Transmission line crossing measurement method and system based on stereo vision

Abstract

The present disclosure relates to the field of electric power technology, and discloses a method and system for measuring the crossing of transmission lines based on stereo vision. The specific scheme is as follows: according to the optical characteristics of the oxide film of the transmission lines in the overlapping crossing area of ​​the lines in the target power grid, the spectral response range of the camera and the polarization direction of the polarization filter are determined, and the camera is controlled to shoot the transmission lines in the overlapping crossing area of ​​the lines to obtain the overlapping area image of the transmission lines; according to the reflectivity and polarization characteristics of the surface oxide film of the lines, the overlapping area image of the transmission lines is segmented to obtain the target line image; based on the target line image, the three-dimensional structure point cloud data of each transmission line is determined; the three-dimensional structure point cloud data of each transmission line is fitted respectively to obtain the space curve equation of each transmission line; based on the space curve equation of each transmission line, the spacing measurement data between each transmission line is determined.

Description

Technical Field

[0001] The present disclosure relates to the field of electric power technology, and in particular to a method, system, electronic device and storage medium for measuring transmission line crossing based on stereoscopic vision. Background Art

[0002] The influence of the optical properties of the oxide film on the surface of the transmission line on stereo vision measurement is a complex technical problem. Different degrees of oxidation and oxide composition will cause significant changes in the reflectivity and polarization characteristics of the surface of the transmission line, especially in the area where the transmission lines cross and overlap. Since the optical properties of the oxide films of multiple transmission lines overlap and interfere with each other, feature extraction and recognition during stereo matching are more difficult. At the same time, the oxide film on the surface of the transmission line may also change dynamically over time, further increasing the uncertainty of optical modeling.

[0003] To address the above issues, it is necessary to conduct in-depth research on the spectral reflectivity and polarization characteristics of the oxide film on the surface of the transmission line, consider the dynamic evolution of the oxide film, and build an accurate optical model of the oxide film. On this basis, it is also necessary to optimize the spectral selectivity and polarization filter settings of the camera, and develop an image enhancement algorithm for the optical characteristics of the oxide film on the transmission line, especially to effectively enhance the image information in the cross-overlapping area of ​​the transmission line, and improve the accuracy and robustness of stereo matching. Summary of the invention

[0004] The present disclosure provides a method, system, electronic device and storage medium for measuring transmission line crossing based on stereoscopic vision, which can solve at least one of the above problems.

[0005] The present disclosure provides a transmission line crossing measurement method based on stereo vision, comprising:

[0006] Determine the spectral response range of the camera and the polarization direction of the polarization filter according to the optical properties of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines in the target power grid;

[0007] Based on the spectral response range of the camera and the polarization direction of the polarization filter, the camera is controlled to shoot the transmission lines in the line overlapping and crossing area to obtain an image of the transmission line overlapping area;

[0008] Segmenting the transmission line overlap region image according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapped intersection region to obtain a target line image;

[0009] Based on the target line image, determining the three-dimensional structure point cloud data of each of the transmission lines;

[0010] Fitting the three-dimensional structure point cloud data to obtain the spatial curve equation of each of the transmission lines;

[0011] Based on the space curve equations of the transmission lines, the spacing measurement data between the transmission lines are determined.

[0012] According to another aspect of the present disclosure, a transmission line crossing measurement system based on stereo vision is provided, comprising:

[0013] A camera parameter determination module, used to determine the spectral response range of the camera and the polarization direction of the polarization filter according to the optical characteristics of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines in the target power grid;

[0014] A camera control module, used for controlling the camera to shoot the transmission lines in the overlapping and crossing area of ​​the lines based on the spectral response range of the camera and the polarization direction of the polarization filter, so as to obtain an image of the overlapping area of ​​the transmission lines;

[0015] A target image acquisition module, used to segment the transmission line overlap area image according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapped intersection area to obtain a target line image;

[0016] A point cloud data determination module, used to determine the three-dimensional structure point cloud data of each of the transmission lines based on the target line image;

[0017] A curve fitting module, used for fitting the three-dimensional structure point cloud data to obtain the spatial curve equation of each transmission line;

[0018] The line spacing measurement module is used to determine the spacing measurement data between each of the transmission lines based on the space curve equation of each of the transmission lines.

