Precise three-dimensional-based detection method for road cover

Abstract

The application provides a kind of based on precision three-dimensional road surface well lid detection method, comprising: based on road surface elevation three-dimensional modeling data, obtain the binary image of well lid edge, obtain well lid edge seed region set from the binary image of well lid edge, obtain the first well lid edge position set corresponding to well lid edge seed region set, determine the first representative well lid edge position of each well lid in the first well lid edge position set, and perform inflation operation on the first representative well lid edge position to obtain the second representative well lid edge position, based on the first representative well lid edge position, the second representative well lid edge position and road surface elevation three-dimensional modeling data, obtain the road frame difference of well lid;Based on the first representative well lid edge position or the second representative well lid edge position, obtain the type information of well lid and the damage information of well lid, by using the height difference of well lid and road surface and the geometric characteristics of well lid, the rapid detection and positioning of road surface well lid are realized, and the accurate extraction of road frame difference is realized.

Description

Technical Field

[0001] This invention relates to the field of road surface inspection technology, and in particular to a method for inspecting road manhole covers based on precise three-dimensional analysis. Background Technology

[0002] Rapid detection and positioning of manhole covers on urban roads is one of the key issues in the management of road assets by municipal departments. The relative height difference between the manhole cover frame and the road surface (road-frame difference) directly affects the comfort and safety of vehicle driving and is a mandatory inspection item in the quality inspection of municipal road engineering.

[0003] Currently, the widely used method for detecting road manhole covers is based on visual image detection technology. However, road images are easily affected by ambient light and complex measurement scenarios during the acquisition process, making it difficult to guarantee image quality. This results in difficulties in ensuring the accuracy and completeness of road manhole cover detection. At the same time, two-dimensional images cannot provide elevation information, so it is impossible to extract road frame differences, which makes it difficult to meet the needs of municipal departments for road asset management and manhole cover detection. Summary of the Invention

[0004] This invention provides a method for detecting road manhole covers based on precise three-dimensional analysis, in order to solve the problems existing in the prior art.

[0005] This invention provides a method for detecting road manhole covers based on precise three-dimensional analysis, comprising:

[0006] Based on the three-dimensional modeling data of road surface elevation, the binary image of the manhole cover edge is obtained by utilizing the elevation change characteristics of adjacent measuring points and the preset elevation change threshold.

[0007] Several seed regions of manhole cover edge are extracted from the binary image of the manhole cover edge to obtain a set of seed regions of manhole cover edge. The first set of manhole cover edge positions corresponding to the set of seed regions of manhole cover edge is obtained. The first set of manhole cover edge positions includes potential manhole cover edge positions corresponding to the seed regions of manhole cover edge with a coverage rate greater than a preset coverage rate threshold. The coverage rate is determined based on the coverage of all measuring points in the potential manhole cover edge positions corresponding to the seed regions of manhole cover edge edge.

[0008] A first representative manhole cover edge position is determined for each manhole cover in the first set of manhole cover edge positions, and an expansion operation is performed on the first representative manhole cover edge position to obtain a second representative manhole cover edge position. The first representative manhole cover edge position for each manhole cover is determined based on the potential manhole cover edge position corresponding to the highest coverage rate for each manhole cover.

[0009] Based on the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the three-dimensional modeling data of the road surface elevation, the road frame difference of the manhole cover is obtained;

[0010] Based on the first representative edge position or the second representative edge position of the manhole cover, obtain the type information and damage information of the manhole cover, and output the road frame difference of the manhole cover, the type information of the manhole cover, the damage information of the manhole cover, and the position of the manhole cover.

[0011] According to a precise three-dimensional road manhole cover detection method provided by the present invention, the step of obtaining a first manhole cover edge position set corresponding to the manhole cover edge seed region set includes:

[0012] Based on the preset manhole cover size, a circle fit is performed on any of the manhole cover edge seed regions in the set of manhole cover edge seed regions to obtain the potential manhole cover edge position corresponding to the manhole cover edge seed region.

[0013] Based on the category to which each measuring point in the potential manhole cover edge location belongs, the coverage rate of the potential manhole cover edge location is obtained, and the category includes effective coverage points and ineffective coverage points;

[0014] From the potential manhole cover edge locations corresponding to the set of seed regions for manhole cover edges, select potential manhole cover edge locations with a coverage rate greater than a preset coverage rate threshold to form a first set of manhole cover edge locations.

[0015] According to a method for detecting road manhole covers based on precise three-dimensional positioning provided by the present invention, determining the first representative manhole cover edge position for each manhole cover in the first manhole cover edge position set includes:

[0016] Determine the center representative position of each potential manhole cover edge position in the first set of manhole cover edge positions;

[0017] Based on the distance between the center representative positions of each potential manhole cover edge position and a preset distance threshold, the potential manhole cover edge positions in the first manhole cover edge position set are classified to obtain manhole cover edge position classification results. In the manhole cover edge position classification results, the potential manhole cover edge positions corresponding to the same manhole cover are classified into the same category.

[0018] For each potential manhole cover edge position in the classification results of manhole cover edge positions, the potential manhole cover edge position with the highest coverage rate among the potential manhole cover edge positions corresponding to each manhole cover is selected as the first representative manhole cover edge position of each manhole cover.

[0019] According to the present invention, a method for detecting road manhole covers based on precise three-dimensional modeling is provided. The method involves obtaining the road frame difference of the manhole cover based on a first representative edge position of the manhole cover, a second representative edge position of the manhole cover, and three-dimensional modeling data of the road surface elevation. The method includes:

[0020] Based on the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the three-dimensional modeling data of the road surface elevation, a set of elevation differences of the manhole cover is obtained. The set of elevation differences includes the elevation difference of any measuring point in the first representative edge position of the manhole cover.

[0021] Based on the set of elevation differences of the manhole covers, the road frame difference of the manhole covers is obtained.

[0022] According to the present invention, a method for detecting road manhole covers based on precise three-dimensional positioning is provided. The elevation difference of any measuring point in the first representative edge position of the manhole cover is obtained in the following manner:

[0023] Along the road width direction and the driving direction, the representative elevation of the manhole cover is determined at any measuring point in the first representative manhole cover edge position. The representative elevation of the manhole cover is the mean of the three-dimensional modeling data of the first target elevation in the manhole cover area adjacent to the measuring point. The three-dimensional modeling data of the first target elevation is obtained from the three-dimensional modeling data of the road surface elevation of the first target measuring point within the preset statistical radius of the manhole cover area, excluding the measuring point corresponding to the second representative manhole cover edge position.

