A method, system and medium for constructing a visual model of a culvert based on SLAM

Abstract

The present application provides a method, system and medium for constructing a visualization model of a culvert based on SLAM. The method includes: obtaining culvert environmental data collected by culvert detection equipment and performing feature point recognition, obtaining feature data of the detection feature points, comparing the feature data of the detection feature points with the feature data of the historical feature points in the culvert historical visualization model, using the historical feature points that meet the preset comparison requirements as matching feature points, and obtaining a coordinate transformation matrix based on the matching feature point coordinate data and the detection feature point coordinate data, and mapping the new detection feature point coordinate data to the global coordinate system based on the coordinate transformation matrix, generating a culvert visualization model based on the feature point global coordinate data, and conducting a culvert risk assessment based on the culvert visualization model, and marking key areas with hidden dangers; thereby realizing the technology of constructing a visualization model of the culvert and intelligent risk assessment.

Description

Technical Field

[0001] The present application relates to the technical field of big data and culvert model construction, and in particular to a culvert visualization model construction method, system and medium based on SLAM. Background Art

[0002] Culverts are an important part of urban drainage systems. However, due to their complex environment, narrow space, deep burial depth, and surface debris coverage, traditional detection methods such as QV detection mirrors, geological radar detectors, and frogman infiltration detection methods have limitations, making it difficult to achieve high-precision detection and rapid modeling while ensuring safety. SLAM (Simultaneous Localization and Mapping) technology can efficiently collect comprehensive three-dimensional point cloud data of complex urban pipelines, accurately obtain the location, internal structure, and direction of underground pipelines, and present them in a three-dimensional visual form, allowing users to understand the distribution of the pipeline network more intuitively and clearly, making operations intelligent. Summary of the invention

[0003] The purpose of this application is to provide a method, system and medium for constructing a culvert visualization model based on SLAM, generate a culvert visualization model according to the culvert environment data collected by the culvert detection equipment, evaluate the risk level of the culvert according to the culvert visualization model, and mark key areas with hidden dangers, thereby realizing the technology of culvert visualization model construction and intelligent risk assessment.

[0004] The present application also provides a method for constructing a culvert visualization model based on SLAM, comprising the following steps:

[0005] Acquire the culvert environment data collected by the culvert detection equipment, perform feature point recognition on the culvert environment data, obtain detection feature point coordinate data and image feature data of the detection feature points, and obtain feature description vectors and feature point direction data according to image feature data processing;

[0006] Obtaining historical feature description vectors and historical feature point direction data of the historical feature points of the culvert historical visualization model, comparing the historical feature description vectors and the historical feature point direction data with the feature description vectors and the feature point direction data respectively, taking the historical feature points that meet the preset comparison requirements as matching feature points, and processing them according to the matching feature point coordinate data and the detected feature point coordinate data to obtain a coordinate conversion matrix;

[0007] Acquire newly collected culvert environment data, perform feature point recognition, obtain newly detected feature point coordinate data of the newly detected feature points, map the newly detected feature point coordinate data to the global coordinate system according to the coordinate transformation matrix, obtain the feature point global coordinate data, and generate a culvert visualization model according to the feature point global coordinate data.

[0008] Optionally, in the method for constructing a culvert visualization model based on SLAM described in the present application, the steps of acquiring culvert environment data collected by a culvert detection device, identifying feature points of the culvert environment data, obtaining detection feature point coordinate data and image feature data of the detection feature points, and obtaining feature description vectors and feature point direction data according to image feature data processing include:

[0009] Obtaining the culvert environment data collected by the culvert detection equipment, using a preset feature recognition algorithm to identify feature points of the culvert environment data, and using the identified feature points as detection feature points;

[0010] Acquire detection feature point coordinate data and image feature data of the detection feature point, the image feature data including gradient direction data and corresponding gradient amplitude data;

[0011] Generating a gradient histogram according to the gradient amplitude data in all gradient directions, and accumulating the gradient amplitude data in all gradient directions to obtain gradient amplitude accumulation values ​​corresponding to different gradient directions;

[0012] Convert all gradient magnitude data in the gradient histogram into vector representation to obtain a feature description vector;

[0013] The gradient amplitude accumulated values ​​corresponding to different gradient directions are sorted in descending order, and the gradient direction data corresponding to the gradient direction with the largest gradient amplitude accumulated value is used as the feature point direction data.

[0014] Optionally, in the method for constructing a culvert visualization model based on SLAM described in the present application, the historical feature description vector and the historical feature point direction data of the historical feature points of the culvert historical visualization model are obtained, the historical feature description vector and the historical feature point direction data are respectively compared with the feature description vector and the feature point direction data, the historical feature points that meet the preset comparison requirements are used as matching feature points, and the matching feature point coordinate data and the detected feature point coordinate data are processed to obtain a coordinate transformation matrix, including:

[0015] Obtain the historical feature description vectors and direction data of the historical feature points of the culvert historical visualization model;

[0016] Comparing the feature description vector with the historical feature description vector, and taking the historical feature points corresponding to the historical feature description vectors that meet the preset comparison requirements as feature points to be matched;

[0017] Comparing the feature point direction data with the historical feature point direction data corresponding to the feature point to be matched, and taking the feature point to be matched corresponding to the historical feature point direction data that meets the preset comparison requirements as the matching feature point;

[0018] Obtaining coordinate data of matching feature points of the matching feature points in the culvert history visualization model;

[0019] A coordinate transformation matrix is ​​obtained by performing calculations based on the matching feature point coordinate data and the detection feature point coordinate data.