[0019] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any of the transmission line crossing measurement methods based on stereo vision in the embodiments of the present disclosure.

[0023] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any of the transmission line crossing measurement methods based on stereo vision in the embodiments of the present disclosure.

[0024] By adopting the technical solution disclosed in the present invention, the spectral response range of the camera and the polarization direction of the polarization filter are determined according to the optical characteristics of the oxide film of the transmission line in the line overlapping and crossing area in the target power grid, and based on the spectral response range of the camera and the polarization direction of the polarization filter, the camera is controlled to shoot the transmission line in the line overlapping and crossing area to obtain the transmission line overlapping area image. In this way, the spectral selectivity and polarization filter setting of the camera can be optimized, and the shooting accuracy of the transmission line overlapping area image can be improved.

[0025] Furthermore, according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapping intersection area, the image of the overlapping area of ​​the transmission lines is segmented to obtain the target line image; from the target line image, the three-dimensional structure point cloud data of each of the transmission lines is extracted; the three-dimensional structure point cloud data is fitted to obtain the space curve equation of each of the transmission lines; based on the space curve equation of each of the transmission lines, the spacing measurement data between each of the transmission lines is determined. In this way, the reflectivity and polarization characteristics of the surface oxide film of the transmission line are used to extract the point cloud data of each transmission line from the image, improve the accuracy of the fitting curve, and thus, when measuring the spacing of each curve, the measurement accuracy of the transmission line can be further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a flow chart of a transmission line crossing measurement method based on stereoscopic vision according to an embodiment of the present disclosure;

[0027] Figure 2 is a structural block diagram of a transmission line crossing measurement system based on stereo vision according to an embodiment of the present disclosure;

[0028] Figure 3 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0030] Figure 1 It is a flow chart of a transmission line crossing measurement method based on stereo vision according to an embodiment of the present disclosure.

[0031] like Figure 1 As shown, the control method includes:

[0032] S110, determining a spectral response range of a camera and a polarization direction of a polarization filter according to optical properties of oxide films of transmission lines in a line overlap intersection region in a target power grid;

[0033] S120, based on the spectral response range of the camera and the polarization direction of the polarization filter, controlling the camera to photograph the transmission lines in the line overlapping and crossing area to obtain an image of the transmission line overlapping area;

[0034] S130, segmenting the transmission line overlap region image according to the reflectivity and polarization characteristics of the surface oxide film of each transmission line in the overlapped intersection region to obtain a target line image;

[0035] S140, determining three-dimensional structural point cloud data of each transmission line based on the target line image;

[0036] S150, fitting the three-dimensional structure point cloud data of each transmission line respectively to obtain the space curve equation of each transmission line;

[0037] S160, determining the spacing measurement data between the transmission lines based on the space curve equations of the transmission lines.

[0038] Exemplarily, the target power grid includes multiple transmission lines, which are parallel to each other in some areas and overlap and cross in some areas. The overlapping and crossing of lines can be understood as taking an image of the transmission lines in the area, in which the transmission lines in the image have overlapping lines and / or crossed lines.

[0039] Exemplarily, the oxide film optical properties may include oxide film thickness, reflectivity, polarization properties, etc. For example, a scanning electron microscope and an energy spectrometer may be used to analyze the oxide film composition and thickness of a transmission line. For example, a spectroscopic reflectometer may be used to measure the reflectivity and polarization properties of a transmission line.

[0040] Exemplarily, based on the optical properties of the oxide film of the transmission lines in the overlapping and crossing areas of the lines in the target power grid and the various optional spectral ranges of the camera, the optional spectral range that is most sensitive to changes in the optical properties of the oxide film of the transmission lines is determined, and the optional spectral range is used as the spectral response range of the camera.

[0041] Exemplarily, based on the optical properties of the oxide film of the power line and the various optional polarization directions of the polarization filter in the camera, the optional polarization direction that is most sensitive to changes in the optical properties of the oxide film of the power line is determined, and the optional polarization direction is used as the polarization direction of the polarization filter in the camera.