[0024] Along the road width direction and the driving direction, the road surface representative elevation of any measuring point in the first representative manhole cover edge position is determined. The road surface representative elevation is the mean of the three-dimensional modeling data of the second target elevation in the road area adjacent to the measuring point. The three-dimensional modeling data of the second target elevation is obtained from the three-dimensional modeling data of the road surface elevation of the second target measuring point within the preset statistical radius of the road area, excluding the measuring point corresponding to the edge position of the second representative manhole cover.

[0025] Along the road width direction and the driving direction, respectively, determine the difference between the representative elevation of the manhole cover and the representative elevation of the road surface at each measuring point in the first representative edge position of the manhole cover;

[0026] The difference with the largest absolute value is selected from the differences between the road width direction and the driving direction as the elevation difference of each measuring point.

[0027] According to the present invention, a method for detecting road manhole covers based on precise three-dimensional measurements is provided, wherein obtaining the road frame difference of the manhole cover based on the set of elevation differences of the manhole cover includes:

[0028] Calculate the average value of the absolute values ​​of the elevation differences in the set of elevation differences of the manhole covers to obtain the average road frame difference;

[0029] The absolute values ​​of the elevation differences in the set of elevation differences of the manhole covers are sorted, and based on the preset quantiles, the preset quantile road frame difference and the preset quantile representative road frame difference are obtained.

[0030] The road frame difference of the manhole cover is obtained based on the average road frame difference, the preset quantile road frame difference, and the preset quantile representative road frame difference. The road frame difference of the manhole cover is one or more of the average road frame difference, the preset quantile road frame difference, and the preset quantile representative road frame difference.

[0031] According to the present invention, a method for detecting road manhole covers based on precise three-dimensional positioning is provided. The method involves obtaining the type information and damage information of the manhole cover based on either a first representative edge position or a second representative edge position.

[0032] The target road surface elevation three-dimensional modeling data and target road surface grayscale data of the manhole cover are obtained. The target road surface elevation three-dimensional modeling data and target road surface grayscale data are obtained based on the first representative edge position of the manhole cover or the second representative edge position of the manhole cover.

[0033] Based on the three-dimensional modeling data of the target road surface elevation and the grayscale data of the target road surface, the text information on the manhole cover is extracted, and based on the text information and the size of the manhole cover, the type information of the manhole cover is obtained;

[0034] Based on the first representative edge position of the manhole cover or the second representative edge position of the manhole cover, the actual edge position of the manhole cover is extracted from the binary image of the manhole cover edge;

[0035] The edge position of the actual manhole cover is compared with the edge position of the standard manhole cover to obtain the damage information of the manhole cover.

[0036] According to the present invention, a method for detecting road manhole covers based on precise three-dimensional modeling is provided, wherein the three-dimensional modeling data of road elevation is obtained in the following manner:

[0037] The road surface elevation data of each measuring point on the road are obtained using a line-scan three-dimensional measurement sensor, and the measurement range of the line-scan three-dimensional measurement sensor covers the entire lane width;

[0038] The measurement attitude of the line-scan three-dimensional measurement sensor is obtained using an attitude measurement sensor;

[0039] Based on the measured posture, the road surface elevation data is subjected to posture compensation to obtain three-dimensional modeling data of road surface elevation.

[0040] According to the present invention, a method for detecting road manhole covers based on precision three-dimensional measurement, wherein the method utilizes a line-scan three-dimensional measurement sensor to acquire road surface elevation data at various measuring points on the road, further includes:

[0041] While acquiring road surface elevation data at various measuring points on the road using a line-scan three-dimensional measurement sensor, the line-scan three-dimensional measurement sensor also acquires road surface grayscale data at various measuring points on the road.

[0042] According to a method for detecting road manhole covers based on precise three-dimensional measurements provided by the present invention, the method further includes: performing attitude compensation on the road elevation data based on the measurement attitude to obtain three-dimensional modeling data of the road elevation; and then further comprising:

[0043] If the aspect ratio of the road surface elevation data exceeds the preset aspect ratio range, the road surface elevation 3D modeling data is interpolated or compressed to obtain road surface 3D modeling correction data that meets the preset aspect ratio range, and the road surface 3D modeling correction data is replaced with the road surface elevation 3D modeling data.

[0044] If the aspect ratio of the road surface grayscale data exceeds the preset aspect ratio range, the road surface grayscale data is interpolated or compressed to obtain road surface grayscale correction data that meets the preset aspect ratio range, and the road surface grayscale correction data is replaced with the road surface grayscale data.

[0045] The present invention provides a precise 3D road manhole cover detection method. Compared with the existing technology that uses 2D images, the present invention uses feature information extracted from 3D road elevation modeling data to detect road manhole covers. Specifically, firstly, based on the 3D road elevation modeling data, using the elevation change features of adjacent measuring points and a preset elevation change threshold, a binary image of the manhole cover edge is obtained. Then, several seed regions of manhole cover edges are extracted from the binary image of the manhole cover edge, resulting in a set of manhole cover edge seed regions. A first set of manhole cover edge positions corresponding to the set of manhole cover edge seed regions is obtained. The first set of manhole cover edge positions includes potential manhole cover edge positions corresponding to manhole cover edge seed regions with a coverage rate greater than a preset coverage rate threshold. The coverage rate is determined based on the coverage of all measuring points in the potential manhole cover edge positions corresponding to the manhole cover edge seed regions. A first representative manhole cover edge position is determined for each manhole cover in the first set of manhole cover edge positions, and further... Furthermore, since the first representative manhole cover edge position usually has a certain positioning error, an expansion operation is performed on the first representative manhole cover edge position to obtain the second representative manhole cover edge position. The first representative manhole cover edge position for each manhole cover is determined based on the potential manhole cover edge position corresponding to the highest coverage rate for each manhole cover. Finally, based on the first representative manhole cover edge position, the second representative manhole cover edge position, and the three-dimensional modeling data of the road surface elevation, the road frame difference of the manhole cover is obtained. Based on the first representative manhole cover edge position or the second representative manhole cover edge position, the type information and damage information of the manhole cover are obtained, and the road frame difference, type information, damage information, and position of the manhole cover are output. This invention realizes rapid detection and positioning of road manhole covers by utilizing the height difference between the manhole cover and the road surface and the geometric features of the manhole cover, and at the same time realizes accurate extraction of the road frame difference, type information, damage information, and position of the manhole cover. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0047] Figure 1 This is a flowchart illustrating the method for detecting road manhole covers based on precise three-dimensional analysis provided by the present invention.

