obtain a manhole frame difference set; Calculating the absolute value of each well frame difference in the well frame difference set to obtain a well frame absolute deviation set; The average value of the absolute deviations of the manhole frames that are greater than a preset manhole frame deviation threshold in the manhole frame absolute deviation set is calculated to obtain a target manhole frame difference between the target manhole cover area and the road manhole cover.

[0010] In one embodiment, the elevation three-dimensional modeling image of the road surface to be tested is obtained based on the following method: Based on the measurement attitude information of the line scanning three-dimensional measurement sensor obtained by the attitude measurement sensor, measurement attitude compensation is performed on the elevation data of the road surface to be measured obtained by the line scanning three-dimensional measurement sensor to obtain the elevation three-dimensional modeling data of the road surface to be measured; Based on the elevation three-dimensional modeling data, generating the elevation three-dimensional modeling image; The sampling spacing of the line scanning three-dimensional measurement sensor in the width direction of the road surface to be measured is less than or equal to 3 mm, the sampling spacing in the driving direction of the road surface to be measured is less than or equal to 5 mm, and the sampling accuracy in the elevation direction of the road surface to be measured is better than 0.5 mm.

[0011] In a second aspect, an embodiment of the present application provides a road manhole cover detection device based on precise three-dimensional images, comprising: An initial manhole cover area acquisition module is used to: acquire multiple initial manhole cover areas in the elevation three-dimensional modeling image of the road surface to be tested based on a preset knowledge graph of the manhole cover area; A center position acquisition module, used to: acquire the center position of each initial manhole cover area among the multiple initial manhole cover areas; An initial representative edge position acquisition module is used to: take the center position as a reference point and obtain the initial representative edge position of the initial manhole cover area based on a plurality of preset standard manhole cover edge positions; the plurality of preset standard manhole cover edge positions are obtained based on a plurality of preset standard manhole cover sizes and take the center position as a reference point; A target representative edge position acquisition module is used to: perform an expansion operation on the initial representative edge position based on preset expansion operation parameters to obtain a target representative edge position; A target manhole cover area acquisition module is used to: determine the area between the center position and the target representative edge position as the target manhole cover area; A nearby road surface area acquisition module is used to: determine a non-manhole cover area adjacent to the target representative edge position as a nearby road surface area; A representative plane acquisition module is used to: acquire a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; A manhole cover defect detection module, used to: determine whether a road manhole cover is defective based on the elevation deviation between a plurality of data points in the target manhole cover area and the representative manhole cover plane; The manhole cover and frame difference detection module is used to obtain a target manhole frame difference of the road surface manhole cover based on the elevation deviation between the representative manhole cover plane and the representative road surface plane.

[0012] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory storing a computer program, wherein when the processor executes the program, the steps of the road manhole cover detection method based on precise three-dimensional images described in the first aspect are implemented.

[0013] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the road manhole cover detection method based on precise three-dimensional images described in the first aspect.

[0014] In a fifth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the road manhole cover detection method based on precise three-dimensional images described in the first aspect.

