Intelligent detection method, system and equipment for mounting angle of cross arm of corner rod and medium

Abstract

The invention discloses an intelligent detection method, system and device for the installation angle of a cross arm of a corner rod, and a medium. The method comprises the following steps: constructing a strain clamp rectangular frame corresponding to each strain clamp contour point set; constructing a first line coordinate point set, and constructing a second line coordinate point set; screening out at least one first target line straight line and at least one second target line straight line according to the first line coordinate point set, the second line coordinate point set and the strain clamp rectangular frame; calculating a first included angle between the first target line straight line and the X-axis positive direction, and calculating a second included angle between the second target line straight line and the X-axis positive direction; calculating a third included angle between the central axis direction of the cross arm and the positive direction of the X axis; and performing difference calculation on the first included angle and the second included angle and the third included angle to obtain two difference calculation results, and performing intelligent detection on the mounting angle of the cross arm of the corner rod according to the two difference calculation results. The intelligent detection accuracy and detection efficiency of the mounting angle of the cross arm of the corner rod can be improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an intelligent detection method, system, device and medium for the installation angle of a corner bar crossarm. Background Technology

[0002] In the construction and operation and maintenance of power lines, the installation angle of the crossarm of angle towers directly affects the mechanical stress balance and long-term operational safety of the line. According to the "Code for Construction and Acceptance of Electrical Installations for 66kV and Below Overhead Power Lines GB50173-2014", the crossarm of the angle tower must be strictly installed on the bisector of the angle in the direction of the line's turn. If the installation angle does not meet the standard, it will lead to uneven conductor tension distribution, accelerated wear of hardware, and in severe cases, may even cause tower collapse.

[0003] Currently, the main methods for detecting the installation angle of crossarms include manual measurement and image analysis. Manual measurement uses a theodolite or total station to measure point by point, which is complex, relies heavily on the experience of technicians, and has low efficiency. Image analysis involves manually taking photos at fixed locations and then annotating the angles using protractor software; however, the measurement results are greatly affected by the shooting angle and the operator's experience, resulting in poor repeatability. Furthermore, both methods require manual inspection of each crossarm, leading to low efficiency. In complex terrain or when observation locations are limited, it is often difficult to obtain effective data, thus making it difficult to obtain accurate detection results. Summary of the Invention

[0004] This application aims to propose an intelligent detection method, system, device, and medium for the installation angle of corner bar crossarms, which can improve the accuracy and efficiency of intelligent detection of the installation angle of corner bar crossarms.

[0005] In a first aspect, embodiments of this application provide an intelligent detection method for the installation angle of a corner bar crossarm, the method comprising: The collected corner bar image sample data is segmented to obtain the crossarm contour point set and multiple tension clamp contour point sets; Based on the multiple sets of tension clamp contour points, construct a tension clamp rectangle corresponding to each set of tension clamp contour points. Construct a polygonal region enclosed by multiple tension clamps, and construct a first set of line coordinate points based on the starting point coordinates and ending point coordinates of each straight line on the power transmission side of the polygonal region; and construct a second set of line coordinate points based on the starting point coordinates and ending point coordinates of each straight line on the power receiving side of the polygonal region. Based on the first set of line coordinate points, the second set of line coordinate points, and the tension clamp rectangle, at least one first target line straight line and one second target line straight line are selected. Based on at least one first target line and one second target line, calculate the first angle between the first target line and the positive X-axis, and calculate the second angle between the second target line and the positive X-axis. Based on the crossarm profile point set, calculate the third angle between the crossarm centerline direction and the positive X-axis direction; The first included angle and the second included angle are respectively compared with the third included angle to obtain two difference calculation results. The installation angle of the corner bar crossarm is intelligently detected based on the two difference calculation results.

[0006] Compared with the prior art, the first aspect of this application has the following beneficial effects: This method segmentes the collected corner pole image sample data to obtain a crossarm contour point set and multiple tension clamp contour point sets. Based on these multiple tension clamp contour point sets, a rectangular frame corresponding to each tension clamp contour point set is constructed. A polygonal region enclosed by the multiple tension clamps is constructed, and a first set of line coordinate points is constructed based on the start and end coordinates of each straight line on the power transmission side of the polygonal region. A second set of line coordinate points is also constructed based on the start and end coordinates of each straight line on the power receiving side of the polygonal region. The method then uses the first and second set of line coordinate points... Using a set of points and a rectangular frame for tension clamps, at least one first target line and one second target line are selected. Based on these two lines, the first angle between the first target line and the positive X-axis is calculated, and the second angle between the second target line and the positive X-axis is also calculated. Based on the crossarm profile point set, the third angle between the crossarm's central axis and the positive X-axis is calculated. The differences between the first and second angles and the third angle are calculated to obtain two difference results. Based on these two difference results, the installation angle of the corner crossarm is intelligently detected. Thus, by collecting corner crossarm image sample data and performing a series of subsequent calculations, the installation angle of the corner crossarm is intelligently detected based on the calculated first, second, and third angles. This eliminates the need for total station measurements or manual angle measurement, is unaffected by complex terrain or observation locations, and does not rely on the experience of technical personnel, thereby improving the accuracy and efficiency of intelligent detection of the corner crossarm installation angle.