[0048] Figure 2 This is a schematic diagram of the process for obtaining the first set of manhole cover edge positions provided by the present invention;

[0049] Figure 3 This is a schematic diagram of the process for obtaining the first representative manhole cover edge position provided by the present invention;

[0050] Figure 4 This is a schematic diagram of the process for obtaining the road frame difference of a manhole cover provided by the present invention;

[0051] Figure 5 This is a schematic diagram of the process for obtaining information on the type and damage of manhole covers provided by the present invention.

[0052] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0054] It should be noted that in the description of this invention, the terms "first," "second," etc., are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, the first object can be one or more.

[0055] The following description, in conjunction with the accompanying drawings, provides an exemplary introduction to the road manhole cover detection method based on precise three-dimensional measurement provided by the present invention.

[0056] Figure 1 This is a flowchart illustrating the precise three-dimensional road manhole cover detection method provided by the present invention, as shown below. Figure 1 As shown, the method includes:

[0057] Step 110: Based on the three-dimensional modeling data of road surface elevation, the binary map of the manhole cover edge is obtained by utilizing the elevation change characteristics of adjacent measuring points and the preset elevation change threshold.

[0058] Step 120: Extract several seed regions of manhole cover edges from the binary image of the manhole cover edge to obtain a set of seed regions of manhole cover edges, and obtain a first set of manhole cover edge positions corresponding to the set of seed regions of manhole cover edges. The first set of manhole cover edge positions includes potential manhole cover edge positions corresponding to the seed regions of manhole cover edges with a coverage rate greater than a preset coverage rate threshold. The coverage rate is determined based on the coverage of all measuring points in the potential manhole cover edge positions corresponding to the seed regions of manhole cover edges.

[0059] Step 130: Determine the first representative manhole cover edge position for each manhole cover in the first manhole cover edge position set, and perform an expansion operation on the first representative manhole cover edge position to obtain the second representative manhole cover edge position. The first representative manhole cover edge position for each manhole cover is determined based on the potential manhole cover edge position corresponding to the highest coverage rate for each manhole cover.

[0060] Step 140: Based on the first representative manhole cover edge position, the second representative manhole cover edge position, and the three-dimensional modeling data of the road surface elevation, obtain the road frame difference of the manhole cover;

[0061] Step 150: Based on the first representative edge position of the manhole cover or the second representative edge position of the manhole cover, obtain the type information and damage information of the manhole cover, and output the road frame difference of the manhole cover, the type information of the manhole cover, the damage information of the manhole cover, and the position of the manhole cover.

[0062] It should be noted that the execution subject of the precise three-dimensional road manhole cover detection method provided in this embodiment of the invention can be an electronic device, a component in an electronic device, an integrated circuit, or a chip. The electronic device can be a mobile electronic device or a non-mobile electronic device. For example, a mobile electronic device can be a mobile phone, tablet computer, laptop computer, PDA, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., while a non-mobile electronic device can be a server, network attached storage (NAS), personal computer (PC), etc. This embodiment of the invention does not specifically limit the specific implementation of these devices.

[0063] The following example, using a computer to execute the precise three-dimensional road manhole cover detection method provided by this invention, illustrates the technical solution of the present invention in detail.

[0064] Specifically, in this embodiment of the invention, three-dimensional modeling data of road surface elevation can be obtained first. In one example, the three-dimensional modeling data of road surface elevation is obtained based on a line-scan three-dimensional measurement sensor. Specifically, the line-scan three-dimensional measurement sensor includes a laser, a high-speed three-dimensional camera, and an attitude measurement sensor. The line-scan three-dimensional measurement sensor is installed on a vehicle platform. During the measurement process, the line-scan three-dimensional measurement sensor continuously collects the elevation information of the road surface along the road direction. The road surface elevation data and road surface grayscale data can be obtained through the data returned by the line-scan three-dimensional measurement sensor.

[0065] Based on road elevation data and the measurement attitude obtained by attitude measurement sensors, the road elevation data is compensated using the measurement attitude to obtain three-dimensional modeling data of road elevation.

[0066] After obtaining the three-dimensional modeling data of the road surface elevation, the elevation change characteristics of adjacent measuring points and the preset elevation change threshold are used. Specifically, measuring points with elevation changes greater than the preset elevation change threshold are marked as target points, and a binary map of the manhole cover edge composed of several target points can be obtained. Among them, adjacent measuring points include left and right adjacent measuring points and top and bottom adjacent measuring points, or eight-neighborhood measuring points. The preset elevation change segmentation threshold is greater than the conventional road surface texture depth, such as 5mm.

[0067] It should be noted that, for the transition area between the manhole cover and the road surface, since there is a gap in the middle of the transition area, the points on the edge of the manhole cover can form a continuous line, which is the seed region of the manhole cover edge. Therefore, in this embodiment of the invention, several seed regions of the manhole cover edge are extracted from the binary image of the manhole cover edge to obtain a set of seed regions of the manhole cover edge. Specifically, in this embodiment, the seed regions of the manhole cover edge are selected based on the length information of the connected region in the binary image of the manhole cover edge and the preset connected region length threshold to obtain a set of seed regions of the manhole cover edge.

[0068] Furthermore, there may be some interfering edge lines in the seed region of the manhole cover edge, which may affect the accuracy of the subsequent road frame difference calculation. Therefore, in this embodiment of the invention, the potential manhole cover edge positions corresponding to the seed regions of each manhole cover edge in the set of seed regions of manhole cover edge are extracted and combined into a first set of manhole cover edge positions.

[0069] It should be noted that the edge lines detected by a manhole cover may be broken. Therefore, a manhole cover may correspond to multiple manhole cover edge seed regions, that is, a manhole cover may correspond to multiple potential manhole cover edge positions. Therefore, in this embodiment, the potential manhole cover edge positions in the first manhole cover edge position set are first classified, and the potential manhole cover edge positions corresponding to the same manhole cover are divided into one category. Then, the potential manhole cover edge position with the highest coverage among the potential manhole cover edge positions corresponding to each manhole cover is taken as the first representative manhole cover edge position of that manhole cover.

