Sonar-based sedimentation depth marking method, equipment and medium

Abstract

The present invention discloses a method, device and medium for marking the depth of sediment deposition based on sonar, and the method includes: obtaining sonar data, generating a recorded video according to the sonar data; automatically intercepting the recorded video image to obtain a cross-sectional image; converting the cross-sectional image into a point cloud to obtain a cross-sectional point cloud; performing preliminary denoising on the cross-sectional point cloud to extract the pipe wall target point cloud; performing least square fitting on the pipe wall target point cloud to obtain the pipe wall contour circular parameters; removing the pipe wall target point cloud from the cross-sectional point cloud and post-processing to obtain the deposition point cloud straight line parameters; marking according to the pipe wall contour circular parameters and the deposition point cloud straight line parameters to obtain a result map. The result map of the cross-sectional deposition depth marking is automatically drawn, which improves the marking efficiency of the urban underground pipe network and reduces the marking error, and can be widely used in the field of pipeline detection technology.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline detection, and in particular to a sonar-based silt deposition depth marking method, equipment and medium. Background Art

[0002] The existing sewage pipe inspection methods, such as CCTV (Closed Circuit Television) and other monitoring methods, require visualization as a prerequisite, which limits the inspection of the submerged pipes. In addition, the data collected from the pipes in the existing technology needs to be manually interpreted and the final result diagrams are annotated, which is inefficient, and the manual interpretation standards are inconsistent, and the annotated result diagrams are prone to errors. Summary of the invention

[0003] In view of this, the purpose of the embodiments of the present invention is to provide a sonar-based silt deposition depth marking method, device and medium, which can automatically mark the silt deposition depth of urban underground pipe networks with high marking efficiency and small marking error.

[0004] In a first aspect, an embodiment of the present invention provides a method for marking silt deposition depth based on sonar, comprising:

[0005] Acquire sonar data of the city's underground pipe network, wherein the sonar data represents data collected in real time by sonar equipment;

[0006] generating a recorded video based on the sonar data;

[0007] Automatically intercepting the recorded video to obtain a cross-sectional image of the urban underground pipe network;

[0008] Converting the cross-sectional image into a point cloud to obtain a cross-sectional point cloud of the urban underground pipe network;

[0009] After extracting the cross-section point cloud, a cross-section point cloud and a pipe wall target point cloud are obtained;

[0010] Performing least square fitting on the pipe wall target point cloud to obtain the pipe wall contour circular parameters;

[0011] Eliminating the pipe wall target point cloud from the cross-section point cloud and then processing to obtain the straight line parameters of the deposition point cloud;

[0012] The result graph is obtained by marking according to the circular parameters of the pipe wall contour and the straight line parameters of the deposition point cloud.

[0013] In some optional embodiments, the step of automatically intercepting the recorded video to obtain the cross-sectional image of the urban underground pipe network includes:

[0014] Color information and straight line information of each frame of the image in the recorded video are obtained, and the color information and straight line information represent the position information of the cross section.

[0015] In some optional embodiments, converting the cross-sectional image into a point cloud to obtain the cross-sectional point cloud of the urban underground pipe network includes:

[0016] Pixel information in the cross-sectional image is obtained and converted into a set of points representing spatial coordinates, wherein the coordinate values ​​of the points represent the spatial depth and distribution of each position in the cross-sectional image to form a cross-sectional point cloud.

[0017] In some optional embodiments, the point cloud is initially subjected to principal component analysis to remove some noise points, and the pipe wall target point cloud is extracted.

[0018] In some optional embodiments, performing least square fitting on the pipe wall target point cloud to obtain the pipe wall contour circular parameters includes:

[0019] Performing least square fitting on the pipe wall target point cloud to obtain a fitting circle;

[0020] The circular parameters of the tube wall contour are obtained by iteratively deleting farther points based on the fitting circle, and the circular parameters of the tube wall contour represent the fitting circle after the farther points are iteratively deleted.