[0042] Exemplarily, based on the spectral response range of the camera and the polarization direction of the polarization filter, the camera parameters are set respectively, and the camera is controlled to shoot the transmission lines in the overlapping and crossing area of ​​the lines to obtain a first image and a second image, and the first image and the second image are fused to obtain an image of the overlapping area of ​​the transmission lines.

[0043] Exemplarily, based on the spectral response range of the camera and the polarization direction of the polarization filter, the camera parameters are set at the same time, and the camera is controlled to shoot the transmission lines in the overlapping and crossing area of ​​the lines to obtain the image of the overlapping area of ​​the transmission lines.

[0044] Exemplarily, the image features of each transmission line in the target line image are matched with the point cloud data corresponding to the overlapping and crossing area of ​​the lines, and the three-dimensional structure point cloud data of the transmission line corresponding to the point cloud data that meets the matching conditions is obtained. Each point in the point cloud data corresponds to a set of position vectors and reflection intensity information.

[0045] Exemplarily, if point cloud data is fused into the target line image, the three-dimensional structure point cloud data of each transmission line can be extracted from the target line image.

[0046] Exemplarily, the least square method may be used to fit the three-dimensional structural point cloud data of each transmission line respectively to obtain the spatial curve equation of each transmission line.

[0047] Exemplarily, a piecewise cubic spline interpolation method may be used to fit the three-dimensional structural point cloud data of each transmission line respectively to obtain the spatial curve equation of each transmission line.

[0048] For example, the spacing measurement data may include the minimum spacing between any two transmission lines, the distance between any two points on two lines, and the like.

[0049] According to the above embodiment, the spectral response range of the camera and the polarization direction of the polarization filter are determined according to the optical characteristics of the oxide film of the transmission line in the line overlapping intersection area in the target power grid, and based on the spectral response range of the camera and the polarization direction of the polarization filter, the camera is controlled to shoot the transmission line in the line overlapping intersection area to obtain the transmission line overlapping area image. In this way, the spectral selectivity and polarization filter setting of the camera can be optimized, so as to improve the shooting accuracy of the transmission line overlapping area image.

[0050] Furthermore, according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapping intersection area, the image of the overlapping area of ​​the transmission lines is segmented to obtain the target line image; from the target line image, the three-dimensional structure point cloud data of each of the transmission lines is extracted; the three-dimensional structure point cloud data is fitted to obtain the space curve equation of each of the transmission lines; based on the space curve equation of each of the transmission lines, the spacing measurement data between each of the transmission lines is determined. In this way, the reflectivity and polarization characteristics of the surface oxide film of the transmission line are used to extract the point cloud data of each transmission line from the image, improve the accuracy of the fitting curve, and thus, when measuring the spacing of each curve, the measurement accuracy of the transmission line can be further improved.

[0051] In one embodiment, determining the spectral response range of the camera and the polarization direction of the polarization filter according to the optical properties of the oxide film of the transmission line in the line overlap intersection area in the target power grid includes:

[0052] Dividing a preset spectral range into a plurality of sub-spectral intervals;

[0053] Determine the response intensity of the camera in each sub-spectral region as the optimization variable in the fitness function, and determine the sensitivity of the change of the optical characteristics of the oxide film of the transmission line in the line overlap intersection region as the dependent variable of the fitness function;

[0054] A genetic algorithm is used to optimize the optimization variables with the goal of maximizing the dependent variable of the fitness function, and the target sub-spectral region is obtained, and the target sub-spectral region is used as the spectral response range of the camera;

[0055] A simulated annealing algorithm is used to simulate the sensitivity of the polarization direction of the polarization filter to the changes in the optical properties of the oxide film of the transmission line in the line overlapping and crossing area, so as to obtain the polarization direction of the polarization filter with the highest sensitivity to the changes in the optical properties of the oxide film of the transmission line in the line overlapping and crossing area.