[0070] Furthermore, since the first representative manhole cover edge position usually has a certain positioning error, this embodiment of the invention performs an expansion operation on the first representative manhole cover edge position. Specifically, the expansion operation can be performed according to preset expansion operation parameters to obtain the second representative manhole cover edge position.

[0071] Finally, on the one hand, the road frame difference of the manhole cover (i.e., the distance between the protrusions or depressions of the manhole cover) is obtained by using the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the three-dimensional modeling data of the road surface elevation. On the other hand, the type information and damage information of the manhole cover are obtained based on the first representative edge position or the second representative edge position of the manhole cover.

[0072] Compared to existing technologies that use two-dimensional images, this invention uses feature information extracted from three-dimensional road elevation modeling data for manhole cover detection. Specifically, firstly, based on the three-dimensional road elevation modeling data, a binary image of the manhole cover edge is obtained using the elevation change features of adjacent measuring points and a preset elevation change threshold. Then, several seed regions of manhole cover edges are extracted from the binary image of the manhole cover edge, resulting in a set of seed regions. A first set of manhole cover edge positions corresponding to this set is then obtained. This first set includes potential manhole cover edge positions corresponding to seed regions with coverage rates greater than a preset coverage rate threshold. The coverage rate is determined based on the coverage of all measuring points within the potential manhole cover edge positions corresponding to the seed regions. A first representative manhole cover edge position is determined for each manhole cover in the first set. Further, since the first representative manhole cover... Since there is usually a certain positioning error at the edge position, an expansion operation is performed on the first representative manhole cover edge position to obtain the second representative manhole cover edge position. The first representative manhole cover edge position for each manhole cover is determined based on the potential manhole cover edge position corresponding to the highest coverage of each manhole cover. Finally, based on the first representative manhole cover edge position, the second representative manhole cover edge position, and the three-dimensional modeling data of the road surface elevation, the road frame difference of the manhole cover is obtained. Based on the first representative manhole cover edge position or the second representative manhole cover edge position, the type information and damage information of the manhole cover are obtained, and the road frame difference, type information, damage information, and position of the manhole cover are output. This invention realizes rapid detection and positioning of road manhole covers by utilizing the height difference between the manhole cover and the road surface and the geometric features of the manhole cover, and at the same time realizes accurate extraction of the road frame difference, type information, damage information, and position of the manhole cover.

[0073] In some embodiments, the three-dimensional modeling data of the road surface elevation is obtained through the following methods:

[0074] The road surface elevation data of each measuring point on the road is obtained by using a line-scanning three-dimensional measurement sensor, and the measurement range of the line-scanning three-dimensional measurement sensor covers the entire lane width;

[0075] The measurement attitude of the line-scan three-dimensional measurement sensor is obtained using an attitude measurement sensor;

[0076] Based on the measured posture, the road surface elevation data is subjected to posture compensation to obtain three-dimensional modeling data of road surface elevation.

[0077] In this embodiment, the measurement range of the line-scan 3D measurement sensor is required to cover the entire lane in the road width direction, and the data sampling interval of the line-scan 3D measurement sensor in the road width direction is less than or equal to 5mm, the data sampling interval in the road driving direction is less than or equal to 5mm, and the measurement accuracy in the elevation direction is better than 0.5mm.

[0078] In this embodiment, one or more sets of line-scanning three-dimensional measurement sensors can be installed on the vehicle according to the detection accuracy requirements, so that the total coverage width can achieve full lane coverage.

[0079] Furthermore, in this embodiment, in order to eliminate the large error between the road surface elevation data obtained by the line-scan three-dimensional measurement sensor and the actual road surface elevation data caused by the dynamic measurement posture of the measurement vehicle during the detection process, an attitude measurement sensor is also used to obtain the measurement posture of the line-scan three-dimensional measurement sensor in real time, and the measurement posture is used to perform attitude compensation on the road surface elevation data.

[0080] This invention utilizes a line-scan 3D measurement sensor to acquire road surface elevation data at various measuring points on the road, with the measurement range of the line-scan 3D measurement sensor covering the entire lane width; it also utilizes an attitude measurement sensor to acquire the measurement attitude of the line-scan 3D measurement sensor; and it performs attitude compensation on the road surface elevation data based on the measurement attitude to obtain 3D modeling data of road surface elevation, thus obtaining more comprehensive and accurate 3D modeling data of road surface elevation.

[0081] In some embodiments, acquiring road surface elevation data at various measuring points on the road using a line-scan three-dimensional measurement sensor further includes:

[0082] While acquiring road surface elevation data at various measuring points on the road using a line-scan three-dimensional measurement sensor, the line-scan three-dimensional measurement sensor also acquires road surface grayscale data at various measuring points on the road.

[0083] Specifically, since the elevation and grayscale of manhole covers differ significantly from those of conventional road surfaces, this embodiment acquires road surface elevation data and road surface grayscale data in addition to using a line-scan three-dimensional measurement sensor. This differential analysis can be used to detect manhole covers on the road surface.

[0084] In some embodiments, the step of performing attitude compensation on the road surface elevation data based on the measured attitude to obtain three-dimensional modeling data of the road surface elevation further includes:

[0085] If the aspect ratio of the road surface elevation data exceeds the preset aspect ratio range, the road surface elevation 3D modeling data is interpolated or compressed to obtain road surface 3D modeling correction data that meets the preset aspect ratio range, and the road surface 3D modeling correction data is replaced with the road surface elevation 3D modeling data.

[0086] If the aspect ratio of the road surface elevation data and the road surface grayscale data exceeds the preset aspect ratio range, the road surface grayscale data is interpolated or compressed to obtain road surface grayscale correction data that meets the preset aspect ratio range, and the road surface grayscale correction data is replaced with the road surface grayscale data.

[0087] Specifically, since the line scan three-dimensional measurement sensor has different sampling intervals in the horizontal and vertical directions when collecting data, and the subsequent extraction of manhole cover features is based on the circular features of the manhole cover, this embodiment of the invention needs to ensure that the horizontal and vertical ratios of the road surface elevation data and the road surface grayscale data exceed the preset horizontal and vertical ratio range.