[0021] In some optional embodiments, the obtaining of the circular parameters of the tube wall contour by iteratively deleting farther points based on the fitting circle includes:

[0022] Iteratively acquiring a first distance from a farther point outside the fitting circle to the fitting circle;

[0023] When the first distance is greater than the first iteration distance, deleting farther points outside the fitting circle;

[0024] Iteratively acquiring a second distance from a farther point in the fitting circle to a center point, wherein the center point represents the center of the fitting circle;

[0025] When the absolute value of the difference between the second distance and the radius of the fitting circle is greater than the second iteration distance, the farther points in the fitting circle are deleted.

[0026] In some optional embodiments, including:

[0027] ;

[0028] ;

[0029] ;

[0030] ;

[0031] in, represents the density of the pipe wall target point cloud, n represents the number of pipe wall target point clouds, i represents the i-th point in the pipe wall target point cloud, represents the horizontal and vertical coordinates of the i-th point, Represents the horizontal and vertical coordinates of the point closest to the i-th point, represents the center coordinates and radius of the fitted circle, Indicate point is the first distance from the farthest point outside the fitted circle to the fitted circle, Indicate point When it is a far point in the fitting circle, The second distance, represents the number of iterations, Indicates the current iteration number, e、f、 A constant parameter with different values.

[0032] In some optional embodiments, the step of removing the pipe wall target point cloud from the cross-section point cloud and then processing to obtain the deposition point cloud straight line parameters includes:

[0033] After removing the pipe wall target point cloud from the cross-section point cloud, an internal point cloud of the pipe wall is obtained;

[0034] Performing fast Euclidean clustering on the internal point cloud of the pipe wall to obtain a deposition point cloud;

[0035] The least squares fitting of the deposition point cloud is performed to obtain the deposition point cloud straight line parameters.

[0036] In a second aspect, an embodiment of the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the steps of the above method are implemented when the computer program is executed by the processor.

[0037] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to perform the method as described above.

[0038] The implementation of the embodiment of the present invention includes the following beneficial effects: The embodiment of the present invention provides a method for marking the depth of sediment deposition based on sonar, including: obtaining sonar data of an urban underground pipe network, the sonar data representing data collected by a sonar device; performing coordinate conversion on the sonar data to obtain a cross-sectional point cloud of the urban underground pipe network; extracting the cross-sectional point cloud to obtain a cross-sectional point cloud and a pipe wall target point cloud; performing least square fitting on the pipe wall target point cloud to obtain a pipe wall contour circular parameter; removing the pipe wall target point cloud from the cross-sectional point cloud and post-processing to obtain a deposition point cloud straight line parameter; marking according to the pipe wall contour circular parameter and the deposition point cloud straight line parameter to obtain a result map. By parsing the sonar data of the urban underground pipe network to obtain a cross-sectional point cloud, and obtaining the pipe wall contour circular parameter and the deposition point cloud straight line parameter after corresponding processing, a result map of cross-sectional deposition depth marking is automatically drawn, thereby improving the marking efficiency of the urban underground pipe network and reducing the marking error. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of a method for marking sediment deposition depth based on sonar provided by an embodiment of the present invention;

[0040] Figure 2 is an example diagram of a recorded video provided by an embodiment of the present invention;

[0041] Figure 3 is an example diagram of a cross-section point cloud provided by an embodiment of the present invention;

[0042] Figure 4 It is a schematic block diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0044] In the description of the present invention, it should be understood that descriptions involving orientation, such as up, down, front, back, left, right, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0045] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0046] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific content of the technical solution.

[0047] The following is a further description of a sonar-based silt deposition depth marking method according to an embodiment of the present invention.

[0048] Reference Figure 1 , Figure 1 A flow chart of a method for marking silt deposition depth based on sonar is provided in an embodiment of the present invention, and the method includes but is not limited to the following steps:

[0049] S101, obtaining sonar data of an urban underground pipe network, wherein the sonar data represents data collected in real time by a sonar device, and generating a recorded video according to the sonar data;

[0050] S102 automatically intercepts the recorded video to obtain a cross-sectional image of the urban underground pipe network;

[0051] S103 converts the cross-sectional image into a point cloud to obtain a cross-sectional point cloud of the urban underground pipe network;

[0052] S104, performing preliminary denoising on the cross-section point cloud to extract the pipe wall target point cloud;

[0053] S105, performing least square fitting on the pipe wall target point cloud to obtain pipe wall contour circular parameters;

[0054] S106, removing the pipe wall target point cloud from the cross-section point cloud and post-processing to obtain the straight line parameters of the deposition point cloud;

[0055] S107, annotating according to the circular parameters of the pipe wall contour and the straight line parameters of the deposition point cloud to obtain a result graph.