[0056] Exemplarily, the preset spectral range may be 400-800 nm, which may be divided into 20 sub-intervals, and the width of each sub-interval is 20 nm.

[0057] Exemplarily, each individual in the genetic algorithm population contains 20 floating point numbers between 0 and 1, which represent the response intensity of each sub-interval. Each individual corresponds to a sub-interval. During crossover mutation, the crossover probability is set to 0.8, and a single-point crossover mutation method is adopted. Alternatively, the mutation probability is set to 0.1, and a Gaussian mutation mutation method is adopted. Specifically, the above-mentioned fitness function can be used to calculate the fitness of each individual. If the fitness does not meet the set requirements, the population is mutated. If the fitness meets the set requirements, the sub-interval corresponding to the individual with the largest fitness is selected in the population as the target sub-spectral region.

[0058] For example, in the simulated annealing algorithm, the initial temperature may be set to 100, and the temperature may be multiplied by 0.95 for each iteration. After 500 iterations, the optimal polarization angle may be obtained. For example, the combination of the optimal polarization angles is 22° and 112°.

[0059] For example, 10,000 oxide film samples were generated, with a mean thickness of 500 nm and a standard deviation of 50 nm; a mean metal oxide content of 60% and a standard deviation of 5%. A sensitivity analysis was performed on the optimized parameters, and it was calculated that the sensitivity of the 520-540 nm band to the oxide film thickness was 0.85, and the sensitivity of the 680-700 nm band to the metal oxide content was 0.78.

[0060] According to the above implementation, based on the optical properties of the oxide film of the transmission lines in the overlapping and crossing area of ​​the target power grid, the spectral response range of the camera with the highest response sensitivity and the polarization direction of the polarization filter can be accurately determined.

[0061] In one embodiment, based on the spectral response range of the camera and the polarization direction of the polarization filter, the camera is controlled to photograph the transmission lines in the line overlapping intersection area to obtain the transmission line overlapping area image, including: based on the spectral response range of the camera, a corresponding spectral filter is set in the camera, and the camera with the spectral filter set is used to photograph the transmission lines in the line overlapping intersection area to obtain a first image; based on the polarization direction of the polarization filter of the camera, a corresponding polarization filter is set in the camera, and the camera with the polarization filter set is used to photograph the transmission lines in the line overlapping intersection area to obtain a second image; three-dimensional point cloud data of the transmission lines in the line overlapping intersection area is obtained; the three-dimensional point cloud data, the first image and the second image are synthesized to obtain the transmission line overlapping area image.

[0062] For example, the image features of each transmission line in the fused image of the first image and the second image can be used to match the three-dimensional point cloud data corresponding to the overlapping and crossing areas of the lines to obtain the three-dimensional point cloud data of each transmission line. For example, the point cloud data that meets the requirements of matching degree is used as the three-dimensional point cloud data of the corresponding transmission line.

[0063] Exemplarily, the spectrum, polarization and three-dimensional coordinate information of a point with the highest fit in the three-dimensional point cloud data, the first image and the second image are associated to generate a corresponding transmission line overlap area image.

[0064] According to the above-mentioned embodiment, an image of the overlapping area of ​​the transmission line having spectral information, polarization information and three-dimensional coordinate information can be obtained.

[0065] In one embodiment, the transmission line overlap area image is segmented according to the reflectivity and polarization characteristics of the surface oxide film of each transmission line in the overlapping intersection area to obtain a target line image, including: determining a characteristic spectrum according to the reflectivity and polarization characteristics of the surface oxide film of each transmission line in the overlapping intersection area, wherein the characteristic spectrum includes a first curve of reflectivity varying with wavelength and a second curve of polarization characteristics varying with incident angle; based on the first curve and the second curve in the characteristic spectrum and the pixel characteristics of each pixel in the transmission line overlap area image, calculating the fit of the characteristic spectrum with each pixel in the transmission line overlap area image to obtain a fit image; using a regional growing algorithm, extracting the pixel with the highest fit in the fit image as an initial seed point to start regional growth, until the growth rate of the region is less than a preset threshold, and stopping the growth, and taking the region as the target line image; wherein the regional growing includes extracting the pixel with the highest fit in the fit image as a growth seed point, and deleting the pixel with the highest fit in the fit image.