[0007] In some embodiments, the step of selecting at least one first target straight line and one second target straight line based on the first set of line coordinate points, the second set of line coordinate points, and the tension clamp rectangle includes: Based on the coordinate points in the first set of coordinate points, construct the equation of the first straight line. Based on the coordinate points in the second set of coordinate points, construct the equation of the second straight line; Based on the equation of the first line, determine multiple first coordinate points for each line corresponding to the first set of coordinate points; Based on the equation of the second line, determine multiple second coordinate points for each line corresponding to the set of coordinate points of the second line; If any of the plurality of first coordinate points is within the rectangular frame of the tension clamp, then the straight line corresponding to the first coordinate point within the rectangular frame of the tension clamp is taken as the first target straight line, and at least one first target straight line is obtained. If any of the plurality of second coordinate points is located within the rectangular frame of the tension clamp, then the straight line corresponding to the second coordinate point within the rectangular frame of the tension clamp is taken as the second target straight line, thus obtaining at least one second target straight line.

[0008] In some embodiments, calculating the third angle between the crossarm's central axis direction and the positive X-axis direction based on the crossarm profile point set includes: Calculate the centroid of the crossarm based on the set of points on the crossarm profile; The data of each contour point in the crossarm contour point set is digitized to obtain a centered matrix; Based on the centralization matrix, calculate the principal axis direction vector and use the principal axis direction vector as the crossarm centerline direction vector; Calculate the third angle between the direction vector of the crossarm's central axis and the positive X-axis direction.

[0009] In some implementations, calculating the principal axis direction vector based on the centralization matrix includes: Construct the covariance matrix based on the centralization matrix; Calculate the eigenvalues ​​in the covariance matrix to obtain all eigenvalues; Select the largest eigenvalue from all the eigenvalues, calculate the target eigenvector, and use the target eigenvector as the principal axis direction vector.

[0010] In some implementations, selecting the largest eigenvalue from all eigenvalues ​​and calculating the target eigenvector includes: ; ; in, Represents the covariance matrix. Represents the largest eigenvalue. Represents the identity matrix. This represents the target feature vector.

[0011] In some embodiments, calculating a first angle between the first target line and the positive X-axis, and calculating a second angle between the second target line and the positive X-axis, based on at least one first target line and one second target line, includes: Obtain a first number of straight lines on the first target route, and obtain a second number of straight lines on the second target route; The sum of the angles between each of the first target line lines and the positive X-axis is obtained to obtain the total sum of the first angles; The sum of the angles between each of the second target line lines and the positive X-axis is obtained to obtain the total sum of the second angles; Divide the sum of the first included angles by the first quantity to obtain the first included angle between the first target line and the positive direction of the X-axis. Divide the sum of the second included angles by the second quantity to obtain the second included angle between the second target line and the positive direction of the X-axis.

[0012] In some implementations, the intelligent detection of the angle bar crossarm installation angle based on the calculation results of the two differences includes: The absolute value of the difference between the two difference calculation results is calculated. If the absolute value of the difference is less than the preset value, it indicates that the crossarm installation angle is detected by the intelligent detection of the crossarm installation angle of the corner bar.

[0013] Secondly, embodiments of this application also provide an intelligent detection system for the installation angle of an angle bar crossarm, the system comprising: The instance segmentation unit is used to segment the collected corner pole image sample data into instances to obtain the crossarm contour point set and multiple tension clamp contour point sets. The first construction unit is used to construct a tension clamp rectangle corresponding to each tension clamp contour point set based on the plurality of tension clamp contour point sets. The second construction unit is used to construct a polygonal region enclosed by multiple tension clamps, and to construct a first set of line coordinate points based on the starting point coordinates and ending point coordinates of each line straight line on the power transmission side of the polygonal region, and to construct a second set of line coordinate points based on the starting point coordinates and ending point coordinates of each line straight line on the power receiving side of the polygonal region. The straight line filtering unit is used to filter out at least one first target line straight line and one second target line straight line based on the first line coordinate point set, the second line coordinate point set, and the tension clamp rectangle. The first calculation unit is configured to calculate, based on at least one first target line and one second target line, a first angle between the first target line and the positive direction of the X-axis, and a second angle between the second target line and the positive direction of the X-axis. The second calculation unit is used to calculate the third angle between the crossarm centerline direction and the positive X-axis direction based on the crossarm profile point set. The intelligent detection unit is used to calculate the difference between the first included angle and the second included angle and the third included angle, respectively, to obtain two difference calculation results, and to perform intelligent detection of the installation angle of the corner bar crossarm based on the two difference calculation results.

[0014] Thirdly, embodiments of this application also provide an electronic device, including at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, which, when executed by the at least one control processor, enable the at least one control processor to perform an intelligent detection method for the installation angle of an angle bar crossarm as described above.