[0088] This invention addresses situations where the aspect ratio of road elevation data exceeds a preset range. It interpolates or compresses the 3D road elevation modeling data to obtain corrected 3D road modeling data that meets the preset aspect ratio range. This corrected data is then replaced with the corrected road elevation modeling data. Furthermore, the invention interpolates or compresses the road grayscale data to obtain corrected road grayscale data that also meets the preset aspect ratio range. This corrected data is then replaced with the corrected road grayscale data. This ensures that the subsequent 3D road elevation modeling data and road grayscale data used are more accurate, thereby enabling the accurate extraction of road frame differences.

[0089] like Figure 2 As shown, in some embodiments, step 120, obtaining the first set of manhole cover edge positions corresponding to the set of seed regions of the manhole cover edge, specifically includes:

[0090] Step 210: Based on the preset manhole cover size, perform circle fitting on any of the manhole cover edge seed regions in the set of manhole cover edge seed regions to obtain the potential manhole cover edge position corresponding to the manhole cover edge seed region;

[0091] Step 220: Based on the category to which each measuring point in the potential manhole cover edge location belongs, obtain the coverage rate of the potential manhole cover edge location, where the category includes effective coverage points and ineffective coverage points;

[0092] Step 230: Select potential manhole cover edge locations with a coverage rate greater than a preset coverage rate threshold from the potential manhole cover edge seed region set to form a first manhole cover edge location set.

[0093] In this embodiment, the potential edge positions of the manhole cover are obtained in the seed region of the manhole cover edge by first using a circle fitting method based on a preset manhole cover size. The preset manhole cover size can be a preset manhole cover diameter or a preset manhole cover radius, and is not limited thereto.

[0094] Specifically, after obtaining the potential manhole cover edge location, for any measuring point in the potential manhole cover edge location, based on the preset search radius parameter, it is determined whether there is a connected region with a length greater than the preset length in the binary graph of the manhole cover edge near any measuring point. If there is, the measuring point is marked as a valid coverage point; otherwise, the measuring point is marked as an invalid coverage point.

[0095] Furthermore, after obtaining the coverage status of all measuring points at each potential manhole cover edge location, the ratio of the number of effective covered points to the total number of measuring points at each potential manhole cover edge location is determined to obtain the coverage rate of the potential manhole cover edge location.

[0096] Understandably, the more effective coverage points there are at the edge of a manhole cover, the greater the likelihood that the edge of the manhole cover belongs to the manhole cover location. Therefore, in this embodiment, potential manhole cover edge locations with a coverage rate greater than a preset coverage rate threshold are selected from all potential manhole cover edge locations corresponding to the first manhole cover edge seed region set to form the first manhole cover edge location set.

[0097] This invention first obtains the potential manhole cover edge locations corresponding to the seed region of the manhole cover edge. Then, based on the category of each measuring point in the potential manhole cover edge locations, the coverage rate of the potential manhole cover edge locations is obtained. Finally, potential manhole cover edge locations with a coverage rate greater than a preset coverage rate threshold are selected to form a first set of manhole cover edge locations. In this way, the potential manhole cover edge locations corresponding to the seed region of the manhole cover edge are filtered based on the coverage of all measuring points in the potential manhole cover edge locations, ensuring the accuracy of subsequent road frame difference calculation.

[0098] like Figure 3 As shown, in some embodiments, step 130, determining the first representative manhole cover edge position for each manhole cover in the first manhole cover edge position set, specifically includes:

[0099] Step 310: Determine the center representative position of each potential manhole cover edge position in the first set of manhole cover edge positions;

[0100] Step 320: Based on the distance between the center representative positions of each potential manhole cover edge position and a preset distance threshold, classify the potential manhole cover edge positions in the first manhole cover edge position set to obtain manhole cover edge position classification results. In the manhole cover edge position classification results, the potential manhole cover edge positions corresponding to the same manhole cover are classified into the same category.

[0101] Step 330: For each potential manhole cover edge position in the classification results of manhole cover edge positions, select the potential manhole cover edge position with the highest coverage rate among the potential manhole cover edge positions corresponding to each manhole cover as the first representative manhole cover edge position of each manhole cover.

[0102] Specifically, in this embodiment, the center representative position of each potential manhole cover edge position in the first manhole cover edge position set is first calculated. It should be noted that since the potential manhole cover edge positions in the first manhole cover edge position set may be potential manhole cover edge positions of multiple manhole covers, this embodiment calculates the distance between them and combines it with a preset distance threshold to classify potential manhole cover edge positions with a distance less than the preset distance threshold into one category. That is, potential manhole cover edge positions corresponding to the same manhole cover are classified into the same category, thus obtaining the manhole cover edge position classification result.

[0103] Furthermore, after classifying the potential manhole cover edge locations corresponding to the same manhole cover into the same category, for any category in the first manhole cover edge location classification results, the potential manhole cover edge location corresponding to the highest coverage rate of the potential manhole cover edge location is selected as the first representative manhole cover edge location of that category.

[0104] like Figure 4 As shown, in some embodiments, step 140, which involves obtaining the road frame difference of the manhole cover based on the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the three-dimensional modeling data of the road surface elevation, includes:

[0105] Step 410: Based on the first representative manhole cover edge position, the second representative manhole cover edge position, and the three-dimensional modeling data of the road surface elevation, obtain the elevation difference set of the manhole cover. The elevation difference set includes the elevation difference of any measuring point in the first representative manhole cover edge position.

[0106] Step 420: Based on the set of elevation differences of the manhole covers, obtain the road frame difference of the manhole covers.

[0107] It should be noted that since covers are usually convex or concave, which can affect driving safety, and the first and second representative manhole cover edge positions are both gaps at the edges of the manhole cover, they cannot be included in the elevation difference statistics. Therefore, in this embodiment, the elevation difference is calculated by combining the non-manhole cover edge positions in the three-dimensional modeling data of road elevation.

[0108] Specifically, the elevation difference of any measuring point at the first representative edge location of the manhole cover is obtained in the following way:

[0109] Along the road width direction and the driving direction, the representative elevation of the manhole cover is determined at any measuring point in the first representative manhole cover edge position. The representative elevation of the manhole cover is the mean of the three-dimensional modeling data of the first target elevation in the manhole cover area adjacent to the measuring point. The three-dimensional modeling data of the first target elevation is obtained from the three-dimensional modeling data of the road surface elevation of the first target measuring point within the preset statistical radius of the manhole cover area, excluding the measuring point corresponding to the second representative manhole cover edge position.