[0015] The present application provides a road manhole cover detection method and device based on precise three-dimensional images. Based on a preset knowledge graph of the manhole cover area, multiple initial manhole cover areas in the elevation three-dimensional modeling image of the road to be tested are obtained. For each initial manhole cover area in the multiple initial manhole cover areas, its center position is obtained. Taking the center position as a reference point, based on multiple preset standard manhole cover edge positions, an initial representative edge position of the initial manhole cover area is obtained. Based on preset expansion operation parameters, an expansion operation is performed on the initial representative edge position to obtain a target representative edge position. The area between the center position and the target representative edge position is determined as the target manhole cover area, and the non-manhole cover area adjacent to the target representative edge position is determined as the nearby road surface area. The representative manhole cover plane of the target manhole cover area and the representative road surface plane of the nearby road surface area are obtained. Based on the elevation deviation between multiple data points in the target manhole cover area and the representative manhole cover plane, it is determined whether the road manhole cover is defective. Based on the elevation deviation between the representative manhole cover plane and the representative road surface plane, the target manhole frame difference of the road manhole cover is obtained. The present application utilizes the preset knowledge graph matching of the manhole cover area to obtain the initial manhole cover area in the elevation three-dimensional modeling image of the road surface to be tested. The initial manhole cover area contains the knowledge graph information and three-dimensional image information of the manhole cover area, and then introduces multiple preset standard manhole cover edge positions to perform edge positioning and edge expansion on the initial manhole cover area to determine the target manhole cover area. Finally, the point and surface data inside and outside the target manhole cover area are fully utilized to detect the manhole frame difference and defects of the road manhole cover. The above detection process covers rich road surface information such as knowledge graph information, three-dimensional image information, preset standard manhole cover edge position information, and point and surface data information, and this information can be referenced and compared with each other to eliminate the adverse effects of environmental factors on the data, thereby ensuring the integrity and accuracy of the road manhole cover detection information, and then ensuring that the manhole frame difference and defects of the road manhole cover can be detected completely and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is one of the flow diagrams of the road manhole cover detection method based on precise three-dimensional images provided in the embodiment of the present application; Figure 2 This is the second flow chart of the road manhole cover detection method based on precise three-dimensional images provided in the embodiment of the present application; Figure 3 This is the third flow chart of the road manhole cover detection method based on precise three-dimensional images provided in the embodiment of the present application; Figure 4 This is the fourth flow chart of the road manhole cover detection method based on precise three-dimensional images provided in the embodiment of the present application; Figure 5 It is a structural schematic diagram of a road manhole cover detection device based on precise three-dimensional images provided in an embodiment of the present application; Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in 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 them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] It should be noted that in the description of the embodiments of the present application, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be a connection between the two elements. For those skilled in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0020] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0021] Figure 1 This is one of the flow charts of the road manhole cover detection method based on precise three-dimensional images provided in the embodiment of the present application. Figure 1 The present application embodiment provides a road manhole cover detection method based on precise three-dimensional images, which may include: 101. Based on the preset knowledge graph of the manhole cover area, a plurality of initial manhole cover areas are obtained in the elevation three-dimensional modeling image of the road surface to be tested; 102. For each initial manhole cover area among the multiple initial manhole cover areas, obtain its center position; 103. Taking the center position as a reference point, based on a plurality of preset standard manhole cover edge positions, an initial representative edge position of the initial manhole cover area is obtained; The edge positions of a plurality of preset standard manhole covers are obtained based on the sizes of a plurality of preset standard manhole covers with the center position as a reference point; 104. Perform an expansion operation on the initial representative edge position based on preset expansion operation parameters to obtain a target representative edge position; 105. Determine the area between the center position and the edge position of the target representative as the target manhole cover area; 106. Determine the non-manhole cover area adjacent to the edge position of the target representative as the nearby road surface area; 107. Obtain a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; 108. Determine whether the road manhole cover is defective based on the elevation deviation between multiple data points in the target manhole cover area and the representative manhole cover plane; 109. Based on the elevation deviation between the plane representing the manhole cover and the plane representing the road surface, the target manhole frame difference of the road surface manhole cover is obtained.

[0022] In step 101, the preset knowledge graph of the manhole cover area includes various information of the manhole cover, such as manhole cover type, manhole cover material, manhole cover attributes, manhole cover installation location, etc., wherein the manhole cover types include rainwater manhole covers, sewage manhole covers, power communication manhole covers, tap water manhole covers, natural gas manhole covers, fire protection facility manhole covers, etc.; the manhole cover materials include cast iron, steel plates, composite materials, plastics, etc.; the manhole cover attributes include specification attributes and identification attributes, the specification attributes include diameter (for round manhole covers), side length (for square manhole covers), thickness, etc., and the identification attributes include affiliated units (such as municipal departments, telecommunications companies, etc.), uses (sewerage, communications, etc.), numbers, etc.

[0023] Since the above information will be reflected in the elevation 3D modeling data of the manhole cover area, which distinguishes it from the elevation 3D modeling data of the conventional road surface area, based on the above information, a deep learning method can be used to identify and obtain the initial manhole cover area in the elevation 3D modeling image of the road surface to be tested.

[0024] In step 102 to step 103, the center position of the initial manhole cover area is first used as the center of multiple preset standard manhole cover sizes to obtain the edge positions of the areas covered by multiple preset standard manhole cover sizes, that is, multiple preset standard manhole cover edge positions. Then, the center position of the initial manhole cover area is used as a reference point to obtain the preset standard manhole cover edge position that is closest to the edge position of the initial manhole cover area among the multiple preset standard manhole cover edge positions, and use it as the initial representative edge position.

[0025] In step 104 to step 105, although the initial representative edge position is determined to be a preset standard manhole cover edge position, there may be a certain positioning error between the preset standard manhole cover edge position obtained in the previous steps and the actual standard manhole cover edge position, that is, there is also a certain positioning error between the initial representative edge position and the actual standard manhole cover edge position. In order to avoid data loss caused by positioning errors and affect the integrity and accuracy of road manhole cover detection information, the initial representative edge position can be appropriately expanded so that the expanded target representative edge position can ensure that it is as close to the preset standard edge position while the target manhole cover area between the center position can also cover all data in the actual standard manhole cover area as much as possible, thereby improving the integrity and accuracy of road manhole cover detection information.

[0026] In step 106, the nearby road surface area is a regular road surface area outside the target manhole cover area and adjacent to the target manhole cover area, and the regular road surface area does not include a marking area, a defect area, and the like.

[0027] It should be noted that the data points in the target manhole cover area and the data points in the nearby road surface area do not include the data points representing the edge position of the target.

[0028] In step 108, if there is a defect in the manhole cover, the elevation deviation between the data points in the defective area and the representative manhole cover plane will be more prominent than the elevation deviation between other areas and the representative manhole cover plane, indicating an abnormality. Therefore, it is possible to determine whether the manhole cover is defective based on the elevation deviation between multiple data points in the target manhole cover area and the representative manhole cover plane.