[0015] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions for causing a computer to execute an intelligent detection method for the installation angle of an angle bar crossarm as described above.

[0016] It is understood that the beneficial effects of the second to fourth aspects compared with the related technologies are the same as the beneficial effects of the first aspect compared with the related technologies. Please refer to the relevant description in the first aspect above, which will not be repeated here. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a flowchart illustrating an embodiment of the intelligent detection method for the installation angle of the corner bar crossarm provided in this application; Figure 2 This is a schematic diagram of image instance segmentation results in the best embodiment of the intelligent detection method for the installation angle of the corner bar crossarm provided in this application; Figure 3 This is a schematic diagram of the line straightness detection result in the best embodiment of the intelligent detection method for the installation angle of the corner pole crossarm provided in this application; Figure 4 This is a schematic diagram of the target line straight line screening results in the best embodiment of the intelligent detection method for the installation angle of the corner pole crossarm provided in this application; Figure 5 This is a schematic diagram of the direction of the crossarm centerline in the best embodiment of the intelligent detection method for the installation angle of the corner bar crossarm provided in this application; Figure 6 This is a schematic diagram of an embodiment of the intelligent detection system for the installation angle of the corner bar crossarm provided in this application; Figure 7 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this application. Detailed Implementation

[0018] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0019] In the description of this application, the use of terms such as "first," "second," etc., is for the purpose of distinguishing technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0020] In the description of this application, it should be understood that the orientation descriptions, such as up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0021] In the description of this application, it should be noted that, unless otherwise explicitly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0022] Currently, the main methods for detecting the installation angle of crossarms include manual measurement and image analysis. Manual measurement uses a theodolite or total station to measure point by point, which is complex, relies heavily on the experience of technicians, and has low efficiency. Image analysis involves manually taking photos at fixed locations and then annotating the angles using protractor software; however, the measurement results are greatly affected by the shooting angle and the operator's experience, resulting in poor repeatability. Furthermore, both methods require manual inspection of each crossarm, leading to low efficiency. In complex terrain or when observation locations are limited, it is often difficult to obtain effective data, thus making it difficult to obtain accurate detection results.

[0023] To address the issues of low detection efficiency and accuracy of crossarm installation angle in existing technologies, this application proposes an intelligent detection method, system, equipment, and medium for the installation angle of corner bar crossarms.

[0024] Reference Figure 1 This application provides a flowchart illustrating the intelligent detection method for the installation angle of a corner bar crossarm. This intelligent detection method for the installation angle of a corner bar crossarm is applied to an electronic device, which may be a server or a mobile terminal, etc. Figure 1 As shown, the intelligent detection method for the installation angle of the corner bar crossarm may include the following steps: Step S101: Perform instance segmentation on the collected corner bar image sample data to obtain the crossarm contour point set and multiple tension clamp contour point sets; Step S102: Based on multiple sets of tension clamp outline points, construct the tension clamp rectangle corresponding to each set of tension clamp outline points; Step S103: Construct a polygonal region enclosed by multiple tension clamps, and construct a first set of line coordinate points based on the starting point coordinates and ending point coordinates of each line straight line on the power transmission side of the polygonal region, and construct a second set of line coordinate points based on the starting point coordinates and ending point coordinates of each line straight line on the power receiving side of the polygonal region. Step S104: Based on the first set of line coordinate points, the second set of line coordinate points, and the tension clamp rectangle, select at least one first target line straight line and one second target line straight line. Step S105: Based on at least one first target line and one second target line, calculate the first angle between the first target line and the positive X-axis, and calculate the second angle between the second target line and the positive X-axis. Step S106: Calculate the third angle between the crossarm centerline direction and the positive X-axis direction based on the crossarm profile point set; Step S107: Calculate the difference between the first included angle and the second included angle and the third included angle respectively to obtain two difference calculation results, and perform intelligent detection of the installation angle of the corner bar crossarm based on the two difference calculation results.

[0025] In this embodiment, by segmenting the collected corner pole image sample data, a crossarm contour point set and multiple tension clamp contour point sets are obtained; based on the multiple tension clamp contour point sets, a tension clamp rectangle corresponding to each tension clamp contour point set is constructed; a polygonal region enclosed by multiple tension clamps is constructed, and a first line coordinate point set is constructed based on the start and end coordinates of each straight line on the power transmission side of the polygonal region; and a second line coordinate point set is constructed based on the start and end coordinates of each straight line on the power receiving side of the polygonal region; based on the first line coordinate point set and the second line coordinate point set... The coordinate point set and the tension clamp rectangle are used to select at least one first target line and one second target line. Based on the at least one first target line and one second target line, the first angle between the first target line and the positive X-axis is calculated, and the second angle between the second target line and the positive X-axis is calculated. Based on the crossarm profile point set, the third angle between the crossarm centerline direction and the positive X-axis is calculated. The first and second angles are then compared with the third angle to obtain two difference calculation results. Based on these two difference calculation results, the installation angle of the corner pole crossarm is intelligently detected. In this way, by collecting corner pole image sample data, a series of subsequent calculations are performed. Then, based on the calculated first, second, and third angles, the installation angle of the corner pole crossarm is intelligently detected. This allows for batch intelligent detection based on images, without the need for total station measurement or manual angle measurement. It is not affected by complex terrain or observation location, nor does it rely on the experience of technical personnel, thus improving the accuracy and efficiency of intelligent detection of the corner pole crossarm installation angle.