[0066] Exemplarily, the theoretical reflectivity, polarization degree and polarization angle at different positions of the overlapping intersection area are calculated to obtain a characteristic spectrum including a curve of reflectivity varying with wavelength and a curve of polarization degree and polarization angle varying with incident angle.

[0067] Exemplarily, the degree of fit between the first curve and the pixel feature of the pixel point is calculated, and the degree of fit between the second curve and the pixel feature of the pixel point is calculated, and the two degrees of fit are summed and averaged to obtain the degree of fit between the spectrum and the pixel point.

[0068] It can be understood that when the pixel point with the highest degree of fit is extracted from the degree of fit image as the initial seed point to start region growing, the pixel point is deleted from the degree of fit image.

[0069] Exemplarily, in the region growing algorithm, pixels with a fitting degree greater than 0.95 are selected as initial seed points, the growth threshold is set to 0.9, and the growth is stopped when the region growth rate is less than 1%.

[0070] According to the above-mentioned implementation mode, a characteristic map is constructed based on the reflectivity and polarization characteristics of the surface oxide film of each transmission line in the overlapping intersection area, and a fitting image is obtained by using the fitting degree of the characteristic map and each pixel point. The image is segmented using the fitting degree of each pixel point in the fitting image, and the target line image can be accurately segmented.

[0071] In one embodiment, three-dimensional structure point cloud data are fitted to obtain space curve equations of each transmission line, including: preliminary fitting of the three-dimensional structure point cloud data to obtain the main direction of each transmission line; projecting the point cloud data corresponding to each transmission line in the three-dimensional structure point cloud data onto the main direction of each transmission line to obtain the projection point cloud data corresponding to each transmission line; using a piecewise cubic spline interpolation method to curve fit the projection point cloud data corresponding to each transmission line to obtain the space curve equation of each transmission line.

[0072] Exemplarily, outlier points are removed from the three-dimensional structure point cloud data. For example, a local outlier factor algorithm may be used to calculate outlier point clouds in the three-dimensional structure point cloud data, and the outlier point clouds are removed as outliers.

[0073] For example, the RANSAC algorithm can be used to fit the point cloud data to obtain the main direction of each transmission line. The number of iterations and the inlier threshold can be set in the RANSAC algorithm. For example, the number of iterations is 1000 and the inlier threshold is 0.1 meters.

[0074] Exemplarily, for the fitted spatial curve equation, if the average distance error between the curve corresponding to the equation and the original point cloud data is greater than a preset error, the process returns to refitting until the error is less than the preset error, then the refitting is stopped and the last fitted spatial curve equation is output.

[0075] According to the above implementation, the control curve equation of each transmission line can be accurately fitted.

[0076] In one embodiment, determining the spacing measurement data between each transmission line based on the space curve equation of each transmission line includes at least one of the following:

[0077] For any two first transmission lines and second transmission lines, N points are taken in different height ranges, and the distance between each point in the first transmission line and the closest point in the second transmission line in the same height range is calculated, where N is a positive integer;

[0078] For the first transmission line and the second transmission line, M points are taken in each different tension area, and the distance between each point in the first transmission line and the nearest point in the second transmission line in the same tension area is calculated, where M is a positive integer.

[0079] For example, N can be set to 10, and M can be set to 15.

[0080] It can be understood that the first transmission line and the second transmission line are any two different transmission lines in the line overlap and intersection area, or are any two different overlapping or intersecting transmission lines in the line overlap and intersection area.

[0081] Exemplarily, the above-mentioned distance measurement data determination process may further include: for any first transmission line and second transmission line, determining the shortest distance between the first transmission line and the second transmission line.

[0082] According to the above embodiment, based on the space curve equation of each transmission line, a plurality of different distance measurement data between each transmission line are obtained.

[0083] Figure 2 It is a structural block diagram of a transmission line crossing measurement system based on stereo vision according to an embodiment of the present disclosure.