[0029] In step 109, since most of the road manhole covers are installed in the road surface in an embedded form, there is inevitably a certain height difference between them and the conventional road surface. Therefore, the height difference between the road manhole cover and the conventional road surface can be determined based on the elevation deviation between the representative manhole cover plane and the representative road surface plane, which is the target manhole frame difference of the road manhole cover.

[0030] The road manhole cover detection method based on precise three-dimensional images provided in the present embodiment obtains multiple initial manhole cover areas in the elevation three-dimensional modeling image of the road to be tested based on a preset knowledge graph of the manhole cover area, obtains the center position of each initial manhole cover area in the multiple initial manhole cover areas, takes the center position as a reference point, obtains the initial representative edge position of the initial manhole cover area based on multiple preset standard manhole cover edge positions, performs an expansion operation on the initial representative edge position based on preset expansion operation parameters to obtain the target representative edge position, determines the area between the center position and the target representative edge position as the target manhole cover area, determines the non-manhole cover area adjacent to the target representative edge position as the nearby road surface area, obtains the representative manhole cover plane of the target manhole cover area and the representative road surface plane of the nearby road surface area, determines whether the road manhole cover is defective based on the elevation deviation between multiple data points in the target manhole cover area and the representative manhole cover plane, and obtains the target manhole frame difference of the road manhole cover based on the elevation deviation between the representative manhole cover plane and the representative road surface plane. This embodiment uses the preset knowledge graph matching of the manhole cover area to obtain the initial manhole cover area in the elevation three-dimensional modeling image of the road surface to be tested. The initial manhole cover area contains the knowledge graph information and three-dimensional image information of the manhole cover area, and then introduces multiple preset standard manhole cover edge positions to perform edge positioning and edge expansion on the initial manhole cover area to determine the target manhole cover area. Finally, the point and surface data inside and outside the target manhole cover area are fully utilized to detect the manhole frame difference and defects of the road manhole cover. The above detection process covers rich road information such as knowledge graph information, three-dimensional image information, preset standard manhole cover edge position information, and point and surface data information, and this information can be referenced and compared with each other to eliminate the adverse effects of environmental factors on the data, thereby ensuring the integrity and accuracy of the road manhole cover detection information, and then ensuring that the manhole frame difference and defects of the road manhole cover can be detected completely and accurately.

[0031] Figure 2 This is the second flow chart of the road manhole cover detection method based on precise three-dimensional images provided in the embodiment of the present application. Figure 2In one embodiment, taking the center position as a reference point and based on a plurality of preset standard manhole cover edge positions, obtaining the initial representative edge position of the initial manhole cover area may include: 201. According to the sampling interval of each data point in the elevation three-dimensional modeling image, obtain elevation mutation data points starting from the center position outward, and determine the position of the elevation mutation data point as the potential manhole cover edge position of the initial manhole cover area; 202. For each preset standard manhole cover edge position among a plurality of preset standard manhole cover edge positions, calculate the cumulative distance error between the potential manhole cover edge position and the preset standard manhole cover edge position to obtain a cumulative distance error set; 203. Determine the preset standard manhole cover edge position corresponding to the minimum cumulative distance error in the cumulative distance error set as the initial representative edge position of the initial manhole cover area.

[0032] In step 201, since there is usually a gap between the manhole cover area and the adjacent conventional road area, and the textures of the manhole cover area and the gap area or the adjacent conventional road area are significantly different, this will lead to a large difference between the elevation data of the manhole cover area and the elevation data of the gap area or the adjacent conventional road area. Therefore, the elevation data can be acquired from the center position outward according to the sampling interval until a sudden elevation change data point is found, indicating that the elevation data acquisition position is close to the edge position of the initial manhole cover area, so that the potential manhole cover edge position of the initial manhole cover area can be obtained. The sampling interval includes the sampling interval in the driving direction and the sampling interval in the width direction.

[0033] In step 202, that is, for any preset standard manhole cover edge position, the data point on it that is closest to each data point in the potential manhole cover edge position is obtained, and the sum of the distances between each data point in the potential manhole cover edge position and the corresponding data point closest to the preset standard manhole cover edge position is calculated to obtain the cumulative distance error between the potential manhole cover edge position and the preset standard manhole cover edge position. Similarly, for other preset standard manhole cover edge positions, the cumulative distance error between the potential manhole cover edge position and them is calculated, thereby obtaining a cumulative distance error set formed by multiple cumulative distance errors.

[0034] It should be noted that the initial manhole cover area can be square, circular or other shapes, which is not limited here, and multiple preset standard manhole covers can also be square, circular or other shapes, which is also not limited here.