[0026] The aforementioned corner pole image sample data can be corner pole image sample data collected by a camera mounted on a drone.

[0027] The polygonal region enclosed by multiple tension clamps can be constructed by connecting multiple tension clamps end to end in a clockwise or counterclockwise order.

[0028] The aforementioned power supply side can be the side of the crossarm closest to the power source (such as a substation).

[0029] The aforementioned power receiving side can be the side of the crossarm closest to the load (such as the user).

[0030] In some implementations, based on the first set of line coordinate points, the second set of line coordinate points, and the tension clamp rectangle, at least one first target line straight line and one second target line straight line are selected, including: Based on the coordinate points in the set of coordinate points of the first line on the power receiving side, construct the straight line equation of the first line; Based on the coordinate points in the set of coordinate points of the second line on the power receiving side, construct the straight line equation of the second line; Based on the equation of the first line on the power receiving side, determine multiple first coordinate points for each line corresponding to the set of coordinate points of the first line on the power receiving side; Based on the equation of the second line on the power receiving side, determine multiple second coordinate points for each line corresponding to the set of coordinate points of the second line on the power receiving side; If any of the multiple first coordinate points on the power receiving side are within the rectangular frame of the tension clamp on the power receiving side, then the line line corresponding to the first coordinate point within the rectangular frame of the tension clamp on the power receiving side will be taken as the first target line line, and at least one first target line line will be obtained. If any of the multiple second coordinate points on the power receiving side are located within the rectangular frame of the tension clamp on the power receiving side, then the line line corresponding to the second coordinate point within the rectangular frame of the tension clamp on the power receiving side will be taken as the second target line line, thus obtaining at least one second target line line.

[0031] In this embodiment, selecting straight lines that satisfy both the line straightness equation and the coordinates corresponding to the points within the tension clamp rectangle improves the accuracy of target line straightness selection. Since some straight lines are not installed on the crossarm, removing those that would affect the accuracy of crossarm installation angle detection, and selecting the target straight lines, provides a solid data foundation for accurately calculating the first and second included angles later, thereby improving the accuracy of intelligent detection of crossarm installation angles.

[0032] The aforementioned multiple first coordinate points and multiple second coordinate points can be coordinate points on the extension lines of each straight line. The purpose is to determine whether there is an intersection between the straight line and the rectangle. Only the straight line with an intersection is the straight line installed on the crossarm, which is the target straight line.

[0033] In some implementations, the third angle between the crossarm's central axis direction and the positive X-axis direction is calculated based on the crossarm profile point set, including: Calculate the centroid of the crossarm based on the set of points on the crossarm profile; The data of each contour point in the crossarm contour point set is digitized to obtain a centered matrix; Based on the centering matrix, calculate the principal axis direction vector and use the principal axis direction vector as the crossarm centerline direction vector. Calculate the third angle between the direction vector of the crossarm's central axis and the positive X-axis direction.

[0034] In this embodiment, due to factors such as image distortion from UAV captures and the accuracy of the crossarm segmentation model, the crossarm profile cannot be guaranteed to be a complete rectangle. Therefore, by digitizing the data of each profile point in the crossarm profile point set to obtain a centered matrix, and then calculating the principal axis direction vector based on the centered matrix, the principal axis direction vector is used as the crossarm centerline direction vector. Finally, the third angle between the crossarm centerline direction vector and the positive X-axis direction is calculated, which improves the accuracy of the crossarm centerline calculation, thereby improving the accuracy of intelligent detection of the corner crossarm installation angle.

[0035] The above calculation of the crossarm centroid based on the crossarm profile point set can be achieved by summing and averaging the coordinates of all profile points in the crossarm profile point set to obtain the crossarm centroid.

[0036] In some implementations, the principal axis direction vector is calculated based on the centralization matrix, including: Construct the covariance matrix based on the centralization matrix; Calculate the eigenvalues ​​in the covariance matrix to obtain all eigenvalues; Select the largest eigenvalue from all eigenvalues, calculate the target eigenvector, and use the target eigenvector as the principal axis direction vector.

[0037] In this embodiment, the largest eigenvalue is selected from all eigenvalues, the target eigenvector is calculated, and the target eigenvector is used as the principal axis direction vector, which can improve the accuracy of the principal axis direction vector calculation.

[0038] In some implementations, the target feature vector is calculated by selecting the largest feature value from all feature values, including: ; ; in, Represents the covariance matrix. Represents the largest eigenvalue. Represents the identity matrix. This represents the target feature vector.