[0084] like Figure 2 As shown, the transmission line crossing measurement system based on stereo vision includes:

[0085] A camera parameter determination module 210, for determining a spectral response range of a camera and a polarization direction of a polarization filter according to the optical characteristics of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines in the target power grid;

[0086] A camera control module 220, for controlling the camera to photograph the power transmission lines in the line overlapping and crossing area based on the spectral response range of the camera and the polarization direction of the polarization filter, so as to obtain an image of the power transmission line overlapping area;

[0087] The target image acquisition module 230 is used to segment the transmission line overlap area image according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapped intersection area to obtain a target line image;

[0088] A point cloud data determination module 240, configured to determine the three-dimensional structure point cloud data of each of the transmission lines based on the target line image;

[0089] A curve fitting module 250 is used to fit the three-dimensional structure point cloud data to obtain the spatial curve equation of each transmission line;

[0090] The line spacing measurement module 260 is used to determine the spacing measurement data between each of the transmission lines based on the space curve equation of each of the transmission lines.

[0091] In one implementation, the camera parameter determination module 210 includes:

[0092] A spectral interval division unit, used for dividing a preset spectral range into a plurality of sub-spectral intervals;

[0093] A fitness function determination unit, used to determine the response intensity of the camera in each of the sub-spectral regions as an optimization variable in the fitness function, and to determine the sensitivity of the change of the optical characteristics of the oxide film of the transmission line in the line overlap intersection region as a dependent variable of the fitness function;

[0094] A spectral response range determination unit, configured to use a genetic algorithm to optimize the optimization variable with the goal of maximizing the dependent variable of the fitness function, to obtain a target sub-spectral region, and to use the target sub-spectral region as the spectral response range of the camera;

[0095] The polarization direction determining unit is used to simulate the sensitivity change of the polarization direction of the polarization filter to the change of the optical characteristics of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines by using a simulated annealing algorithm, so as to obtain the polarization direction of the polarization filter with the highest sensitivity to the change of the optical characteristics of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines.

[0096] In one implementation, the camera control module 220 includes:

[0097] A first image generating unit is used to set a corresponding spectral filter in the camera based on the spectral response range of the camera, and use the camera with the spectral filter set to shoot the power transmission line in the line overlapping and crossing area to obtain a first image;

[0098] A second image generating unit is used to set a corresponding polarization filter in the camera based on the polarization direction of the polarization filter of the camera, and use the camera with the polarization filter set to shoot the power transmission line in the line overlapping and crossing area to obtain a second image;

[0099] A point cloud data acquisition unit, used to acquire three-dimensional point cloud data of the power transmission line in the overlapping and crossing area of ​​the lines;

[0100] A data synthesis unit is used to synthesize the three-dimensional point cloud data, the first image and the second image to obtain the transmission line overlapping area image.

[0101] In one implementation, the target image acquisition module 230 includes:

[0102] A characteristic spectrum determination unit, configured to determine a characteristic spectrum according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapping intersection area, wherein the characteristic spectrum includes a first curve of reflectivity varying with wavelength and a second curve of polarization characteristics varying with incident angle;

[0103] A fitting image generating unit, configured to calculate the fitting degree of the feature map and each pixel point in the transmission line overlap area image based on the first curve and the second curve in the feature map and the pixel features of each pixel point in the transmission line overlap area image, so as to obtain a fitting image;

[0104] The target image generating unit is used for adopting a region growing algorithm, extracting the pixel point with the highest degree of fit in the fit image as an initial seed point to start region growing, and stopping the growth when the growth rate of the region is less than a preset threshold, and taking the region as a target line image; wherein, the region growing includes extracting the pixel point with the highest degree of fit in the fit image as a growth seed point, and deleting the pixel point with the highest degree of fit in the fit image.