[0020] Optionally, the method for constructing a culvert visualization model based on SLAM described in the present application further includes:

[0021] Calculate according to the global coordinate data of the feature point and the coordinate data of the matching feature point to obtain a distance measurement value;

[0022] Performing secondary detection on the newly detected feature points to obtain coordinate data of the secondary detected feature points, and mapping the coordinate data of the secondary detected feature points to a global coordinate system to obtain global coordinate data of the secondary detected feature points;

[0023] Calculate the secondary detection distance measurement value based on the global coordinate data of the secondary detection feature point and the coordinate data of the matching feature point;

[0024] The distance measurement value and the secondary detection distance measurement value are compared, and if the comparison result does not meet the preset comparison result requirement, a re-detection reminder is performed.

[0025] Optionally, the method for constructing a culvert visualization model based on SLAM described in the present application further includes:

[0026] Using the culvert visualization model to simulate the leakage state of the culvert, and obtaining simulation result data, including pollutant diffusion area data and leakage rate data;

[0027] Obtain environmental data around the culvert, including data on the number of residents gathered and the distance to the water source;

[0028] The risk assessment index is obtained by performing calculations based on the pollutant diffusion area data, leakage rate data, resident gathering data, and water source distance data.

[0029] Optionally, the method for constructing a culvert visualization model based on SLAM described in the present application further includes:

[0030] Obtaining historical leakage data of underground canals, including pollution impact range data, environmental impact degree data, economic loss data and occurrence frequency data, and extracting underground canal pipeline damage area data and underground canal pipeline damage degree data according to the underground canal visualization model;

[0031] Calculate based on the pollution impact range data, environmental impact degree data, economic loss data, occurrence frequency data, and the underground pipeline damage area data and underground pipeline damage degree data to obtain a risk assessment correction factor;

[0032] Correcting the risk level assessment index according to the risk level assessment correction factor to obtain a risk level assessment correction index;

[0033] Comparing the risk level assessment correction index with a preset risk level assessment correction index threshold, and taking the range level to which the threshold comparison result belongs as the risk level assessment level;

[0034] The risk level assessment level is input into a preset culvert emergency repair plan database for matching and identification to obtain culvert emergency repair plan data.

[0035] Optionally, the method for constructing a culvert visualization model based on SLAM described in the present application further includes:

[0036] Obtain water pollution degree data for different areas of the culvert, and calculate based on the culvert pipeline damage area data, culvert pipeline damage degree data, and water pollution degree data for different areas of the culvert to obtain culvert damage assessment indexes corresponding to different areas;

[0037] The culvert damage assessment index is compared with a preset culvert damage assessment index threshold value. If the threshold comparison result does not meet the preset threshold comparison result requirement, the area corresponding to the culvert damage assessment index is used as a key monitoring area;

[0038] Obtain pipeline material data in key monitoring areas, including material strength data and material service life data, and obtain historical maintenance record data of culverts in key monitoring areas, including repair degree data and repair frequency data;

[0039] Calculate according to the material strength data, material service life data, and the repair degree data and repair frequency data to obtain a hidden danger degree assessment index;

[0040] The hidden danger level assessment index is compared with a preset hidden danger level assessment index threshold. If the comparison result does not meet the preset threshold comparison result requirement, the key monitoring area is marked in the culvert visualization model.

[0041] In a second aspect, the present application provides a culvert visualization model construction system based on SLAM, the system comprising: a memory and a processor, wherein the memory stores a program of a culvert visualization model construction method based on SLAM, and when the program of the culvert visualization model construction method based on SLAM is executed by the processor, the following steps are implemented:

[0042] Acquire the culvert environment data collected by the culvert detection equipment, perform feature point recognition on the culvert environment data, obtain detection feature point coordinate data and image feature data of the detection feature points, and obtain feature description vectors and feature point direction data according to image feature data processing;

[0043] Obtaining historical feature description vectors and historical feature point direction data of the historical feature points of the culvert historical visualization model, comparing the historical feature description vectors and the historical feature point direction data with the feature description vectors and the feature point direction data respectively, taking the historical feature points that meet the preset comparison requirements as matching feature points, and processing them according to the matching feature point coordinate data and the detected feature point coordinate data to obtain a coordinate conversion matrix;

[0044] Acquire newly collected culvert environment data, perform feature point recognition, obtain newly detected feature point coordinate data of the newly detected feature points, map the newly detected feature point coordinate data to the global coordinate system according to the coordinate transformation matrix, obtain the feature point global coordinate data, and generate a culvert visualization model according to the feature point global coordinate data.

[0045] Optionally, in the culvert visualization model construction system based on SLAM described in the present application, the steps of acquiring culvert environment data collected by the culvert detection device, identifying feature points of the culvert environment data, obtaining detection feature point coordinate data and image feature data of the detection feature points, and obtaining feature description vectors and feature point direction data according to image feature data processing include:

[0046] Obtaining the culvert environment data collected by the culvert detection equipment, using a preset feature recognition algorithm to identify feature points of the culvert environment data, and using the identified feature points as detection feature points;

[0047] Acquire detection feature point coordinate data and image feature data of the detection feature point, the image feature data including gradient direction data and corresponding gradient amplitude data;

[0048] Generating a gradient histogram according to the gradient amplitude data in all gradient directions, and accumulating the gradient amplitude data in all gradient directions to obtain gradient amplitude accumulation values ​​corresponding to different gradient directions;

[0049] Convert all gradient magnitude data in the gradient histogram into vector representation to obtain a feature description vector;

[0050] The gradient amplitude accumulated values ​​corresponding to different gradient directions are sorted in descending order, and the gradient direction data corresponding to the gradient direction with the largest gradient amplitude accumulated value is used as the feature point direction data.