[0056] It is worth noting that the section of the present application can be understood as a cross section through the pipeline. Intensity information is that sonar collects data through the principle of acoustic propagation. After the sound waves emitted by the sonar encounter an object, a strong energy value is generated here and returned. This energy value is considered to be intensity information. The place where the intensity information value is higher in the pipeline is the cross-sectional profile of the pipeline. Each high intensity value point can be converted into an (x, y) coordinate representation to obtain a point cloud set. Sonar data includes multiple frames of cross-sectional intensity information. Different frames represent different positions in the pipeline at different times. When collecting data, the sonar collects data while moving. After the collection at one position is completed, it is necessary to continue to move to collect sonar data at other positions of the pipeline. The sediment point cloud represents the point cloud obtained by processing the sonar data of the sediment in the pipeline. The sediment can be silt, stones and other debris, which are not limited here.

[0057] It should be noted that the sonar data of the urban underground pipe network collected by the sonar equipment in this application includes the intensity information of the cross section; then the intensity information of the cross section is converted into the information of the points stored in the Cartesian coordinate system (the specific coordinates are not limited here) to form the corresponding image, and the recorded video is obtained according to the images at different time points, that is, the real-time recorded video is generated by the real-time sonar data, and the recorded video is saved for subsequent processing; the corresponding cross-sectional image is obtained by automatically intercepting the recorded video, and the cross-sectional image is processed by image to point cloud to obtain the cross-sectional point cloud, and the cross-sectional point cloud is pre-processed and roughly extracted to obtain the cross-sectional point cloud and the pipe wall target point cloud. According to the obtained target point cloud, iteratively remove the distant points, and perform least squares fitting to obtain the circular parameters of the pipe wall contour; after removing the pipe wall point cloud from the cross-sectional point cloud, the deposition point cloud straight line parameters are extracted based on fast Euclidean clustering, iteratively remove the distant points and least squares fitting, and the result diagram is obtained by drawing and annotating according to the obtained pipe wall contour circular parameters and deposition straight line parameters. This will automatically realize the annotation of the results drawings, reduce a lot of tedious manpower and material resources, and improve the annotation efficiency.

[0058] In some optional embodiments, Figure 1 The step 102 shown includes, but is not limited to: obtaining color information and straight line information of each frame of the image in the recorded video, wherein the color information and straight line information represent the position information of the cross section.

[0059] Specifically, the cross-sectional sonar interface is always located in the lower left part of the recorded video. The region of interest of the cross-sectional sonar interface is extracted by cropping, the image is converted from the BGR color space to the HSV color space, and an appropriate HSV threshold is set. The threshold operation is combined to segment the specific color area in the image. Then, the Canny edge detection algorithm is used to extract the edges in the image after color segmentation, and the Hough transform is used to detect the straight lines in the image. After the straight lines are detected, the intersection points between the straight lines are calculated by solving the linear equations to further extract the orange grid structure under the cross-sectional sonar background. Finally, the detected image is binarized to obtain the final image.

[0060] In some optional embodiments, Figure 1 Step 103 shown includes but is not limited to: for the cross-sectional image of the urban underground pipe network, converting the pipe network data information collected by the sonar into point information represented by a vertical coordinate according to its three-channel GRB color information, thereby forming cross-sectional point cloud data representing the urban pipe network.

[0061] In some optional embodiments, Figure 1 Step 104 shown includes but is not limited to: for the cross-sectional point cloud of the urban pipe network, according to the distribution law of all points in the point cloud, preliminary denoising is performed by principal component analysis, discrete distribution, sheet distribution and other noise points in the cross-sectional point cloud are proposed, and the pipe wall target point cloud is preliminarily extracted.