[0039] In some embodiments, calculating a first angle between the first target line and the positive X-axis, and calculating a second angle between the second target line and the positive X-axis, based on at least one first target line and one second target line, includes: Obtain the first number of straight lines on the first target route, and obtain the second number of straight lines on the second target route; Sum the angles between each of the first target line lines and the positive X-axis to obtain the total sum of the first angles; Sum the angles between each second target line and the positive X-axis to obtain the total sum of the second angles; Divide the sum of the first included angles by the first quantity to obtain the first included angle between the first target line and the positive X-axis direction; Divide the sum of the second included angles by the second quantity to obtain the second included angle between the second target line and the positive X-axis direction.

[0040] In this embodiment, if there are multiple first target line straight lines and multiple second target line straight lines, the average angle between the multiple first target line straight lines and the multiple second target line straight lines and the positive X-axis direction will be obtained. Using the average angle as the first angle or the second angle can improve the accuracy of the calculation of the first angle and the second angle, thereby improving the accuracy of the intelligent detection of the crossarm installation angle.

[0041] In some implementations, intelligent detection of the angle bar crossarm installation angle is performed based on the calculation results of two differences, including: The absolute value of the difference between the two difference calculation results is calculated. If the absolute value of the difference is less than the preset value, it indicates that the crossarm installation angle is detected by the intelligent detection of the crossarm installation angle of the corner bar.

[0042] In this embodiment, the installation angle of the corner bar crossarm is intelligently detected by calculating the result of two differences. The entire process does not require total station measurement or manual angle measurement, which realizes fully automated intelligent detection and improves the detection efficiency of the installation angle of the corner bar crossarm.

[0043] To facilitate understanding by those skilled in the art, a set of preferred embodiments is provided below: In the construction and operation and maintenance of power lines, the installation angle of the crossarm of angle towers directly affects the mechanical stress balance and long-term operational safety of the line. According to the "Code for Construction and Acceptance of Electrical Installations for 66kV and Below Overhead Power Lines GB50173-2014", the crossarm of the angle tower must be strictly installed on the bisector of the angle in the direction of the line's turn. If the installation angle does not meet the standard, it will lead to uneven conductor tension distribution, accelerated wear of hardware, and in severe cases, may even cause tower collapse.

[0044] Currently, the main methods for detecting the installation angle of crossarms include manual measurement and image analysis. Manual measurement uses a theodolite or total station to measure point by point, which is complex, relies heavily on the experience of technicians, and is inefficient. Image analysis involves manually taking photos at fixed locations and then annotating the angles using protractor software; however, the measurement results are greatly affected by the shooting angle and the operator's experience, resulting in poor repeatability. Furthermore, both methods require manual inspection of each crossarm, leading to low efficiency, increased labor intensity, and difficulty in obtaining effective data in complex terrain or when observation locations are limited, thus hindering the acquisition of accurate detection results.

[0045] To address the problems existing in the prior art, this embodiment proposes an intelligent detection method for the installation angle of corner pole crossarms. This method aims to automatically identify crossarms in images using deep learning technology, calculate other materials and equipment required for the crossarm installation angle, and perform post-processing on the images to calculate the data needed for the crossarm installation angle process point. Through contour recognition, mathematical processing, and morphological analysis, it achieves accurate measurement of the crossarm installation angle, overcoming the shortcomings of existing technologies for corner pole crossarm installation angles. This invention automatically calculates the installation angle of corner pole crossarms through deep learning algorithms and image processing, eliminating the need for total station measurements or manual angle measurement. This not only solves the subjectivity inherent in manual measurement but also significantly improves measurement speed. Furthermore, combined with automatic image acquisition by drones, it avoids situations where detection is impossible due to complex terrain or limited observation locations, enabling batch detection of process points along the entire line and greatly improving detection efficiency and scenario applicability.

[0046] The technical solution of this embodiment specifically includes the following contents: (1) Image sample data of corner poles were collected using a camera mounted on a drone. The preferred angle for acquisition was a 90° overhead view directly above the pole, followed by an upward view from about 2 / 3 of the pole's height in the direction of the horizontal line. Based on the instance segmentation model framework, instance segmentation models for crossarms and tension clamps were constructed to achieve instance segmentation of crossarms and tension clamps, obtaining the outline point set of crossarms and tension clamps. Then, from the outline point set of tension clamps, all outline points were obtained. Maximum value and minimum value as well as Maximum value and minimum value , and The coordinates of the top-left and bottom-right points of the rectangle are used as the reference points, and the rectangle of the tension clamp is constructed based on these coordinates. The instance segmentation results of the crossarm and tension clamp are as follows: Figure 2 As shown.

[0047] It should be noted that the instance segmentation model in this embodiment can be a commonly used instance segmentation model in the prior art, which will not be described in detail in this embodiment.