[0035] This embodiment first extends outward from the center position based on the data sampling intervals in the driving direction and the width direction, and obtains the potential manhole cover edge position that is closest to the initial manhole cover area edge position, and then based on the cumulative distance errors between multiple preset standard manhole cover edge positions and the potential manhole cover edge position, the preset standard manhole cover edge position with the smallest cumulative distance error is determined as the initial representative edge position of the initial manhole cover area, and the initial representative edge position is accurately acquired through multi-directional sampling intervals to the potential manhole cover edge position and then to the initial representative edge position.

[0036] In one embodiment, obtaining a representative manhole cover plane of a target manhole cover area and a representative road surface plane of a nearby road surface area may include: Perform plane fitting on each data point in the target manhole cover area to obtain a representative manhole cover plane; Perform plane fitting on each data point in the nearby road surface area to obtain a representative road surface plane.

[0037] Plane fitting is to find an optimal plane in three-dimensional space based on each data point using a mathematical model so that the sum of the distances from each data point to the optimal plane (or some measure of the distance) is minimized.

[0038] In this embodiment, the plane fitting method may include the least squares method, the random sampling consistency algorithm, the singular value decomposition method, the gradient descent method, the principal component analysis method, etc. Any of the above plane fitting methods or a combination of multiple plane fitting methods can be used to perform plane fitting on each data point, which is not limited here.

[0039] This embodiment performs plane fitting on each data point in the target manhole cover area and each data point in the nearby road surface area, so as to obtain representative planes with better characterization capabilities for the target manhole cover area and the nearby road surface area, thereby facilitating subsequent calculation of deviations between points and planes and between planes.

[0040] Figure 3 This is the third flow chart of the road manhole cover detection method based on precise three-dimensional images provided in the embodiment of the present application. Figure 3 In one embodiment, determining whether a road manhole cover is defective based on the elevation deviation between a plurality of data points in the target manhole cover area and the representative manhole cover plane may include: 301. For each data point in the target manhole cover area, calculate the elevation difference between the data point and the representative manhole cover plane to obtain a manhole cover deviation set; 302. Calculate the absolute value of each manhole cover deviation in the manhole cover deviation set to obtain the manhole cover absolute deviation set; 303. Calculate the ratio of the absolute deviations of manhole covers in the manhole cover absolute deviation set that are greater than a preset manhole cover deviation threshold; 304. If the number ratio is greater than the preset ratio threshold, it is determined that the road surface manhole cover corresponding to the target manhole cover area is defective; 305. If the quantity ratio is less than or equal to the preset ratio threshold, it is determined that the road manhole covers corresponding to the target manhole cover area are intact.

[0041] In step 301, the elevation difference between any data point in the target manhole cover area and the representative manhole cover plane of the target manhole cover area is calculated. Similarly, the elevation differences between other data points in the target manhole cover area and the representative manhole cover plane of the target manhole cover area are calculated, thereby obtaining manhole cover deviations represented by multiple elevation differences to form a manhole cover deviation set.

[0042] In step 302 to step 303, data points corresponding to the absolute deviations of the manhole covers that are greater than a preset manhole cover deviation threshold are determined as abnormal data points.

[0043] In step 304 to step 305, when the proportion of these abnormal data points exceeds the preset proportion threshold, it is determined that there is a defect in the road manhole cover, and the treatment measures for the road manhole cover can be determined based on the specific defect situation. Otherwise, it is determined that there is no defect in the road manhole cover.

[0044] Among them, the preset proportion threshold can be set according to actual conditions and is not limited here. In this embodiment, the preset proportion threshold can be set to 30%.

[0045] This embodiment first determines the abnormal data points based on the abnormal elevation deviation between the data points and the representative manhole cover plane, and then determines whether the road manhole cover is defective based on the proportion of the abnormal data points, so as to avoid determining that the road manhole cover is defective when there are very few unavoidable error abnormal points, resulting in false detection of manhole cover defects.

[0046] Figure 4 This is the fourth flow chart of the road manhole cover detection method based on precise three-dimensional images provided in the embodiment of the present application. Figure 4 In one embodiment, obtaining a target manhole frame difference of a road manhole cover based on an elevation deviation between a representative manhole cover plane and a representative road surface plane may include: 401. For each data point in the plane representing the manhole cover, obtain a target data point adjacent to the data point in the plane representing the road surface; 402. Calculate the elevation difference between each data point in the plane representing the manhole cover and its corresponding target data point to obtain a manhole frame difference set; 403. Calculate the absolute value of each well frame difference in the well frame difference set to obtain a well frame absolute deviation set; 404. Calculate the average of the absolute deviations of the well frames that are greater than a preset well frame deviation threshold in the well frame absolute deviation set to obtain a target well frame difference between the target well cover area and the road surface well cover.

[0047] In step 401, the target data point may be a data point in the plane representing the road surface that is closest to each data point in the plane representing the manhole cover.

[0048] In step 402, the elevation difference between any data point in the manhole cover plane and its corresponding target data point is calculated. Similarly, the elevation differences between other data points in the manhole cover plane and their corresponding target data points are calculated, thereby obtaining well frame differences represented by multiple elevation differences to form a well frame difference set.