[0110] Along the road width direction and the driving direction, the road surface representative elevation of any measuring point in the first representative manhole cover edge position is determined. The road surface representative elevation is the mean of the three-dimensional modeling data of the second target elevation in the road area adjacent to the measuring point. The three-dimensional modeling data of the second target elevation is obtained from the three-dimensional modeling data of the road surface elevation of the second target measuring point within the preset statistical radius of the road area, excluding the measuring point corresponding to the edge position of the second representative manhole cover.

[0111] Along the road width direction and the driving direction, respectively, determine the difference between the representative elevation of the manhole cover and the representative elevation of the road surface at each measuring point in the first representative edge position of the manhole cover;

[0112] The difference with the largest absolute value is selected from the differences between the road width direction and the driving direction as the elevation difference of each measuring point.

[0113] In this embodiment, for any measuring point in the first representative manhole cover edge position, based on the preset statistical radius, the difference between the manhole cover representative elevation and the road surface representative elevation of any measuring point is calculated along the road width direction and the driving direction respectively; and the difference with the larger absolute value is selected from the differences corresponding to the road width direction and the driving direction as the elevation difference between the manhole cover edge and the road surface adjacent to the manhole cover edge near the measuring point.

[0114] After obtaining the elevation difference, the road frame difference of the manhole cover is obtained based on the set of elevation differences of the manhole cover. It should be noted that, in this embodiment, the road frame difference refers to the distance of the manhole cover's protrusion or depression.

[0115] Specifically, in this embodiment, the average value of the absolute values ​​of the elevation differences in the set of elevation differences of manhole covers is first calculated to obtain the average road frame difference; then, the absolute values ​​of the elevation differences in the set of elevation differences of manhole covers are sorted, and based on a preset quantile, a preset quantile road frame difference and a preset quantile representative road frame difference are obtained; finally, based on the average road frame difference, the preset quantile road frame difference, and the preset quantile representative road frame difference, the road frame difference of the manhole cover is obtained, wherein the road frame difference of the manhole cover is one or more of the average road frame difference, the preset quantile road frame difference, and the preset quantile representative road frame difference.

[0116] Furthermore, in this implementation, based on the set of elevation differences, the direction of the manhole cover is obtained according to the average of the elevation differences whose absolute values ​​are greater than the road frame differences. Specifically, if the average elevation difference is greater than zero, it is a convex manhole cover; if the average elevation difference is less than zero, it is a concave manhole cover.

[0117] This invention obtains a set of elevation differences for manhole covers by using three-dimensional modeling data of the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the road surface elevation. Based on the set of elevation differences, the road frame difference of the manhole cover is obtained. In this way, the elevation difference between the manhole cover and the road surface and the shape characteristics of the manhole cover are used to achieve rapid detection and positioning of manhole covers on the road surface, and to accurately extract the road frame difference of the manhole cover.

[0118] like Figure 5 As shown, in some embodiments, step 150, which involves obtaining the type information and damage information of the manhole cover based on a first representative edge position or a second representative edge position, includes:

[0119] Step 510: Obtain the target road surface elevation three-dimensional modeling data and target road surface grayscale data of the manhole cover. The target road surface elevation three-dimensional modeling data and target road surface grayscale data are obtained based on the first representative manhole cover edge position or the second representative manhole cover edge position. Specifically, they are the road surface elevation three-dimensional modeling data and target road surface grayscale data inside the manhole cover edge position.

[0120] Step 520: Based on the three-dimensional modeling data of the target road surface elevation and the grayscale data of the target road surface, extract the text information on the manhole cover, and based on the text information and the size of the manhole cover, obtain the type information of the manhole cover;

[0121] Step 530: Based on the first representative edge position of the manhole cover or the second representative edge position of the manhole cover, extract the actual edge position of the manhole cover from the binary image of the manhole cover edge;

[0122] Step 540: Compare the actual manhole cover edge position with the standard manhole cover edge position to obtain the damage information of the manhole cover.

[0123] Specifically, based on the first or second representative edge position of the manhole cover, the 3D modeling data of the target road surface elevation and the grayscale data of the target road surface corresponding to the manhole cover area are extracted. Then, based on the 3D modeling data of the target road surface elevation and the grayscale data of the target road surface, the text information on the manhole cover is extracted, and the manhole cover type is determined by combining the size of the manhole cover to obtain the type information of the manhole cover.

[0124] In addition, this embodiment also extracts the actual manhole cover edge position based on the first or second representative manhole cover edge position, combined with the length of the connected region in the binary graph of the manhole cover edge and the relative positional relationship between the connected region and the manhole cover edge.

[0125] The system also compares the actual edge position of the manhole cover with the edge position of the standard manhole cover to determine whether the manhole cover is damaged. For example, if there is a large deviation in the edge position of a long area, the manhole cover is considered to be damaged.

[0126] This invention achieves accurate extraction of manhole cover type and damage information by acquiring target road surface elevation 3D modeling data and target road surface grayscale data; extracting text information from the manhole cover based on the target road surface elevation 3D modeling data and target road surface grayscale data, and obtaining manhole cover type information based on the text information and manhole cover size; extracting the actual manhole cover edge position from the binary image of the manhole cover edge based on the first representative edge position or the second representative edge position of the manhole cover; and comparing the actual manhole cover edge position with the standard manhole cover edge position to obtain manhole cover damage information.

[0127] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include: a processor 601, a communication interface 602, a memory 603, and a communication bus 604. The processor 601, communication interface 602, and memory 603 communicate with each other via the communication bus 604. The processor 601 can call logical instructions from the memory 603 to execute a precise three-dimensional road manhole cover detection method. This method includes:

[0128] Based on the three-dimensional modeling data of road surface elevation, the binary image of the manhole cover edge is obtained by utilizing the elevation change characteristics of adjacent measuring points and the preset elevation change threshold.