[0051] In the third aspect, the present application also provides a computer-readable storage medium, which stores a SLAM-based culvert visualization model construction method program. When the SLAM-based culvert visualization model construction method program is executed by a processor, the steps of the SLAM-based culvert visualization model construction method as described in any one of the above items are implemented.

[0052] From the above, it can be seen that the present application provides a method, system and medium for constructing a culvert visualization model based on SLAM, which generates a culvert visualization model based on the culvert environmental data collected by the culvert detection equipment, and evaluates the risk level of the culvert based on the culvert visualization model, and marks key areas with hidden dangers, thereby realizing the technology of constructing a visualization model of the culvert and intelligent risk assessment of the culvert.

[0053] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A flowchart of a method for constructing a culvert visualization model based on SLAM provided in an embodiment of the present application;

[0056] Figure 2 A flowchart of obtaining feature description vectors and feature point direction data of a method for constructing a culvert visualization model based on SLAM provided in an embodiment of the present application;

[0057] Figure 3 A flowchart of obtaining a coordinate transformation matrix for a method for constructing a culvert visualization model based on SLAM provided in an embodiment of the present application;

[0058] Figure 4A flowchart of obtaining culvert emergency repair plan data for a culvert visualization model construction method based on SLAM provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0060] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0061] Please refer to Figure 1 , Figure 1 The flowchart of the method for constructing a visual model of a culvert based on SLAM in some embodiments of the present application. The method for constructing a visual model of a culvert based on SLAM is used in a terminal device, such as a computer, a mobile phone terminal, etc. The method for constructing a visual model of a culvert based on SLAM includes the following steps:

[0062] S11, acquiring the culvert environment data collected by the culvert detection equipment, performing feature point recognition on the culvert environment data, obtaining detection feature point coordinate data and image feature data of the detection feature points, and obtaining feature description vectors and feature point direction data according to image feature data processing;

[0063] S12, obtaining the historical feature description vector and the historical feature point direction data of the historical feature points of the culvert historical visualization model, comparing the historical feature description vector and the historical feature point direction data with the feature description vector and the feature point direction data respectively, taking the historical feature points that meet the preset comparison requirements as matching feature points, and processing them according to the matching feature point coordinate data and the detected feature point coordinate data to obtain a coordinate conversion matrix;

[0064] S13. Acquire newly collected culvert environment data, perform feature point recognition, obtain newly detected feature point coordinate data, map the newly detected feature point coordinate data to the global coordinate system according to the coordinate transformation matrix, obtain the feature point global coordinate data, and generate a culvert visualization model according to the feature point global coordinate data.

[0065] It should be noted that the underground channel environmental data collected by the underground channel detection equipment is obtained and feature point recognition is performed to obtain feature data of the detected feature points, the feature data of the detected feature points are compared with the feature data of the historical feature points in the underground channel historical visualization model, the historical feature points that meet the preset comparison requirements are used as matching feature points, and the coordinate transformation matrix is ​​obtained according to the matching feature point coordinate data and the detected feature point coordinate data, and the coordinate transformation matrix is ​​used to map the new detected feature point coordinate data to the global coordinate system to obtain the feature point global coordinate data, and the underground channel visualization model is generated according to the feature point global coordinate data;

[0066] The calculation formula of the global coordinate data of the feature point is:

[0067] ;

[0068] in, is the coordinate transformation matrix, is the horizontal coordinate data of the newly detected feature point in the device coordinate system, It is the ordinate data of the newly detected feature point in the device coordinate system. , , They are the global coordinate data of the feature points on the x-axis, y-axis, and z-axis of the newly detected feature points in the global coordinate system. It is the preset equipment parameter matrix (which can be obtained by querying the preset culvert history visualization model database).

[0069] Please refer to Figure 2 , Figure 2 The present invention is a flowchart of obtaining feature description vectors and feature point direction data of a method for constructing a culvert visualization model based on SLAM in some embodiments of the present invention. According to an embodiment of the present invention, the method of obtaining culvert environment data collected by a culvert detection device, identifying feature points of the culvert environment data, obtaining detection feature point coordinate data and image feature data of the detection feature points, and obtaining feature description vectors and feature point direction data according to image feature data processing includes:

[0070] S21, acquiring the culvert environment data collected by the culvert detection equipment, identifying feature points of the culvert environment data using a preset feature recognition algorithm, and using the identified feature points as detection feature points;

[0071] S22, acquiring the detected feature point coordinate data and image feature data of the detected feature point, where the image feature data includes gradient direction data and its corresponding gradient amplitude data;

[0072] S23, generating a gradient histogram according to the gradient amplitude data in all gradient directions, and accumulating the gradient amplitude data in all gradient directions to obtain gradient amplitude accumulation values ​​corresponding to different gradient directions;

[0073] S24, converting all the gradient amplitude data in the gradient histogram into vector representation to obtain a feature description vector;

[0074] S25 , sorting the gradient amplitude accumulated values ​​corresponding to different gradient directions in descending order, and taking the gradient direction data corresponding to the gradient direction with the largest gradient amplitude accumulated value as the feature point direction data.

[0075] It should be noted that the underground channel environment data collected by the underground channel detection equipment is obtained, feature points are identified on the underground channel environment data, the detection feature point coordinate data and image feature data of the detection feature points are obtained, and the feature description vector and feature point direction data are obtained according to the image feature data processing. The feature description vector is data representing the feature of the feature point, and the gradient direction data and gradient amplitude data are both data describing the image features of the feature points.