[0049] In step 403 to step 404, if the absolute deviation of the well frame is greater than the preset well frame deviation threshold, it means that the target well cover area is much higher or lower than the nearby road surface area, which is not conducive to the safety and stability of vehicle driving and pedestrian walking. Therefore, the absolute well frame deviation greater than the preset well frame deviation threshold is determined as the well frame deviation that needs to be focused on, and its average value is calculated to obtain the target well frame difference of the road manhole cover. Subsequently, the treatment measures for the road manhole cover can be determined according to the size of the target well frame difference.

[0050] This embodiment first screens out larger absolute deviations of the manhole frame based on the elevation deviations between the data points in the plane representing the manhole cover and the plane representing the road surface, and then takes their average value as the target manhole frame difference. By focusing on the larger manhole frame differences, efficient and accurate detection of abnormal manhole covers can be achieved, and measures can be taken in time to deal with abnormal manhole covers, thereby improving the safety and stability of vehicle driving and pedestrian walking.

[0051] In one embodiment, the elevation three-dimensional modeling image of the road surface to be tested can be obtained based on the following method: Based on the measurement attitude information of the line scanning 3D measurement sensor obtained by the attitude measurement sensor, measurement attitude compensation is performed on the elevation data of the road surface to be measured obtained by the line scanning 3D measurement sensor to obtain the elevation 3D modeling data of the road surface to be measured, and based on the elevation 3D modeling data, an elevation 3D modeling image is generated.

[0052] The sampling spacing of the line scanning three-dimensional measurement sensor in the width direction of the road surface to be measured is less than or equal to 3 mm, and in this embodiment, it can be less than or equal to 2 mm. The sampling spacing in the driving direction of the road surface to be measured is less than or equal to 5 mm. The sampling accuracy in the elevation direction of the road surface to be measured is better than 0.5 mm, and in this embodiment, it can be better than 0.3 mm.

[0053] This embodiment obtains elevation data of the road surface to be measured by a line scanning three-dimensional measurement sensor, and can use line scanning to cover the entire width of the road surface to be measured, thereby obtaining comprehensive and complete elevation data, and then performing measurement posture compensation to improve the accuracy of the elevation data, and finally generating an elevation three-dimensional modeling image, thereby achieving a complete and accurate three-dimensional visualization presentation of the elevation data of the road surface to be measured, which greatly facilitates the subsequent positioning of the manhole cover area and edge position, thereby improving the integrity and accuracy of the road manhole cover detection information.

[0054] The following is a description of the road manhole cover detection device based on precise three-dimensional images provided in an embodiment of the present application. The road manhole cover detection device based on precise three-dimensional images described below and the road manhole cover detection method based on precise three-dimensional images described above can be referenced to each other.

[0055] Figure 5 Schematic diagram of the structure of the road manhole cover detection device based on precise three-dimensional image provided by the embodiment of the present application. Figure 5 The embodiment of the present application provides a road manhole cover detection device based on precise three-dimensional images, which may include: The initial manhole cover area acquisition module 501 is used to: acquire multiple initial manhole cover areas in the elevation three-dimensional modeling image of the road surface to be tested based on a preset knowledge graph of the manhole cover area; The center position acquisition module 502 is used to: acquire the center position of each initial manhole cover area among the multiple initial manhole cover areas; The initial representative edge position acquisition module 503 is used to: take the center position as a reference point and obtain the initial representative edge position of the initial manhole cover area based on a plurality of preset standard manhole cover edge positions; the plurality of preset standard manhole cover edge positions are obtained based on a plurality of preset standard manhole cover sizes and take the center position as a reference point; The target representative edge position acquisition module 504 is used to: perform an expansion operation on the initial representative edge position based on preset expansion operation parameters to obtain a target representative edge position; The target manhole cover area acquisition module 505 is used to: determine the area between the center position and the target representative edge position as the target manhole cover area; A nearby road surface area acquisition module 506 is used to: determine a non-manhole cover area adjacent to the target representative edge position as a nearby road surface area; The representative plane acquisition module 507 is used to: acquire a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; A manhole cover defect detection module 508 is used to determine whether a road manhole cover is defective based on the elevation deviation between a plurality of data points in the target manhole cover area and the representative manhole cover plane; The manhole cover and frame difference detection module 509 is used to obtain a target manhole frame difference of the road surface manhole cover based on the elevation deviation between the representative manhole cover plane and the representative road surface plane.