[0048] (2) Based on Figure 2 The polygonal region enclosed by multiple tension clamps is used as the calculation range for the left and right line directions, with the left boundary (power supply side) and right boundary (power receiving side) of the region selected respectively. Image enhancement, edge detection, and Hough transform line detection are employed to obtain the starting and ending coordinates of the straight line of each wire in the line. The line straightness detection results are as follows: Figure 3 As shown, Figure 3 The dashed line in the middle represents the detected straight line.

[0049] (1); (2); in, This indicates the number of straight lines on the power transmission side. This indicates the number of straight lines on the power receiving side. and They can be equal or unequal, depending on what is shown in the captured image of the corner pole. and Straight lines on the crossarm transmitting and receiving sides The set of (straight lines on the power transmission side) The set of points is the first set of line coordinates, and the power receiving side line is straight. The set of coordinates is the set of coordinates for the second route. , and These are two coordinate points on the straight line of the route, including the starting coordinate point and the ending coordinate point.

[0050] It should be noted that the image enhancement, edge detection, and Hough transform line detection in this embodiment are all existing technologies known to those skilled in the art, and will not be described in detail in this embodiment.

[0051] (3) Based on the positional relationship between the straight line and the rectangular frame containing the tension clamp, select the target straight line (including at least one first target straight line and one second target straight line), ensuring that the extension of the straight line intersects with the rectangular frame containing the tension clamp, as follows: (3); (4); Among them, formula (3) is the equation of the straight line of the line. For any coordinate point that satisfies the straight line equation (3), formula (4) represents the boundary of the tension clamp rectangular frame. and Let A and B be the coordinates of the upper left and lower right points of the tension clamp rectangle, respectively. Solving the above equations, we can find the line that exists... satisfy That is, the straight line of the railway line intersects with the rectangular frame containing the tension clamp. Satisfying formulas (3) and (4) indicates that the straight line of the railway line intersects with the rectangular frame; this is the target straight line of the railway line to be retained in this embodiment. The results of the target straight line selection are as follows: Figure 4 As shown, Figure 4 The dashed line in the middle represents the detected target line straight line.

[0052] (4) Calculate the direction of the crossarm's central axis. Due to image distortion from UAV photography and the accuracy of the crossarm segmentation model, the crossarm outline cannot be guaranteed to be a complete rectangle. To improve the accuracy of the crossarm's central axis calculation, this embodiment uses principal component analysis to calculate the principal axis direction of the crossarm as the central axis direction. The specific calculation steps are as follows: 1) The crossarm profile point set obtained in step (1) ,Include Coordinates of each contour point As shown in the following formula: (5); 2) Calculate the center of mass of the crossarm That is to The average coordinate value is obtained by summing the coordinates of each contour point and then averaging them. As shown in the following formula: (6); 3) Data-driven analysis of each contour point in the crossarm contour point set is performed to form a centralized matrix, as shown in the following formula: (7); 4) Calculate the principal axis direction vector. First, construct the covariance matrix as follows: (8); in, , , .

[0053] The eigenvalues ​​of the covariance matrix are calculated as follows: (9); in, Represents a determinant.

[0054] All eigenvalues ​​can be obtained using the above formula. Select the largest eigenvalue Calculating the eigenvector is equivalent to calculating the principal axis direction vector. .

[0055] (10); (11); Calculate the principal axis direction vector Angle with the positive X-axis direction (i.e., the third included angle), as shown in the following formula: (12); in, Represents the principal axis direction vector Direction vector, Represents the principal axis direction vector Direction vector. The direction of the crossarm's central axis is as follows: Figure 5 As shown.

[0056] (5) Calculate the average angle between the target line straight line selected in step (3) and the positive direction of the X-axis for the power transmission side and the power receiving side line straight line. (i.e., the first included angle) and the average included angle (i.e., the second included angle).

[0057] (13); (14); in, The angle between a single straight line on the route and the positive direction of the X-axis. and All of them adopt The calculation method is as follows. If there are multiple target straight lines on both the power transmission and receiving sides, the number of target straight lines on the power transmission side corresponds to... , The number of straight lines on the target line on the power receiving side corresponds to the following: , ,in, and They can be equal or unequal; if there is only one straight target line between the power supply side and the power receiving side, then .

[0058] (6) Calculate the angle difference between the target line on the power transmission side and the centerline of the crossarm on the power receiving side respectively. and and judge and absolute value of the difference If the angle is less than 5° (i.e., the preset value), it indicates that the installation angle of the crossarm has passed the algorithm detection of this embodiment, meaning that the installation angle of the crossarm meets the requirements and satisfies the standard specifications. The angle difference is calculated as follows: (15); (16); (17); It should be noted that although the preset value in this embodiment is set to 5°, it can be changed according to the actual situation. This embodiment does not make specific limitations. For example, when the standard specification is changed to 4°, the preset value can be changed to 4°.