[0076] Please refer to Figure 3 , Figure 3 It is a flowchart of obtaining a coordinate transformation matrix of a method for constructing a culvert visualization model based on SLAM in some embodiments of the present application. According to an embodiment of the present invention, the historical feature description vector and the historical feature point direction data of the historical feature points of the culvert historical visualization model are obtained, and the historical feature description vector and the historical feature point direction data are respectively compared with the feature description vector and the feature point direction data, and the historical feature points that meet the preset comparison requirements are used as matching feature points, and the matching feature point coordinate data and the detected feature point coordinate data are processed to obtain a coordinate transformation matrix, including:

[0077] S31, obtaining historical feature description vectors and direction data of historical feature points of the historical visualization model of the culvert;

[0078] S32, comparing the feature description vector with the historical feature description vector, and taking the historical feature points corresponding to the historical feature description vectors that meet the preset comparison requirements as feature points to be matched;

[0079] S33, comparing the feature point direction data with the historical feature point direction data corresponding to the feature point to be matched, and taking the feature point to be matched corresponding to the historical feature point direction data that meets the preset comparison requirements as the matching feature point;

[0080] S34, obtaining the coordinate data of the matching feature points of the matching feature points in the historical visualization model of the culvert;

[0081] S35 . Calculate according to the matching feature point coordinate data and the detection feature point coordinate data to obtain a coordinate transformation matrix.

[0082] It should be noted that the feature data of the detected feature points are compared with the feature data of the historical feature points in the historical visualization model of the culvert, and the historical feature points that meet the preset comparison requirements are used as matching feature points, and the coordinate transformation matrix is ​​obtained based on the coordinate data of the matching feature points and the coordinate data of the detected feature points. The culvert visualization model is a three-dimensional space model, while the data collected by the detection equipment is two-dimensional data, which needs to be converted to the global coordinate system, so the coordinate transformation matrix needs to be calculated;

[0083] The calculation formula of the coordinate transformation matrix is:

[0084] ;

[0085] in, is the coordinate transformation matrix, m is the horizontal coordinate data of the detected feature point in the device coordinate system, n is the vertical coordinate data of the detected feature point in the device coordinate system, , , They are the coordinate data of the matching feature points on the x-axis, y-axis, and z-axis in the global coordinate system. It is the preset equipment parameter matrix (which can be obtained by querying the preset culvert history visualization model database).

[0086] According to an embodiment of the present invention, it also includes:

[0087] Calculate according to the global coordinate data of the feature point and the coordinate data of the matching feature point to obtain a distance measurement value;

[0088] Performing secondary detection on the newly detected feature points to obtain coordinate data of the secondary detected feature points, and mapping the coordinate data of the secondary detected feature points to a global coordinate system to obtain global coordinate data of the secondary detected feature points;

[0089] Calculate the secondary detection distance measurement value based on the global coordinate data of the secondary detection feature point and the coordinate data of the matching feature point;

[0090] The distance measurement value and the secondary detection distance measurement value are compared, and if the comparison result does not meet the preset comparison result requirement, a re-detection reminder is performed.

[0091] It should be noted that the positional relationship of the same feature point detected twice in space should be consistent. By comparing the spatial distances between the feature points detected twice and the matching feature points in the historical visualization model, it can be determined whether there is a detection error. If the two detections are inconsistent, it means that there is a detection error and re-detection is required.

[0092] The calculation formula of the distance metric value is:

[0093] ;

[0094] in, is the distance metric;

[0095] The calculation formula of the secondary detection distance measurement value is:

[0096] ;

[0097] in, is the secondary detection distance measurement value, , , They are respectively the coordinate data of the secondary detection feature points in the global coordinate system on the x-axis, y-axis, and z-axis.

[0098] According to an embodiment of the present invention, it also includes:

[0099] Using the culvert visualization model to simulate the leakage state of the culvert, and obtaining simulation result data, including pollutant diffusion area data and leakage rate data;

[0100] Obtain environmental data around the culvert, including data on the number of residents gathered and the distance to the water source;

[0101] The risk assessment index is obtained by performing calculations based on the pollutant diffusion area data, leakage rate data, resident gathering data, and water source distance data.

[0102] It should be noted that the culvert visualization model is used to simulate the leakage status of the culvert, and the culvert risk level is assessed based on the simulation result data;

[0103] The calculation formula of the risk assessment index is:

[0104] ;

[0105] in, is the risk assessment index, is the pollutant diffusion area data, To leak speed data, For the data of the number of residents gathered, is the distance data of water source, , , and It is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database).

[0106] Please refer to Figure 4 , Figure 4 The flowchart of the method for constructing a culvert visualization model based on SLAM in some embodiments of the present application for obtaining emergency repair plan data of the culvert. According to an embodiment of the present invention, it also includes:

[0107] S41, obtaining historical leakage data of the culvert, including pollution impact range data, environmental impact degree data, economic loss data and occurrence frequency data, and extracting culvert pipeline damage area data and culvert pipeline damage degree data according to the culvert visualization model;

[0108] S42, calculating according to the pollution impact range data, environmental impact degree data, economic loss data, occurrence frequency data, and the underground pipeline damage area data and underground pipeline damage degree data to obtain a risk assessment correction factor;

[0109] S43, correcting the risk level assessment index according to the risk level assessment correction factor to obtain a risk level assessment correction index;

[0110] S44, comparing the risk level assessment correction index with a preset risk level assessment correction index threshold, and taking the range level to which the threshold comparison result belongs as the risk level assessment level;

[0111] S45, inputting the risk assessment level into a preset culvert emergency repair plan database for matching and identification, and obtaining culvert emergency repair plan data.

[0112] It should be noted that the risk assessment correction factor is calculated based on the historical leakage data of the culvert, the damaged area data of the culvert pipes and the damaged degree data of the culvert pipes;

[0113] The calculation formula of the risk assessment correction factor is:

[0114] ;

[0115] in, is the risk assessment correction factor, For pollution impact data, For environmental impact data, For economic loss data, is the frequency data, The damaged area of ​​underground pipes is The damage degree data of underground pipes. , , and is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database);

[0116] The risk level assessment index is corrected according to the risk level assessment correction factor to obtain the risk level assessment correction index;

[0117] The calculation formula of the risk assessment correction index is:

[0118] ;

[0119] in, To assess the risk level, the index is modified. It is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database).