[0056] The road manhole cover detection device based on precise three-dimensional images provided in the present embodiment obtains multiple initial manhole cover areas in the elevation three-dimensional modeling image of the road to be tested based on a preset knowledge graph of the manhole cover area, obtains the center position of each initial manhole cover area in the multiple initial manhole cover areas, takes the center position as a reference point, obtains the initial representative edge position of the initial manhole cover area based on multiple preset standard manhole cover edge positions, performs an expansion operation on the initial representative edge position based on preset expansion operation parameters to obtain the target representative edge position, determines the area between the center position and the target representative edge position as the target manhole cover area, determines the non-manhole cover area adjacent to the target representative edge position as the nearby road surface area, obtains the representative manhole cover plane of the target manhole cover area and the representative road surface plane of the nearby road surface area, determines whether the road manhole cover is defective based on the elevation deviation between multiple data points in the target manhole cover area and the representative manhole cover plane, and obtains the target manhole frame difference of the road manhole cover based on the elevation deviation between the representative manhole cover plane and the representative road surface plane. This embodiment uses the preset knowledge graph matching of the manhole cover area to obtain the initial manhole cover area in the elevation three-dimensional modeling image of the road surface to be tested. The initial manhole cover area contains the knowledge graph information and three-dimensional image information of the manhole cover area, and then introduces multiple preset standard manhole cover edge positions to perform edge positioning and edge expansion on the initial manhole cover area to determine the target manhole cover area. Finally, the point and surface data inside and outside the target manhole cover area are fully utilized to detect the manhole frame difference and defects of the road manhole cover. The above detection process covers rich road information such as knowledge graph information, three-dimensional image information, preset standard manhole cover edge position information, and point and surface data information, and this information can be referenced and compared with each other to eliminate the adverse effects of environmental factors on the data, thereby ensuring the integrity and accuracy of the road manhole cover detection information, and then ensuring that the manhole frame difference and defects of the road manhole cover can be detected completely and accurately.

[0057] In one embodiment, the initial representative edge position acquisition module 503 is specifically used to: According to the sampling interval of each data point in the elevation three-dimensional modeling image, the elevation mutation data points are acquired from the central position outward, and the positions of the elevation mutation data points are determined as the potential manhole cover edge positions of the initial manhole cover area; For each preset standard manhole cover edge position of the plurality of preset standard manhole cover edge positions, calculating the cumulative distance error between the potential manhole cover edge position and the preset standard manhole cover edge position to obtain a cumulative distance error set; The preset standard manhole cover edge position corresponding to the minimum cumulative distance error in the cumulative distance error set is determined as the initial representative edge position of the initial manhole cover area.

[0058] In one embodiment, the representative plane acquisition module 507 is specifically used to: Performing plane fitting on each data point in the target manhole cover area to obtain the representative manhole cover plane; Performing plane fitting on each data point in the nearby road surface area to obtain the representative road surface plane.

[0059] In one embodiment, the manhole cover defect detection module 508 is specifically used to: For each data point in the target manhole cover area, calculating the elevation difference between the data point and the representative manhole cover plane to obtain a manhole cover deviation set; Calculating the absolute value of each manhole cover deviation in the manhole cover deviation set to obtain a manhole cover absolute deviation set; Calculate the proportion of absolute deviations of manhole covers greater than a preset manhole cover deviation threshold in the manhole cover absolute deviation set; If the number ratio is greater than a preset ratio threshold, it is determined that the road surface manhole cover corresponding to the target manhole cover area is defective; If the number ratio is less than or equal to the preset ratio threshold, it is determined that the road manhole covers corresponding to the target manhole cover area are intact.

[0060] In one embodiment, the manhole cover and frame difference detection module 509 is specifically used to: For each data point in the representative manhole cover plane, obtaining a target data point in the representative road surface plane that is adjacent to the data point; Calculate the elevation difference between each data point in the representative manhole cover plane and its corresponding target data point to obtain a manhole frame difference set; Calculating the absolute value of each well frame difference in the well frame difference set to obtain a well frame absolute deviation set; The average value of the absolute deviations of the manhole frames that are greater than a preset manhole frame deviation threshold in the manhole frame absolute deviation set is calculated to obtain a target manhole frame difference between the target manhole cover area and the road manhole cover.

[0061] In one embodiment, the elevation three-dimensional modeling image of the road surface to be tested is obtained based on the following method: Based on the measurement attitude information of the line scanning three-dimensional measurement sensor obtained by the attitude measurement sensor, measurement attitude compensation is performed on the elevation data of the road surface to be measured obtained by the line scanning three-dimensional measurement sensor to obtain the elevation three-dimensional modeling data of the road surface to be measured; Based on the elevation three-dimensional modeling data, generating the elevation three-dimensional modeling image; The sampling spacing of the line scanning three-dimensional measurement sensor in the width direction of the road surface to be measured is less than or equal to 3 mm, the sampling spacing in the driving direction of the road surface to be measured is less than or equal to 5 mm, and the sampling accuracy in the elevation direction of the road surface to be measured is better than 0.5 mm.