[0059] Reference Figure 6This application embodiment also provides an intelligent detection system for the installation angle of a corner bar crossarm. The system includes an instance segmentation unit 601, a first construction unit 602, a second construction unit 603, a straight line filtering unit 604, a first calculation unit 605, a second calculation unit 606, and an intelligent detection unit 607, wherein: The instance segmentation unit 601 is used to segment the collected corner pole image sample data into instances to obtain the crossarm contour point set and multiple tension clamp contour point sets. The first building unit 602 is used to build a tension clamp rectangle corresponding to each tension clamp contour point set based on multiple tension clamp contour point sets. The second construction unit 603 is used to construct a polygonal region enclosed by multiple tension clamps, and to construct a first set of line coordinate points based on the starting point coordinates and ending point coordinates of each line straight line on the power transmission side of the polygonal region, and to construct a second set of line coordinate points based on the starting point coordinates and ending point coordinates of each line straight line on the power receiving side of the polygonal region. The straight line filtering unit 604 is used to filter out at least one first target line straight line and one second target line straight line based on the first line coordinate point set, the second line coordinate point set, and the tension clamp rectangle. The first calculation unit 605 is used to calculate, based on at least one first target line and one second target line, a first angle between the first target line and the positive direction of the X-axis, and a second angle between the second target line and the positive direction of the X-axis. The second calculation unit 606 is used to calculate the third angle between the direction of the crossarm centerline and the positive direction of the X-axis based on the crossarm profile point set; The intelligent detection unit 607 is used to calculate the difference between the first included angle and the second included angle and the third included angle respectively, obtain two difference calculation results, and perform intelligent detection of the installation angle of the corner bar crossarm based on the two difference calculation results.

[0060] It should be noted that since the intelligent detection system for the installation angle of the corner bar crossarm in this embodiment is based on the same inventive concept as the intelligent detection method for the installation angle of the corner bar crossarm described above, the corresponding content in the method embodiment is also applicable to this system embodiment, and will not be described in detail here.

[0061] Reference Figure 7 This application also provides an electronic device, which includes: At least one memory; At least one processor; At least one program; The program is stored in memory, and the processor executes at least one program to implement the intelligent detection method for the installation angle of the corner bar crossarm described above in this disclosure.

[0062] This electronic device can be any smart terminal, including mobile phones, tablets, personal digital assistants (PDAs), and in-vehicle computers.

[0063] The electronic devices according to embodiments of this application will now be described in detail.

[0064] The processor 1600 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this disclosure. The memory 1700 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1700 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1700 and is called and executed by the processor 1600 to execute the intelligent detection method for the installation angle of the corner bar crossarm according to the embodiments of this disclosure.

[0065] The input / output interface 1800 is used to implement information input and output. The communication interface 1900 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 2000 transmits information between various components of the device (e.g., processor 1600, memory 1700, input / output interface 1800, and communication interface 1900); The processor 1600, memory 1700, input / output interface 1800 and communication interface 1900 are connected to each other within the device via bus 2000.

[0066] This disclosure also provides a storage medium, which is a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the above-described intelligent detection method for the installation angle of the corner bar crossarm.

[0067] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0068] The embodiments described in this disclosure are for the purpose of more clearly illustrating the technical solutions of this disclosure and do not constitute a limitation on the technical solutions provided by this disclosure. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by this disclosure are also applicable to similar technical problems.

[0069] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this disclosure, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0070] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0072] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0073] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0077] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks. The embodiments of this application have been described in detail above with reference to the accompanying drawings, but this application is not limited to the above embodiments. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of this application.

[0078] The embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of this application.

Claims

1. An intelligent detection method for the installation angle of a corner bar crossarm, characterized in that, The method includes: The collected corner bar image sample data is segmented to obtain the crossarm contour point set and multiple tension clamp contour point sets; Based on the multiple sets of tension clamp contour points, construct a tension clamp rectangle corresponding to each set of tension clamp contour points. Construct a polygonal region enclosed by multiple tension clamps, and construct a first set of line coordinate points based on the starting point coordinates and ending point coordinates of each straight line on the power transmission side of the polygonal region; and construct a second set of line coordinate points based on the starting point coordinates and ending point coordinates of each straight line on the power receiving side of the polygonal region. Based on the first set of line coordinate points, the second set of line coordinate points, and the tension clamp rectangle, at least one first target line straight line and one second target line straight line are selected. Based on at least one first target line and one second target line, calculate the first angle between the first target line and the positive X-axis, and calculate the second angle between the second target line and the positive X-axis. Based on the crossarm profile point set, calculate the third angle between the crossarm centerline direction and the positive X-axis direction; The first included angle and the second included angle are respectively compared with the third included angle to obtain two difference calculation results. The installation angle of the corner bar crossarm is intelligently detected based on the two difference calculation results.