[0120] According to an embodiment of the present invention, it also includes:

[0121] Obtain water pollution degree data for different areas of the culvert, and calculate based on the culvert pipeline damage area data, culvert pipeline damage degree data, and water pollution degree data for different areas of the culvert to obtain culvert damage assessment indexes corresponding to different areas;

[0122] The culvert damage assessment index is compared with a preset culvert damage assessment index threshold value. If the threshold comparison result does not meet the preset threshold comparison result requirement, the area corresponding to the culvert damage assessment index is used as a key monitoring area;

[0123] Obtain pipeline material data in key monitoring areas, including material strength data and material service life data, and obtain historical maintenance record data of culverts in key monitoring areas, including repair degree data and repair frequency data;

[0124] Calculate according to the material strength data, material service life data, and the repair degree data and repair frequency data to obtain a hidden danger degree assessment index;

[0125] The hidden danger level assessment index is compared with a preset hidden danger level assessment index threshold. If the comparison result does not meet the preset threshold comparison result requirement, the key monitoring area is marked in the culvert visualization model.

[0126] It should be noted that the key monitoring areas are screened by using the culvert damage assessment index in different areas. The calculation formula of the culvert damage assessment index is:

[0127] ;

[0128] in, is the culvert damage assessment index, For water pollution degree data, , and is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database);

[0129] The hidden danger level of key areas is assessed to obtain a hidden danger level assessment index, the calculation formula of which is:

[0130] ;

[0131] in, is the hidden danger level assessment index, is the material strength data, is the material service life data, To repair the degree data, To repair the frequency data, , and It is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database).

[0132] The present invention also discloses a culvert visualization model construction system based on SLAM, comprising a memory and a processor, wherein the culvert visualization model construction method program based on SLAM is stored in the memory, and when the culvert visualization model construction method program based on SLAM is executed by the processor, the following steps are implemented:

[0133] Acquire the culvert environment data collected by the culvert detection equipment, perform feature point recognition on the culvert environment data, obtain detection feature point coordinate data and image feature data of the detection feature points, and obtain feature description vectors and feature point direction data according to image feature data processing;

[0134] Obtaining historical feature description vectors and historical feature point direction data of the historical feature points of the culvert historical visualization model, comparing the historical feature description vectors and the historical feature point direction data with the feature description vectors and the feature point direction data respectively, taking the historical feature points that meet the preset comparison requirements as matching feature points, and processing them according to the matching feature point coordinate data and the detected feature point coordinate data to obtain a coordinate conversion matrix;

[0135] Acquire newly collected culvert environment data, perform feature point recognition, obtain newly detected feature point coordinate data of the newly detected feature points, map the newly detected feature point coordinate data to the global coordinate system according to the coordinate transformation matrix, obtain the feature point global coordinate data, and generate a culvert visualization model according to the feature point global coordinate data.

[0136] It should be noted that the underground channel environmental data collected by the underground channel detection equipment is obtained and feature point recognition is performed to obtain feature data of the detected feature points, the feature data of the detected feature points are compared with the feature data of the historical feature points in the underground channel historical visualization model, the historical feature points that meet the preset comparison requirements are used as matching feature points, and the coordinate transformation matrix is ​​obtained according to the matching feature point coordinate data and the detected feature point coordinate data, and the coordinate transformation matrix is ​​used to map the new detected feature point coordinate data to the global coordinate system to obtain the feature point global coordinate data, and the underground channel visualization model is generated according to the feature point global coordinate data;

[0137] The calculation formula of the global coordinate data of the feature point is:

[0138] ;

[0139] in, is the coordinate transformation matrix, is the horizontal coordinate data of the newly detected feature point in the device coordinate system, It is the ordinate data of the newly detected feature point in the device coordinate system. , , They are the global coordinate data of the feature points on the x-axis, y-axis, and z-axis of the newly detected feature points in the global coordinate system. It is the preset equipment parameter matrix (which can be obtained by querying the preset culvert history visualization model database).

[0140] According to an embodiment of the present invention, the method of acquiring the culvert environment data collected by the culvert detection device, identifying feature points of the culvert environment data, obtaining detection feature point coordinate data and image feature data of the detection feature points, and obtaining feature description vectors and feature point direction data according to image feature data processing includes:

[0141] Obtaining the culvert environment data collected by the culvert detection equipment, using a preset feature recognition algorithm to identify feature points of the culvert environment data, and using the identified feature points as detection feature points;

[0142] Acquire detection feature point coordinate data and image feature data of the detection feature point, the image feature data including gradient direction data and corresponding gradient amplitude data;

[0143] Generating a gradient histogram according to the gradient amplitude data in all gradient directions, and accumulating the gradient amplitude data in all gradient directions to obtain gradient amplitude accumulation values ​​corresponding to different gradient directions;

[0144] Convert all gradient magnitude data in the gradient histogram into vector representation to obtain a feature description vector;

[0145] The gradient amplitude accumulated values ​​corresponding to different gradient directions are sorted in descending order, and the gradient direction data corresponding to the gradient direction with the largest gradient amplitude accumulated value is used as the feature point direction data.

[0146] It should be noted that the underground channel environment data collected by the underground channel detection equipment is obtained, feature points are identified on the underground channel environment data, the detection feature point coordinate data and image feature data of the detection feature points are obtained, and the feature description vector and feature point direction data are obtained according to the image feature data processing. The feature description vector is data representing the feature of the feature point, and the gradient direction data and gradient amplitude data are both data describing the image features of the feature points.