[0062] Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call a computer program in the memory 630 to execute the steps of the road manhole cover detection method based on precise three-dimensional images, for example including: Based on the preset knowledge graph of the manhole cover area, multiple initial manhole cover areas are obtained in the elevation 3D modeling image of the road surface to be tested; For each initial manhole cover area among the multiple initial manhole cover areas, obtaining the center position thereof; Taking the center position as a reference point, based on a plurality of preset standard manhole cover edge positions, an initial representative edge position of the initial manhole cover area is obtained; the plurality of preset standard manhole cover edge positions are obtained based on a plurality of preset standard manhole cover sizes and taking the center position as a reference point; Based on preset expansion operation parameters, the initial representative edge position is expanded to obtain a target representative edge position; Determine the area between the center position and the target representative edge position as the target manhole cover area; Determine a non-manhole cover area adjacent to the target representative edge position as a nearby road surface area; Acquire a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; Determining whether a road manhole cover is defective based on elevation deviations between a plurality of data points in the target manhole cover area and the representative manhole cover plane; Based on the elevation deviation between the representative manhole cover plane and the representative road surface plane, a target manhole frame difference of the road surface manhole cover is obtained.

[0063] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0064] On the other hand, an embodiment of the present application further provides a computer program product, the computer program product including a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the steps of the road manhole cover detection method based on precise three-dimensional images provided in the above embodiments, for example, including: Based on the preset knowledge graph of the manhole cover area, multiple initial manhole cover areas are obtained in the elevation 3D modeling image of the road surface to be tested; For each initial manhole cover area among the multiple initial manhole cover areas, obtaining the center position thereof; Taking the center position as a reference point, based on a plurality of preset standard manhole cover edge positions, an initial representative edge position of the initial manhole cover area is obtained; the plurality of preset standard manhole cover edge positions are obtained based on a plurality of preset standard manhole cover sizes and taking the center position as a reference point; Based on preset expansion operation parameters, the initial representative edge position is expanded to obtain a target representative edge position; Determine the area between the center position and the target representative edge position as the target manhole cover area; Determine a non-manhole cover area adjacent to the target representative edge position as a nearby road surface area; Acquire a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; Determining whether a road manhole cover is defective based on elevation deviations between a plurality of data points in the target manhole cover area and the representative manhole cover plane; Based on the elevation deviation between the representative manhole cover plane and the representative road surface plane, a target manhole frame difference of the road surface manhole cover is obtained.

[0065] On the other hand, an embodiment of the present application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is used to cause a processor to execute the steps of the road manhole cover detection method based on precise three-dimensional images provided in the above embodiments, for example, including: Based on the preset knowledge graph of the manhole cover area, multiple initial manhole cover areas are obtained in the elevation 3D modeling image of the road surface to be tested; For each initial manhole cover area among the multiple initial manhole cover areas, obtaining the center position thereof; Taking the center position as a reference point, based on a plurality of preset standard manhole cover edge positions, an initial representative edge position of the initial manhole cover area is obtained; the plurality of preset standard manhole cover edge positions are obtained based on a plurality of preset standard manhole cover sizes and taking the center position as a reference point; Based on preset expansion operation parameters, the initial representative edge position is expanded to obtain a target representative edge position; Determine the area between the center position and the target representative edge position as the target manhole cover area; Determine a non-manhole cover area adjacent to the target representative edge position as a nearby road surface area; Acquire a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; Determining whether a road manhole cover is defective based on elevation deviations between a plurality of data points in the target manhole cover area and the representative manhole cover plane; Based on the elevation deviation between the representative manhole cover plane and the representative road surface plane, a target manhole frame difference of the road surface manhole cover is obtained.

[0066] The non-transitory computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)), etc.

[0067] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0068] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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. 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 application.

Claims

1. A road manhole cover detection method based on precise three-dimensional images, characterized in that: include: Based on the preset knowledge graph of the manhole cover area, multiple initial manhole cover areas are obtained in the elevation 3D modeling image of the road surface to be tested; For each initial manhole cover area among the multiple initial manhole cover areas, obtaining the center position thereof; Taking the center position as a reference point, based on a plurality of preset standard manhole cover edge positions, an initial representative edge position of the initial manhole cover area is obtained; the plurality of preset standard manhole cover edge positions are obtained based on a plurality of preset standard manhole cover sizes and taking the center position as a reference point; Based on preset expansion operation parameters, the initial representative edge position is expanded to obtain a target representative edge position; Determine the area between the center position and the target representative edge position as the target manhole cover area; Determine a non-manhole cover area adjacent to the target representative edge position as a nearby road surface area; Acquire a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; Determining whether a road manhole cover is defective based on elevation deviations between a plurality of data points in the target manhole cover area and the representative manhole cover plane; Based on the elevation deviation between the representative manhole cover plane and the representative road surface plane, a target manhole frame difference of the road surface manhole cover is obtained.

2. The road manhole cover detection method based on precise three-dimensional images according to claim 1 is characterized in that: The method of obtaining the initial representative edge position of the initial manhole cover area based on a plurality of preset standard manhole cover edge positions by taking the center position as a reference point includes: According to the sampling interval of each data point in the elevation three-dimensional modeling image, the elevation mutation data points are acquired from the central position outward, and the positions of the elevation mutation data points are determined as the potential manhole cover edge positions of the initial manhole cover area; For each preset standard manhole cover edge position of the plurality of preset standard manhole cover edge positions, calculating the cumulative distance error between the potential manhole cover edge position and the preset standard manhole cover edge position to obtain a cumulative distance error set; The preset standard manhole cover edge position corresponding to the minimum cumulative distance error in the cumulative distance error set is determined as the initial representative edge position of the initial manhole cover area.