[0062] In some optional embodiments, Figure 1 The step 105 shown includes but is not limited to: performing least square fitting on the pipe wall target point cloud to obtain a fitting circle; iteratively deleting farther points based on the fitting circle to obtain the pipe wall contour circle parameters, the pipe wall contour circle parameters representing the fitting circle after iteratively deleting farther points.

[0063] Specifically, for the target pipe wall point cloud that has been obtained , It includes pipe wall point cloud (point cloud representing the pipe), deposition point cloud in space (point cloud representing the deposition in the pipe) and other scattered point clouds. First, the target pipe wall point cloud is A least squares fit is performed to obtain a fitted circle. The points far from the circle are deleted when the distance from the point to the circle is greater than a threshold. Then the fit is performed iteratively and the points on the circle are retained.

[0064] In some optional embodiments, the circular parameters of the tube wall contour are obtained after iteratively deleting farther points based on the fitting circle, including: iteratively obtaining a first distance from a farther point outside the fitting circle to the fitting circle; when the first distance is greater than the first iterative distance, deleting the farther point outside the fitting circle; iteratively obtaining a second distance from a farther point inside the fitting circle to a center point, the center point representing the center of the fitting circle; when the absolute value of the difference between the second distance and the radius of the fitting circle is greater than the second iterative distance, deleting the farther point inside the fitting circle.

[0065] Specifically, based on the fitting circle, the points that are not on the fitting circle are deleted iteratively, so that the clarity of the fitting circle is continuously improved after multiple iterations, and other interference points are continuously deleted. Specifically, the farther points outside the fitting circle are continuously deleted iteratively, and the farther points inside the fitting circle are also deleted iteratively, and the points on the fitting circle are retained as much as possible to obtain the circular parameters of the pipe wall contour. Specifically, the formula includes the following:

[0066] ;

[0067] ;

[0068] ;

[0069] ;

[0070] in, represents the density of the pipe wall target point cloud, n represents the number of pipe wall target point clouds, i represents the i-th point in the pipe wall target point cloud, represents the horizontal and vertical coordinates of the i-th point, Represents the horizontal and vertical coordinates of the point closest to the i-th point, represents the center coordinates and radius of the fitted circle, Indicate point is the first distance from the farthest point outside the fitted circle to the fitted circle, Indicate point When it is a far point in the fitting circle, The second distance, represents the number of iterations, Indicates the current iteration number, e、f、 are constant parameters with different values, e Take 10, f Take 30, Take 0.6, the specific value is not limited here. The second iteration distance is: ; The first iteration distance is: The second iteration distance decreases with the increase of iteration number, and the first iteration distance increases with the increase of iteration number, that is, the convergence speed within the fitting circle is less than the convergence speed outside the fitting circle. By deleting the points within the fitting circle and converging to the fitting circle, and deleting the points outside the fitting circle and converging to the fitting circle, the circular parameters of the pipe wall contour are obtained, that is, the circular point cloud representing the pipe wall contour.

[0071] In some optional embodiments, Figure 1 Step 106 shown includes but is not limited to: removing the pipe wall target point cloud from the cross-sectional point cloud to obtain the pipe wall internal point cloud; performing fast Euclidean clustering on the pipe wall internal point cloud to obtain the deposition point cloud; performing least squares fitting on the deposition point cloud to obtain the deposition point cloud straight line parameters.

[0072] Specifically, for the cross-section point cloud , the cross-section point cloud The above includes the point cloud elimination of the circular parameters of the pipe wall. Specifically, the points on and outside the fitting circle are eliminated. The deposition point cloud is extracted from the remaining point cloud (including deposition point cloud and noise points) through fast Euclidean clustering, and then the farther points are eliminated iteratively. Then, the least squares fitting is performed to directly obtain the fitting straight line parameters of the deposition point cloud. The iterative elimination formula is as follows:

[0073] ; ;