[0147] According to an embodiment of the present invention, the historical feature description vector and the historical feature point direction data of the historical feature point of the culvert historical visualization model are obtained, the historical feature description vector and the historical feature point direction data are respectively compared with the feature description vector and the feature point direction data, the historical feature points that meet the preset comparison requirements are used as matching feature points, and the matching feature point coordinate data and the detected feature point coordinate data are processed to obtain a coordinate transformation matrix, including:

[0148] Obtain the historical feature description vectors and direction data of the historical feature points of the culvert historical visualization model;

[0149] Comparing the feature description vector with the historical feature description vector, and taking the historical feature points corresponding to the historical feature description vectors that meet the preset comparison requirements as feature points to be matched;

[0150] Comparing the feature point direction data with the historical feature point direction data corresponding to the feature point to be matched, and taking the feature point to be matched corresponding to the historical feature point direction data that meets the preset comparison requirements as the matching feature point;

[0151] Obtaining coordinate data of matching feature points of the matching feature points in the culvert history visualization model;

[0152] A coordinate transformation matrix is ​​obtained by performing calculations based on the matching feature point coordinate data and the detection feature point coordinate data.

[0153] It should be noted that the feature data of the detected feature points are compared with the feature data of the historical feature points in the historical visualization model of the culvert, and the historical feature points that meet the preset comparison requirements are used as matching feature points, and the coordinate transformation matrix is ​​obtained based on the coordinate data of the matching feature points and the coordinate data of the detected feature points. The culvert visualization model is a three-dimensional space model, while the data collected by the detection equipment is two-dimensional data, which needs to be converted to the global coordinate system, so the coordinate transformation matrix needs to be calculated;

[0154] The calculation formula of the coordinate transformation matrix is:

[0155] ;

[0156] in, is the coordinate transformation matrix, m is the horizontal coordinate data of the detected feature point in the device coordinate system, n is the vertical coordinate data of the detected feature point in the device coordinate system, , , They are the coordinate data of the matching feature points on the x-axis, y-axis, and z-axis in the global coordinate system. It is the preset equipment parameter matrix (which can be obtained by querying the preset culvert history visualization model database).

[0157] According to an embodiment of the present invention, it also includes:

[0158] Calculate according to the global coordinate data of the feature point and the coordinate data of the matching feature point to obtain a distance measurement value;

[0159] Performing secondary detection on the newly detected feature points to obtain coordinate data of the secondary detected feature points, and mapping the coordinate data of the secondary detected feature points to a global coordinate system to obtain global coordinate data of the secondary detected feature points;

[0160] Calculate the secondary detection distance measurement value based on the global coordinate data of the secondary detection feature point and the coordinate data of the matching feature point;

[0161] The distance measurement value and the secondary detection distance measurement value are compared, and if the comparison result does not meet the preset comparison result requirement, a re-detection reminder is performed.

[0162] It should be noted that the positional relationship of the same feature point detected twice in space should be consistent. By comparing the spatial distances between the feature points detected twice and the matching feature points in the historical visualization model, it can be determined whether there is a detection error. If the two detections are inconsistent, it means that there is a detection error and re-detection is required.

[0163] The calculation formula of the distance metric value is:

[0164] ;

[0165] in, is the distance metric;

[0166] The calculation formula of the secondary detection distance measurement value is:

[0167] ;

[0168] in, is the secondary detection distance measurement value, , , They are respectively the coordinate data of the secondary detection feature points in the global coordinate system on the x-axis, y-axis, and z-axis.

[0169] According to an embodiment of the present invention, it also includes:

[0170] Using the culvert visualization model to simulate the leakage state of the culvert, and obtaining simulation result data, including pollutant diffusion area data and leakage rate data;

[0171] Obtain environmental data around the culvert, including data on the number of residents gathered and the distance to the water source;

[0172] The risk assessment index is obtained by performing calculations based on the pollutant diffusion area data, leakage rate data, resident gathering data, and water source distance data.

[0173] It should be noted that the culvert visualization model is used to simulate the leakage status of the culvert, and the culvert risk level is assessed based on the simulation result data;

[0174] The calculation formula of the risk assessment index is:

[0175] ;

[0176] in, is the risk assessment index, is the pollutant diffusion area data, To leak speed data, For the data of the number of residents gathered, is the distance data of water source, , , and It is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database).

[0177] According to an embodiment of the present invention, it also includes:

[0178] Obtaining historical leakage data of underground canals, including pollution impact range data, environmental impact degree data, economic loss data and occurrence frequency data, and extracting underground canal pipeline damage area data and underground canal pipeline damage degree data according to the underground canal visualization model;

[0179] Calculate based on the pollution impact range data, environmental impact degree data, economic loss data, occurrence frequency data, and the underground pipeline damage area data and underground pipeline damage degree data to obtain a risk assessment correction factor;

[0180] Correcting the risk level assessment index according to the risk level assessment correction factor to obtain a risk level assessment correction index;

[0181] Comparing the risk level assessment correction index with a preset risk level assessment correction index threshold, and taking the range level to which the threshold comparison result belongs as the risk level assessment level;

[0182] The risk level assessment level is input into a preset culvert emergency repair plan database for matching and identification to obtain culvert emergency repair plan data.