2. The intelligent detection method for the installation angle of the corner bar crossarm according to claim 1, characterized in that, The step of selecting at least one first target line straight line and one second target line straight line based on the first set of line coordinate points, the second set of line coordinate points, and the tension clamp rectangle includes: Based on the coordinate points in the first set of coordinate points, construct the equation of the first straight line; Based on the coordinate points in the second set of coordinate points, construct the equation of the second straight line; Based on the equation of the first line, determine multiple first coordinate points for each line corresponding to the first set of coordinate points; Based on the equation of the second line, determine multiple second coordinate points for each line corresponding to the set of coordinate points of the second line; If any of the plurality of first coordinate points is within the rectangular frame of the tension clamp, then the straight line corresponding to the first coordinate point within the rectangular frame of the tension clamp is taken as the first target straight line, and at least one first target straight line is obtained. If any of the plurality of second coordinate points is located within the rectangular frame of the tension clamp, then the straight line corresponding to the second coordinate point within the rectangular frame of the tension clamp is taken as the second target straight line, thus obtaining at least one second target straight line.

3. The intelligent detection method for the installation angle of the corner bar crossarm according to claim 1, characterized in that, The step of calculating the third angle between the crossarm's central axis direction and the positive X-axis direction based on the crossarm profile point set includes: Calculate the centroid of the crossarm based on the set of points on the crossarm profile; The data of each contour point in the crossarm contour point set is digitized to obtain a centered matrix; Based on the centralization matrix, calculate the principal axis direction vector and use the principal axis direction vector as the crossarm centerline direction vector; Calculate the third angle between the direction vector of the crossarm's central axis and the positive X-axis direction.

4. The intelligent detection method for the installation angle of the corner bar crossarm according to claim 3, characterized in that, The step of calculating the principal axis direction vector based on the centered matrix includes: Construct the covariance matrix based on the centralization matrix; Calculate the eigenvalues ​​in the covariance matrix to obtain all eigenvalues; Select the largest eigenvalue from all the eigenvalues, calculate the target eigenvector, and use the target eigenvector as the principal axis direction vector.

5. The intelligent detection method for the installation angle of the corner bar crossarm according to claim 4, characterized in that, The step of selecting the largest eigenvalue from all the eigenvalues ​​and calculating the target feature vector includes: ； ； in, Represents the covariance matrix. Represents the largest eigenvalue. Represents the identity matrix. This represents the target feature vector.

6. The intelligent detection method for the installation angle of the corner bar crossarm according to claim 1, characterized in that, The step of calculating a first angle between the first target line and the positive X-axis, and calculating a second angle between the second target line and the positive X-axis, based on at least one first target line and one second target line, includes: Obtain a first number of straight lines on the first target route, and obtain a second number of straight lines on the second target route; The sum of the angles between each of the first target line lines and the positive X-axis is obtained to obtain the total sum of the first angles; The sum of the angles between each of the second target line lines and the positive X-axis is obtained to obtain the total sum of the second angles; Divide the sum of the first included angles by the first quantity to obtain the first included angle between the first target line and the positive direction of the X-axis. Divide the sum of the second included angles by the second quantity to obtain the second included angle between the second target line and the positive direction of the X-axis.

7. The intelligent detection method for the installation angle of the corner bar crossarm according to claim 1, characterized in that, The intelligent detection of the installation angle of the corner bar crossarm based on the calculation results of the two differences includes: The absolute value of the difference between the two difference calculation results is calculated. If the absolute value of the difference is less than the preset value, it indicates that the crossarm installation angle is detected by the intelligent detection of the crossarm installation angle of the corner bar.

8. An intelligent detection system for the installation angle of a corner bar crossarm, characterized in that, The system includes: The instance segmentation unit is used to segment the collected corner pole image sample data into instances to obtain the crossarm contour point set and multiple tension clamp contour point sets. The first construction unit is used to construct a tension clamp rectangle corresponding to each tension clamp contour point set based on the plurality of tension clamp contour point sets. The second construction unit is used to construct a polygonal region enclosed by multiple tension clamps, and to construct a first set of line coordinate points based on the starting point coordinates and ending point coordinates of each line straight line on the power transmission side of the polygonal region, and to construct a second set of line coordinate points based on the starting point coordinates and ending point coordinates of each line straight line on the power receiving side of the polygonal region. The straight line filtering unit is used to filter out at least one first target line straight line and one second target line straight line based on the first line coordinate point set, the second line coordinate point set, and the tension clamp rectangle. The first calculation unit is configured to calculate, based on at least one first target line and one second target line, a first angle between the first target line and the positive direction of the X-axis, and a second angle between the second target line and the positive direction of the X-axis. The second calculation unit is used to calculate the third angle between the crossarm centerline direction and the positive X-axis direction based on the crossarm profile point set. The intelligent detection unit is used to calculate the difference between the first included angle and the second included angle and the third included angle respectively, to obtain two difference calculation results, and to perform intelligent detection of the installation angle of the corner bar crossarm based on the two difference calculation results.

9. An electronic device, characterized in that, It includes at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, which, when executed by the at least one control processor, enable the at least one control processor to perform the intelligent detection method for the installation angle of the corner bar crossarm as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the intelligent detection method for the installation angle of the corner bar crossarm as described in any one of claims 1 to 7.

Images