[0105] In one implementation, the curve fitting module 250 includes:

[0106] A main direction determination unit, used to perform preliminary direction fitting on the three-dimensional structure point cloud data of each of the transmission lines to obtain the main direction of each of the transmission lines;

[0107] A projection unit, used to project the three-dimensional structure point cloud data of each of the transmission lines onto the main direction of each of the transmission lines, to obtain projection point cloud data corresponding to each of the transmission lines;

[0108] The curve fitting unit is used to adopt a piecewise cubic spline interpolation method to perform curve fitting on the projection point cloud data corresponding to each of the transmission lines to obtain a spatial curve equation of each of the transmission lines.

[0109] In one implementation, the point cloud data determination module 240 includes:

[0110] A first distance measurement unit, for any two first transmission lines and second transmission lines, respectively taking N points in different height ranges, and calculating the distance between each point in the first transmission line and the closest point in the second transmission line in the same height range, where N is a positive integer;

[0111] The second distance measurement unit is used to select M points in different tension areas for the first transmission line and the second transmission line, and calculate the distance between each point in the first transmission line and the nearest point in the same tension area of ​​the second transmission line, where M is a positive integer.

[0112] According to an embodiment of the present disclosure, the above method of the present disclosure may be applied to an electronic device and a readable storage medium.

[0113] Figure 3 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0114] like Figure 3 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0115] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0116] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a transmission line crossing span measurement method based on stereoscopic vision. For example, in some embodiments, a transmission line crossing span measurement method based on stereoscopic vision may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of a transmission line crossing span measurement method based on stereoscopic vision described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured in any other appropriate manner (eg, by means of firmware) to execute a transmission line crossing measurement method based on stereo vision.

[0117] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0119] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0121] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0122] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0123] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0124] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A transmission line crossing measurement method based on stereo vision, characterized in that: include: Determine the spectral response range of the camera and the polarization direction of the polarization filter according to the optical properties of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines in the target power grid; Based on the spectral response range of the camera and the polarization direction of the polarization filter, the camera is controlled to shoot the transmission lines in the line overlapping and crossing area to obtain an image of the transmission line overlapping area; Segmenting the transmission line overlap region image according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapped intersection region to obtain a target line image; Based on the target line image, determining the three-dimensional structure point cloud data of each of the transmission lines; Fitting the three-dimensional structure point cloud data of each of the transmission lines respectively to obtain the spatial curve equation of each of the transmission lines; Based on the space curve equations of the transmission lines, the spacing measurement data between the transmission lines are determined.

2. The method according to claim 1, characterized in that: The step of determining the spectral response range of the camera and the polarization direction of the polarization filter according to the optical characteristics of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines in the target power grid comprises: Dividing a preset spectral range into a plurality of sub-spectral intervals; Determine the response intensity of the camera in each of the sub-spectral regions as an optimization variable in a fitness function, and determine the sensitivity of the change in the optical characteristics of the oxide film of the transmission line in the line overlap intersection region as a dependent variable of the fitness function; Using a genetic algorithm, the optimization variable is optimized with the goal of maximizing the dependent variable of the fitness function, a target sub-spectral region is obtained, and the target sub-spectral region is used as the spectral response range of the camera; A simulated annealing algorithm is used to simulate the sensitivity change of the polarization direction of the polarization filter to the change of the optical properties of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines, so as to obtain the polarization direction of the polarization filter with the highest sensitivity to the change of the optical properties of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines.

3. The method according to claim 1, characterized in that The method of controlling the camera to photograph the power transmission lines in the line overlapping and crossing area based on the spectral response range of the camera and the polarization direction of the polarization filter to obtain the transmission line overlapping area image includes: Based on the spectral response range of the camera, a corresponding spectral filter is set in the camera, and the camera with the spectral filter set is used to shoot the power transmission line in the line overlapping and crossing area to obtain a first image; Based on the polarization direction of the polarization filter of the camera, a corresponding polarization filter is set in the camera, and the camera with the polarization filter set is used to shoot the power transmission line in the line overlapping and crossing area to obtain a second image; Acquire three-dimensional point cloud data of the power transmission lines in the overlapping and crossing area of ​​the lines; The three-dimensional point cloud data, the first image and the second image are synthesized to obtain the transmission line overlapping area image.