[0183] It should be noted that the risk assessment correction factor is calculated based on the historical leakage data of the culvert, the damaged area data of the culvert pipes and the damaged degree data of the culvert pipes;

[0184] The calculation formula of the risk assessment correction factor is:

[0185] ;

[0186] in, is the risk assessment correction factor, For pollution impact data, For environmental impact data, For economic loss data, is the frequency data, The damaged area of ​​underground pipes is The damage degree data of underground pipes. , , and is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database);

[0187] The risk level assessment index is corrected according to the risk level assessment correction factor to obtain the risk level assessment correction index;

[0188] The calculation formula of the risk assessment correction index is:

[0189] ;

[0190] in, To assess the risk level, the index is modified. It is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database).

[0191] According to an embodiment of the present invention, it also includes:

[0192] Obtain water pollution degree data for different areas of the culvert, and calculate based on the culvert pipeline damage area data, culvert pipeline damage degree data, and water pollution degree data for different areas of the culvert to obtain culvert damage assessment indexes corresponding to different areas;

[0193] The culvert damage assessment index is compared with a preset culvert damage assessment index threshold value. If the threshold comparison result does not meet the preset threshold comparison result requirement, the area corresponding to the culvert damage assessment index is used as a key monitoring area;

[0194] Obtain pipeline material data in key monitoring areas, including material strength data and material service life data, and obtain historical maintenance record data of culverts in key monitoring areas, including repair degree data and repair frequency data;

[0195] Calculate according to the material strength data, material service life data, and the repair degree data and repair frequency data to obtain a hidden danger degree assessment index;

[0196] The hidden danger level assessment index is compared with a preset hidden danger level assessment index threshold. If the comparison result does not meet the preset threshold comparison result requirement, the key monitoring area is marked in the culvert visualization model.

[0197] It should be noted that the key monitoring areas are screened by using the culvert damage assessment index in different areas. The calculation formula of the culvert damage assessment index is:

[0198] ;

[0199] in, is the culvert damage assessment index, For water pollution degree data, , and is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database);

[0200] The hidden danger level of key areas is assessed to obtain a hidden danger level assessment index, the calculation formula of which is:

[0201] ;

[0202] in, is the hidden danger level assessment index, is the material strength data, is the material service life data, To repair the degree data, To repair the frequency data, , and It is the preset characteristic coefficient (which can be obtained by querying the preset culvert history visualization model database).

[0203] A third aspect of the present invention provides a readable storage medium, which stores a SLAM-based culvert visualization model construction method program. When the SLAM-based culvert visualization model construction method program is executed by a processor, the steps of the SLAM-based culvert visualization model construction method as described in any one of the above items are implemented.

[0204] The present invention discloses a method, system and medium for constructing a culvert visualization model based on SLAM, which generates a culvert visualization model according to culvert environmental data collected by culvert detection equipment, evaluates the risk level of the culvert according to the culvert visualization model, and marks key areas with hidden dangers, thereby realizing the technology of constructing a visualization model of the culvert and intelligent risk assessment of the culvert.

[0205] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0206] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0207] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0208] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0209] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A method for constructing a visual model of a culvert based on SLAM, characterized in that: The following steps are involved: Acquire the culvert environment data collected by the culvert detection equipment, perform feature point recognition on the culvert environment data, obtain detection feature point coordinate data and image feature data of the detection feature points, and obtain feature description vectors and feature point direction data according to image feature data processing; Obtaining historical feature description vectors and historical feature point direction data of the historical feature points of the culvert historical visualization model, comparing the historical feature description vectors and the historical feature point direction data with the feature description vectors and the feature point direction data respectively, taking the historical feature points that meet the preset comparison requirements as matching feature points, and processing them according to the matching feature point coordinate data and the detected feature point coordinate data to obtain a coordinate conversion matrix; Acquire newly collected culvert environment data, perform feature point recognition, obtain newly detected feature point coordinate data of the newly detected feature point, map the newly detected feature point coordinate data to the global coordinate system according to the coordinate transformation matrix, obtain the feature point global coordinate data, and generate a culvert visualization model according to the feature point global coordinate data; The method of acquiring the culvert environment data collected by the culvert detection device, identifying feature points of the culvert environment data, obtaining detection feature point coordinate data and image feature data of the detection feature points, and obtaining feature description vectors and feature point direction data according to image feature data processing includes: Obtaining the culvert environment data collected by the culvert detection equipment, using a preset feature recognition algorithm to identify feature points of the culvert environment data, and using the identified feature points as detection feature points; Acquire detection feature point coordinate data and image feature data of the detection feature point, the image feature data including gradient direction data and corresponding gradient amplitude data; Generating a gradient histogram according to the gradient amplitude data in all gradient directions, and accumulating the gradient amplitude data in all gradient directions to obtain gradient amplitude accumulation values ​​corresponding to different gradient directions; Convert all gradient magnitude data in the gradient histogram into vector representation to obtain a feature description vector; The gradient amplitude accumulated values ​​corresponding to different gradient directions are sorted in descending order, and the gradient direction data corresponding to the gradient direction with the largest gradient amplitude accumulated value is used as the feature point direction data.

2. The method for constructing a culvert visualization model based on SLAM according to claim 1, characterized in that: The method of obtaining the historical feature description vector and the historical feature point direction data of the historical feature points of the culvert historical visualization model, comparing the historical feature description vector and the historical feature point direction data with the feature description vector and the feature point direction data respectively, taking the historical feature points that meet the preset comparison requirements as matching feature points, and processing according to the matching feature point coordinate data and the detected feature point coordinate data to obtain a coordinate transformation matrix includes: Obtain the historical feature description vectors and direction data of the historical feature points of the culvert historical visualization model; Comparing the feature description vector with the historical feature description vector, and taking the historical feature points corresponding to the historical feature description vectors that meet the preset comparison requirements as feature points to be matched; Comparing the feature point direction data with the historical feature point direction data corresponding to the feature point to be matched, and taking the feature point to be matched corresponding to the historical feature point direction data that meets the preset comparison requirements as the matching feature point; Obtaining coordinate data of matching feature points of the matching feature points in the culvert history visualization model; Calculation is performed based on the matching feature point coordinate data and the detection feature point coordinate data to obtain a coordinate transformation matrix.