[0129] Several seed regions of manhole cover edge are extracted from the binary image of the manhole cover edge to obtain a set of seed regions of manhole cover edge. The first set of manhole cover edge positions corresponding to the set of seed regions of manhole cover edge is obtained. The first set of manhole cover edge positions includes potential manhole cover edge positions corresponding to the seed regions of manhole cover edge with a coverage rate greater than a preset coverage rate threshold. The coverage rate is determined based on the coverage of all measuring points in the potential manhole cover edge positions corresponding to the seed regions of manhole cover edge edge.

[0130] A first representative manhole cover edge position is determined for each manhole cover in the first set of manhole cover edge positions, and an expansion operation is performed on the first representative manhole cover edge position to obtain a second representative manhole cover edge position. The first representative manhole cover edge position for each manhole cover is determined based on the potential manhole cover edge position corresponding to the highest coverage rate for each manhole cover.

[0131] Based on the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the three-dimensional modeling data of the road surface elevation, the road frame difference of the manhole cover is obtained;

[0132] Based on the first representative edge position or the second representative edge position of the manhole cover, obtain the type information and damage information of the manhole cover, and output the road frame difference of the manhole cover, the type information of the manhole cover, the damage information of the manhole cover, and the position of the manhole cover.

[0133] Furthermore, the logical instructions in the aforementioned memory 603 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0134] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the road manhole cover detection method based on precise three-dimensional measurement provided by the above methods, the method comprising:

[0135] Based on the three-dimensional modeling data of road surface elevation, the binary image of the manhole cover edge is obtained by utilizing the elevation change characteristics of adjacent measuring points and the preset elevation change threshold.

[0136] Several seed regions of manhole cover edge are extracted from the binary image of the manhole cover edge to obtain a set of seed regions of manhole cover edge. The first set of manhole cover edge positions corresponding to the set of seed regions of manhole cover edge is obtained. The first set of manhole cover edge positions includes potential manhole cover edge positions corresponding to the seed regions of manhole cover edge with a coverage rate greater than a preset coverage rate threshold. The coverage rate is determined based on the coverage of all measuring points in the potential manhole cover edge positions corresponding to the seed regions of manhole cover edge edge.

[0137] A first representative manhole cover edge position is determined for each manhole cover in the first set of manhole cover edge positions, and an expansion operation is performed on the first representative manhole cover edge position to obtain a second representative manhole cover edge position. The first representative manhole cover edge position for each manhole cover is determined based on the potential manhole cover edge position corresponding to the highest coverage rate for each manhole cover.

[0138] Based on the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the three-dimensional modeling data of the road surface elevation, the road frame difference of the manhole cover is obtained;

[0139] Based on the first representative edge position or the second representative edge position of the manhole cover, obtain the type information and damage information of the manhole cover, and output the road frame difference of the manhole cover, the type information of the manhole cover, the damage information of the manhole cover, and the position of the manhole cover.

[0140] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the road manhole cover detection method based on precise three-dimensional measurement provided by the methods described above, the method comprising:

[0141] Based on the three-dimensional modeling data of road surface elevation, the binary image of the manhole cover edge is obtained by utilizing the elevation change characteristics of adjacent measuring points and the preset elevation change threshold.

[0142] Several seed regions of manhole cover edge are extracted from the binary image of the manhole cover edge to obtain a set of seed regions of manhole cover edge. The first set of manhole cover edge positions corresponding to the set of seed regions of manhole cover edge is obtained. The first set of manhole cover edge positions includes potential manhole cover edge positions corresponding to the seed regions of manhole cover edge with a coverage rate greater than a preset coverage rate threshold. The coverage rate is determined based on the coverage of all measuring points in the potential manhole cover edge positions corresponding to the seed regions of manhole cover edge edge.

[0143] A first representative manhole cover edge position is determined for each manhole cover in the first set of manhole cover edge positions, and an expansion operation is performed on the first representative manhole cover edge position to obtain a second representative manhole cover edge position. The first representative manhole cover edge position for each manhole cover is determined based on the potential manhole cover edge position corresponding to the highest coverage rate for each manhole cover.

[0144] Based on the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the three-dimensional modeling data of the road surface elevation, the road frame difference of the manhole cover is obtained;

[0145] Based on the first representative edge position or the second representative edge position of the manhole cover, obtain the type information and damage information of the manhole cover, and output the road frame difference of the manhole cover, the type information of the manhole cover, the damage information of the manhole cover, and the position of the manhole cover.

[0146] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0147] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting road manhole covers based on precise three-dimensional analysis, characterized in that, include: Based on the three-dimensional modeling data of road surface elevation, the binary image of the manhole cover edge is obtained by utilizing the elevation change characteristics of adjacent measuring points and the preset elevation change threshold. Several seed regions of manhole cover edge are extracted from the binary image of the manhole cover edge to obtain a set of seed regions of manhole cover edge. The first set of manhole cover edge positions corresponding to the set of seed regions of manhole cover edge is obtained. The first set of manhole cover edge positions includes potential manhole cover edge positions corresponding to the seed regions of manhole cover edge with a coverage rate greater than a preset coverage rate threshold. The coverage rate is determined based on the coverage of all measuring points in the potential manhole cover edge positions corresponding to the seed regions of manhole cover edge edge. A first representative manhole cover edge position is determined for each manhole cover in the first set of manhole cover edge positions, and an expansion operation is performed on the first representative manhole cover edge position to obtain a second representative manhole cover edge position. The first representative manhole cover edge position for each manhole cover is determined based on the potential manhole cover edge position corresponding to the highest coverage rate for each manhole cover. Based on the first representative edge position of the manhole cover, the second representative edge position of the manhole cover, and the three-dimensional modeling data of the road surface elevation, a set of elevation differences of the manhole cover is obtained. The set of elevation differences includes the elevation difference of any measuring point in the first representative edge position of the manhole cover. Based on the set of elevation differences of the manhole covers, the road frame difference of the manhole covers is obtained; Based on the first representative edge position or the second representative edge position of the manhole cover, obtain the type information and damage information of the manhole cover, and output the road frame difference of the manhole cover, the type information of the manhole cover, the damage information of the manhole cover, and the position of the manhole cover.