[0074] in Indicates a farther point The third distance to the fitted line, 1 represents the density of the deposition point cloud, represents the number of iterations, 1 indicates the current iteration number, e and f is a constant parameter, e Take 10, f Take 30, the specific value is not limited here; the third iteration distance is: ; The third iteration distance decreases with the increase of the number of iterations, and the farther points whose third distance is greater than the third iteration distance are deleted, so that after multiple iterations, relatively complete straight line parameters of the deposition point cloud are obtained; the required deposition point cloud straight line parameters are obtained by least squares fitting, k represents the slope of the deposition point cloud straight line parameters, and c represents the intercept of the deposition point cloud straight line parameters; specifically, the straight line mathematical model obtained by straight line fitting the deposition point cloud is the deposition point cloud straight line parameters, the slope of the straight line mathematical model is represented by k, and the intercept is represented by c.

[0075] Figure 2 It shows the visualization of sonar data of a frame in a recorded video collected using a sonar device; Figure 3It is the cross-section point cloud data after conversion of this frame of sonar data; Figure 4 The depth result diagram of sediments such as pipeline siltation obtained after being processed by the method of the present invention can greatly improve work efficiency and reduce labor costs.

[0076] The implementation of the embodiment of the present invention includes the following beneficial effects: The embodiment of the present invention provides a method for marking the depth of sediment deposition based on sonar, including: obtaining sonar data of an urban underground pipe network, the sonar data representing data collected by a sonar device; intercepting and converting the recorded video of the sonar data to obtain a cross-sectional point cloud of the urban underground pipe network; extracting the cross-sectional point cloud to obtain a cross-sectional point cloud and a pipe wall target point cloud; performing least square fitting on the pipe wall target point cloud to obtain a pipe wall contour circular parameter; removing the pipe wall target point cloud from the cross-sectional point cloud and processing it to obtain a deposition point cloud straight line parameter; marking according to the pipe wall contour circular parameter and the deposition point cloud straight line parameter to obtain a result map. By analyzing the sonar data of the urban underground pipe network to obtain a cross-sectional point cloud, and obtaining the pipe wall contour circular parameter and the deposition point cloud straight line parameter after corresponding processing, the result map of the cross-sectional deposition depth marking is automatically drawn, which improves the marking efficiency of the urban underground pipe network and reduces the marking error.

[0077] like Figure 4 As shown, in the second aspect, an embodiment of the present invention further provides a computer device, which can be a terminal. The computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, enable the processor to execute any one of the methods for visualizing management of industrial equipment. The processor is used to provide computing and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium, which, when executed by the processor, enables the processor to execute any one of the methods for visualizing management of industrial equipment. The network interface is used for network communications, such as sending assigned tasks, etc. Those skilled in the art will appreciate that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include Figure 4More or less components shown in, or some components are combined, or there are different component arrangements. It should be understood that the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In one embodiment, the processor is used to run a computer program stored in a memory to implement the following steps: obtaining sonar data of an urban underground pipe network, wherein the sonar data represents data collected by a sonar device; performing coordinate transformation on the sonar data to obtain a cross-sectional point cloud of the urban underground pipe network; extracting the cross-sectional point cloud to obtain a cross-sectional point cloud and a pipe wall target point cloud; performing least squares fitting on the pipe wall target point cloud to obtain circular parameters of a pipe wall contour; removing the pipe wall target point cloud from the cross-sectional point cloud and processing the resultant point cloud to obtain straight line parameters of a deposition point cloud; and annotating the resultant graph according to the circular parameters of the pipe wall contour and the straight line parameters of the deposition point cloud.

[0078] It can be seen that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0079] In addition, the embodiment of the present application also discloses a computer program product or a computer program, and the computer program product or the computer program is stored in a computer-readable storage medium. The processor of the computer device can read the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device performs the above method. Similarly, the contents in the above method embodiment are all applicable to the storage medium embodiment, and the functions specifically implemented by the storage medium embodiment are the same as those in the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method embodiment.

[0080] It is understood that all or some steps and systems in the disclosed method above can be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital information processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, disk storage or other magnetic storage device, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media generally contain computer readable instructions, data structures, program modules, or other data in modulated data information such as carrier waves or other transport mechanisms, and may include any information delivery media.