4. The method according to claim 1, characterized in that: The method of segmenting the transmission line overlap region image according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapped intersection region to obtain the target line image comprises: Determine a characteristic spectrum according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapping intersection area, wherein the characteristic spectrum includes a first curve of reflectivity varying with wavelength and a second curve of polarization characteristics varying with incident angle; Based on the first curve and the second curve in the feature map and the pixel features of each pixel in the transmission line overlap area image, calculate the degree of fit between the feature map and each pixel in the transmission line overlap area image to obtain a degree of fit image; A region growing algorithm is adopted to extract the pixel point with the highest degree of fit in the fit image as the initial seed point to start region growing, and the growth is stopped when the growth rate of the region is less than a preset threshold, and the region is used as the target line image; wherein, the region growing includes extracting the pixel point with the highest degree of fit in the fit image as the growth seed point, and deleting the pixel point with the highest degree of fit in the fit image.

5. The method according to claim 1, characterized in that The three-dimensional structure point cloud data of each of the transmission lines are fitted respectively to obtain the space curve equation of each of the transmission lines, including: Performing preliminary direction fitting on the three-dimensional structure point cloud data of each of the transmission lines to obtain the main direction of each of the transmission lines; Projecting the three-dimensional structure point cloud data of each of the transmission lines onto the main direction of each of the transmission lines to obtain projection point cloud data corresponding to each of the transmission lines; The piecewise cubic spline interpolation method is adopted to perform curve fitting on the projection point cloud data corresponding to each of the transmission lines to obtain the spatial curve equation of each of the transmission lines.

6. The method according to claim 1, characterized in that Determining the spacing measurement data between each of the transmission lines based on the space curve equation of each of the transmission lines comprises at least one of the following: For any two first transmission lines and second transmission lines, N points are respectively selected in different height ranges, and the distance between each point in the first transmission line and the closest point in the second transmission line in the same height range is calculated, where N is a positive integer; For the first transmission line and the second transmission line, M points are respectively selected in different tension areas, and the distance between each point in the first transmission line and the nearest point in the second transmission line in the same tension area is calculated, where M is a positive integer.

7. A transmission line crossing measurement system based on stereo vision, characterized in that: include: A camera parameter determination module, used to determine the spectral response range of the camera and the polarization direction of the polarization filter according to the optical characteristics of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines in the target power grid; A camera control module, used for controlling the camera to shoot the transmission lines in the overlapping and crossing area of ​​the lines based on the spectral response range of the camera and the polarization direction of the polarization filter, so as to obtain an image of the overlapping area of ​​the transmission lines; A target image acquisition module, used to segment the transmission line overlap area image according to the reflectivity and polarization characteristics of the surface oxide film of each of the transmission lines in the overlapped intersection area to obtain a target line image; A point cloud data determination module, used to determine the three-dimensional structure point cloud data of each of the transmission lines based on the target line image; A curve fitting module, used to fit the three-dimensional structure point cloud data of each of the transmission lines respectively to obtain the spatial curve equation of each of the transmission lines; The line spacing measurement module is used to determine the spacing measurement data between each of the transmission lines based on the space curve equation of each of the transmission lines.

8. The system according to claim 7, characterized in that The camera parameter determination module comprises: A spectral interval division unit, used for dividing a preset spectral range into a plurality of sub-spectral intervals; A fitness function determination unit, used to determine the response intensity of the camera in each of the sub-spectral regions as an optimization variable in the fitness function, and to determine the sensitivity of the change of the optical characteristics of the oxide film of the transmission line in the line overlap intersection region as a dependent variable of the fitness function; A spectral response range determination unit, configured to use a genetic algorithm to optimize the optimization variable with the goal of maximizing the dependent variable of the fitness function, to obtain a target sub-spectral region, and to use the target sub-spectral region as the spectral response range of the camera; The polarization direction determining unit is used to simulate the sensitivity change of the polarization direction of the polarization filter to the change of the optical characteristics of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines by using a simulated annealing algorithm, so as to obtain the polarization direction of the polarization filter with the highest sensitivity to the change of the optical characteristics of the oxide film of the transmission line in the overlapping and crossing area of ​​the lines.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

Images