2. The method for detecting road manhole covers based on precise three-dimensional analysis according to claim 1, characterized in that, The step of obtaining the first set of manhole cover edge positions corresponding to the set of seed regions of the manhole cover edge includes: Based on the preset manhole cover size, a circle fit is performed on any of the manhole cover edge seed regions in the set of manhole cover edge seed regions to obtain the potential manhole cover edge position corresponding to the manhole cover edge seed region. Based on the category to which each measuring point in the potential manhole cover edge location belongs, the coverage rate of the potential manhole cover edge location is obtained, and the category includes effective coverage points and ineffective coverage points; From the potential manhole cover edge locations corresponding to the set of seed regions for manhole cover edges, select potential manhole cover edge locations with a coverage rate greater than a preset coverage rate threshold to form a first set of manhole cover edge locations.

3. The method for detecting road manhole covers based on precise three-dimensional analysis according to claim 1, characterized in that, Determining the first representative manhole cover edge position for each manhole cover in the first manhole cover edge position set includes: Determine the center representative position of each potential manhole cover edge position in the first set of manhole cover edge positions; Based on the distance between the center representative positions of each potential manhole cover edge position and a preset distance threshold, the potential manhole cover edge positions in the first manhole cover edge position set are classified to obtain manhole cover edge position classification results. In the manhole cover edge position classification results, the potential manhole cover edge positions corresponding to the same manhole cover are classified into the same category. For each potential manhole cover edge position in the classification results of manhole cover edge positions, the potential manhole cover edge position with the highest coverage rate among the potential manhole cover edge positions corresponding to each manhole cover is selected as the first representative manhole cover edge position of each manhole cover.

4. The method for detecting road manhole covers based on precise three-dimensional analysis according to claim 1, characterized in that, The elevation difference of any measuring point at the first representative edge position of the manhole cover is obtained in the following way: Along the road width direction and the driving direction, the representative elevation of the manhole cover is determined at any measuring point in the first representative manhole cover edge position. The representative elevation of the manhole cover is the mean of the three-dimensional modeling data of the first target elevation in the manhole cover area adjacent to the measuring point. The three-dimensional modeling data of the first target elevation is obtained from the three-dimensional modeling data of the road surface elevation of the first target measuring point within the preset statistical radius of the manhole cover area, excluding the measuring point corresponding to the second representative manhole cover edge position. Along the road width direction and the driving direction, the road surface representative elevation of any measuring point in the first representative manhole cover edge position is determined. The road surface representative elevation is the mean of the three-dimensional modeling data of the second target elevation in the road area adjacent to the measuring point. The three-dimensional modeling data of the second target elevation is obtained from the three-dimensional modeling data of the road surface elevation of the second target measuring point within the preset statistical radius of the road area, excluding the measuring point corresponding to the edge position of the second representative manhole cover. Along the road width direction and the driving direction, respectively, determine the difference between the representative elevation of the manhole cover and the representative elevation of the road surface at each measuring point in the first representative edge position of the manhole cover; The difference with the largest absolute value is selected from the differences between the road width direction and the driving direction as the elevation difference of each measuring point.

5. The method for detecting road manhole covers based on precise three-dimensional analysis according to claim 1, characterized in that, The method for obtaining the road frame difference of the manhole cover based on the set of elevation differences of the manhole cover includes: Calculate the average value of the absolute values ​​of the elevation differences in the set of elevation differences of the manhole covers to obtain the average road frame difference; The absolute values ​​of the elevation differences in the set of elevation differences of the manhole covers are sorted, and based on the preset quantiles, the preset quantile road frame difference and the preset quantile representative road frame difference are obtained. The road frame difference of the manhole cover is obtained based on the average road frame difference, the preset quantile road frame difference, and the preset quantile representative road frame difference. The road frame difference of the manhole cover is one or more of the average road frame difference, the preset quantile road frame difference, and the preset quantile representative road frame difference.

6. The method for detecting road manhole covers based on precise three-dimensional analysis according to claim 1, characterized in that, The process of obtaining the type information and damage information of the manhole cover based on either the first or second representative edge position of the manhole cover includes: The target road surface elevation three-dimensional modeling data and target road surface grayscale data of the manhole cover are obtained. The target road surface elevation three-dimensional modeling data and target road surface grayscale data are obtained based on the first representative edge position of the manhole cover or the second representative edge position of the manhole cover. Based on the three-dimensional modeling data of the target road surface elevation and the grayscale data of the target road surface, the text information on the manhole cover is extracted, and based on the text information and the size of the manhole cover, the type information of the manhole cover is obtained; Based on the first representative edge position of the manhole cover or the second representative edge position of the manhole cover, the actual edge position of the manhole cover is extracted from the binary image of the manhole cover edge; The edge position of the actual manhole cover is compared with the edge position of the standard manhole cover to obtain the damage information of the manhole cover.

7. The method for detecting road manhole covers based on precise three-dimensional analysis according to claim 1, characterized in that, The three-dimensional modeling data of the road surface elevation was obtained through the following methods: The road surface elevation data of each measuring point on the road is obtained by using a line-scanning three-dimensional measurement sensor, and the measurement range of the line-scanning three-dimensional measurement sensor covers the entire lane width; The measurement attitude of the line-scan three-dimensional measurement sensor is obtained using an attitude measurement sensor; Based on the measured posture, the road surface elevation data is subjected to posture compensation to obtain three-dimensional modeling data of road surface elevation.

8. The method for detecting road manhole covers based on precise three-dimensional analysis according to claim 7, characterized in that, The method of acquiring road surface elevation data at various measuring points on the road using a line-scan three-dimensional measurement sensor also includes: While acquiring road surface elevation data at various measuring points on the road using a line-scan three-dimensional measurement sensor, the line-scan three-dimensional measurement sensor also acquires road surface grayscale data at various measuring points on the road.

9. The method for detecting road manhole covers based on precise three-dimensional analysis according to claim 7 or 8, characterized in that, The process of performing attitude compensation on the road surface elevation data based on the measured attitude to obtain three-dimensional modeling data of the road surface elevation further includes: If the aspect ratio of the road surface elevation data exceeds the preset aspect ratio range, the road surface elevation 3D modeling data is interpolated or compressed to obtain road surface 3D modeling correction data that meets the preset aspect ratio range, and the road surface 3D modeling correction data is replaced with the road surface elevation 3D modeling data. If the aspect ratio of the road surface grayscale data exceeds the preset aspect ratio range, the road surface grayscale data is interpolated or compressed to obtain road surface grayscale correction data that meets the preset aspect ratio range, and the road surface grayscale correction data is replaced with the road surface grayscale data.

Images