[0081] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the technical field without departing from the purpose of the present invention.

Claims

1. A method for marking sediment deposition depth based on sonar, characterized in that: include: Acquire sonar data of the city's underground pipe network, wherein the sonar data represents data collected in real time by sonar equipment; generating a recorded video based on the sonar data; Automatically intercepting the recorded video to obtain a cross-sectional image of the urban underground pipe network; Converting the cross-sectional image into a point cloud to obtain a cross-sectional point cloud of the urban underground pipe network; Performing preliminary denoising on the cross-section point cloud to extract the pipe wall target point cloud; Performing least square fitting on the pipe wall target point cloud to obtain the pipe wall contour circular parameters; Eliminating the pipe wall target point cloud from the cross-section point cloud and then processing to obtain the straight line parameters of the deposition point cloud; Marking is performed according to the circular parameters of the pipe wall contour and the straight line parameters of the deposition point cloud to obtain a result graph; The automatic interception of the recorded video to obtain the cross-sectional image of the urban underground pipe network specifically includes: extracting the region of interest of the cross-sectional sonar interface by cropping, converting the image of the region of interest from the BGR color space to the HSV color space, segmenting the specific color region in the image according to the HSV threshold, extracting the edge in the image after color segmentation by the Canny edge detection algorithm, detecting the straight line in the image by the Hough transform, calculating the intersection point between the straight lines by solving the linear equation group, further extracting the orange grid structure under the cross-sectional sonar background, and binarizing the image to obtain the cross-sectional image; The least square fitting of the pipe wall target point cloud to obtain the pipe wall contour circular parameters includes: performing least square fitting on the pipe wall target point cloud to obtain a fitting circle; iteratively obtaining a first distance from a farther point outside the fitting circle to the fitting circle; when the first distance is greater than the first iterative distance, deleting the farther point outside the fitting circle; iteratively obtaining a second distance from a farther point inside the fitting circle to a center point, the center point representing the center of the fitting circle; when the absolute value of the difference between the second distance and the radius of the fitting circle is greater than the second iterative distance, deleting the farther point inside the fitting circle; including the formula: ； ； ； ； in, represents the density of the pipe wall target point cloud, n represents the number of pipe wall target point clouds, i represents the i-th point in the pipe wall target point cloud, represents the horizontal and vertical coordinates of the i-th point, Represents the horizontal and vertical coordinates of the point closest to the i-th point, represents the center coordinates and radius of the fitted circle, Indicate point is the first distance from the farthest point outside the fitted circle to the fitted circle, Indicate point When it is a far point in the fitting circle, The second distance, represents the number of iterations, Indicates the current iteration number, e、f、 A constant parameter with different values.

2. The method according to claim 1, characterized in that: The step of automatically intercepting the recorded video to obtain the cross-sectional image of the urban underground pipe network includes: Color information and straight line information of each frame of the image in the recorded video are obtained, and the color information and straight line information represent the position information of the cross section.

3. The method according to claim 1, characterized in that The step of converting the cross-sectional image into a point cloud to obtain a cross-sectional point cloud of the urban underground pipe network includes: Pixel information in the cross-sectional image is obtained and converted into a set of points representing spatial coordinates, wherein the coordinate values ​​of the points represent the spatial depth and distribution of each position in the cross-sectional image.

4. The method according to claim 1, characterized in that: The cross-section point cloud is preliminarily denoised to extract the pipe wall target point cloud, including: The principal component analysis method is used to preliminarily remove some noise points from the point cloud and extract the pipe wall target point cloud.

5. The method according to claim 1, characterized in that: The step of removing the pipe wall target point cloud from the cross-section point cloud and then processing to obtain the deposition point cloud straight line parameters includes: After removing the pipe wall target point cloud from the cross-section point cloud, an internal point cloud of the pipe wall is obtained; Performing fast Euclidean clustering on the internal point cloud of the pipe wall to obtain a deposition point cloud; The least squares fitting of the deposition point cloud is performed to obtain the deposition point cloud straight line parameters.

6. A computer device, wherein: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to perform the method according to any one of claims 1 to 5 when executed by the processor.

Images