3. The road manhole cover detection method based on precise three-dimensional images according to claim 1 is characterized in that: The step of obtaining a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area includes: Performing plane fitting on each data point in the target manhole cover area to obtain the representative manhole cover plane; Performing plane fitting on each data point in the nearby road surface area to obtain the representative road surface plane.

4. The road manhole cover detection method based on precise three-dimensional images according to claim 1 is characterized in that: The determining whether a road manhole cover is defective based on the elevation deviation between a plurality of data points in the target manhole cover area and the representative manhole cover plane comprises: For each data point in the target manhole cover area, calculating the elevation difference between the data point and the representative manhole cover plane to obtain a manhole cover deviation set; Calculating the absolute value of each manhole cover deviation in the manhole cover deviation set to obtain a manhole cover absolute deviation set; Calculate the proportion of absolute deviations of manhole covers greater than a preset manhole cover deviation threshold in the manhole cover absolute deviation set; If the number ratio is greater than a preset ratio threshold, it is determined that the road surface manhole cover corresponding to the target manhole cover area is defective; If the number ratio is less than or equal to the preset ratio threshold, it is determined that the road manhole covers corresponding to the target manhole cover area are intact.

5. The road manhole cover detection method based on precise three-dimensional images according to claim 1 is characterized in that: The step of obtaining a target manhole frame difference of a road manhole cover based on the elevation deviation between the representative manhole cover plane and the representative road surface plane includes: For each data point in the representative manhole cover plane, obtaining a target data point in the representative road surface plane that is adjacent to the data point; Calculate the elevation difference between each data point in the representative manhole cover plane and its corresponding target data point to obtain a manhole frame difference set; Calculating the absolute value of each well frame difference in the well frame difference set to obtain a well frame absolute deviation set; The average value of the absolute deviations of the manhole frames that are greater than a preset manhole frame deviation threshold in the manhole frame absolute deviation set is calculated to obtain a target manhole frame difference between the target manhole cover area and the road manhole cover.

6. The road manhole cover detection method based on precise three-dimensional images according to claim 1 is characterized in that: The elevation three-dimensional modeling image of the road surface to be tested is obtained based on the following method: Based on the measurement attitude information of the line scanning three-dimensional measurement sensor obtained by the attitude measurement sensor, measurement attitude compensation is performed on the elevation data of the road surface to be measured obtained by the line scanning three-dimensional measurement sensor to obtain the elevation three-dimensional modeling data of the road surface to be measured; Based on the elevation three-dimensional modeling data, generating the elevation three-dimensional modeling image; The sampling spacing of the line scanning three-dimensional measurement sensor in the width direction of the road surface to be measured is less than or equal to 3 mm, the sampling spacing in the driving direction of the road surface to be measured is less than or equal to 5 mm, and the sampling accuracy in the elevation direction of the road surface to be measured is better than 0.5 mm.

7. A road manhole cover detection device based on precise three-dimensional images, characterized in that: include: An initial manhole cover area acquisition module is used to: acquire multiple initial manhole cover areas in the elevation three-dimensional modeling image of the road surface to be tested based on a preset knowledge graph of the manhole cover area; A center position acquisition module is used to: acquire the center position of each initial manhole cover area among the multiple initial manhole cover areas; An initial representative edge position acquisition module is used to: take the center position as a reference point and obtain the initial representative edge position of the initial manhole cover area based on a plurality of preset standard manhole cover edge positions; the plurality of preset standard manhole cover edge positions are obtained based on a plurality of preset standard manhole cover sizes and take the center position as a reference point; A target representative edge position acquisition module is used to: perform an expansion operation on the initial representative edge position based on preset expansion operation parameters to obtain a target representative edge position; A target manhole cover area acquisition module is used to: determine the area between the center position and the target representative edge position as the target manhole cover area; A nearby road surface area acquisition module is used to: determine a non-manhole cover area adjacent to the target representative edge position as a nearby road surface area; A representative plane acquisition module is used to: acquire a representative manhole cover plane of the target manhole cover area and a representative road surface plane of the nearby road surface area; A manhole cover defect detection module, used to: determine whether a road manhole cover is defective based on the elevation deviation between a plurality of data points in the target manhole cover area and the representative manhole cover plane; The manhole cover and frame difference detection module is used to obtain a target manhole frame difference of the road surface manhole cover based on the elevation deviation between the representative manhole cover plane and the representative road surface plane.

8. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the road manhole cover detection method based on precise three-dimensional images as described in any one of claims 1 to 6 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the road manhole cover detection method based on precise three-dimensional images as described in any one of claims 1 to 6 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the road manhole cover detection method based on precise three-dimensional images as described in any one of claims 1 to 6 are implemented.

Images