3. The method for constructing a culvert visualization model based on SLAM according to claim 2, characterized in that: Also includes: Calculate the distance value based on the global coordinate data of the feature point and the coordinate data of the matching feature point; Performing secondary detection on the newly detected feature points to obtain coordinate data of the secondary detected feature points, and mapping the coordinate data of the secondary detected feature points to a global coordinate system to obtain global coordinate data of the secondary detected feature points; Calculate the secondary detection distance measurement value based on the global coordinate data of the secondary detection feature point and the coordinate data of the matching feature point; The distance measurement value and the secondary detection distance measurement value are compared, and if the comparison result does not meet the preset comparison result requirement, a re-detection reminder is performed.

4. The method for constructing a culvert visualization model based on SLAM according to claim 3, characterized in that: Also includes: Using the culvert visualization model to simulate the leakage state of the culvert, and obtaining simulation result data, including pollutant diffusion area data and leakage speed data; Obtain environmental data around the culvert, including data on the number of residents gathered and the distance to the water source; The risk assessment index is obtained by performing calculations based on the pollutant diffusion area data, leakage rate data, resident gathering data, and water source distance data.

5. The method for constructing a culvert visualization model based on SLAM according to claim 4, characterized in that: Also includes: Obtaining historical leakage data of the culvert, including pollution impact range data, environmental impact degree data, economic loss data and occurrence frequency data, and extracting culvert pipeline damage area data and culvert pipeline damage degree data according to the culvert visualization model; Calculate based on the pollution impact range data, environmental impact degree data, economic loss data, occurrence frequency data, and the underground pipeline damage area data and underground pipeline damage degree data to obtain a risk assessment correction factor; Correcting the risk level assessment index according to the risk level assessment correction factor to obtain a risk level assessment correction index; Comparing the risk level assessment correction index with a preset risk level assessment correction index threshold, and taking the range level to which the threshold comparison result belongs as the risk level assessment level; The risk level assessment level is input into a preset culvert emergency repair plan database for matching and identification to obtain culvert emergency repair plan data.

6. The method for constructing a culvert visualization model based on SLAM according to claim 5, characterized in that: Also includes: Obtain water pollution degree data for different areas of the culvert, and calculate based on the culvert pipeline damage area data, culvert pipeline damage degree data, and water pollution degree data for different areas of the culvert to obtain culvert damage assessment indexes corresponding to different areas; The culvert damage assessment index is compared with a preset culvert damage assessment index threshold value. If the threshold comparison result does not meet the preset threshold comparison result requirement, the area corresponding to the culvert damage assessment index is used as a key monitoring area; Obtain pipeline material data in key monitoring areas, including material strength data and material service life data, and obtain historical maintenance record data of culverts in key monitoring areas, including repair degree data and repair frequency data; Calculate according to the material strength data, material service life data, and the repair degree data and repair frequency data to obtain a hidden danger degree assessment index; The hidden danger level assessment index is compared with a preset hidden danger level assessment index threshold. If the comparison result does not meet the preset threshold comparison result requirement, the key monitoring area is marked in the culvert visualization model.

7. A SLAM-based culvert visualization model construction system, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a program of a method for constructing a visual model of a culvert based on SLAM, and when the program of the method for constructing a visual model of a culvert based on SLAM is executed by the processor, the following steps are implemented: Acquire the culvert environment data collected by the culvert detection equipment, perform feature point recognition on the culvert environment data, obtain detection feature point coordinate data and image feature data of the detection feature points, and obtain feature description vectors and feature point direction data according to image feature data processing; Obtaining historical feature description vectors and historical feature point direction data of the historical feature points of the culvert historical visualization model, comparing the historical feature description vectors and the historical feature point direction data with the feature description vectors and the feature point direction data respectively, taking the historical feature points that meet the preset comparison requirements as matching feature points, and processing them according to the matching feature point coordinate data and the detected feature point coordinate data to obtain a coordinate conversion matrix; Acquire newly collected culvert environment data, perform feature point recognition, obtain newly detected feature point coordinate data of the newly detected feature point, map the newly detected feature point coordinate data to the global coordinate system according to the coordinate transformation matrix, obtain the feature point global coordinate data, and generate a culvert visualization model according to the feature point global coordinate data; The method of acquiring the culvert environment data collected by the culvert detection device, identifying feature points of the culvert environment data, obtaining detection feature point coordinate data and image feature data of the detection feature points, and obtaining feature description vectors and feature point direction data according to image feature data processing includes: Obtaining the culvert environment data collected by the culvert detection equipment, using a preset feature recognition algorithm to identify feature points of the culvert environment data, and using the identified feature points as detection feature points; Acquire detection feature point coordinate data and image feature data of the detection feature point, the image feature data including gradient direction data and corresponding gradient amplitude data; Generating a gradient histogram according to the gradient amplitude data in all gradient directions, and accumulating the gradient amplitude data in all gradient directions to obtain gradient amplitude accumulation values ​​corresponding to different gradient directions; Convert all gradient magnitude data in the gradient histogram into vector representation to obtain a feature description vector; The gradient amplitude accumulated values ​​corresponding to different gradient directions are sorted in descending order, and the gradient direction data corresponding to the gradient direction with the largest gradient amplitude accumulated value is used as the feature point direction data.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a SLAM-based culvert visualization model construction program. When the SLAM-based culvert visualization model construction program is executed by a processor, the steps of the SLAM-based culvert visualization model construction method as described in any one of claims 1 to 6 are implemented.

Images