Intelligent detection method, system and device for installation angle of corner pole cross arm and medium

Abstract

The application discloses a kind of corner pole cross arm installation angle intelligent detection method, system, equipment and medium, the method is by constructing the outline point set corresponding to strain clamp rectangular frame of each strain clamp;First line coordinate point set is constructed, second line coordinate point set is constructed;According to first line coordinate point set, second line coordinate point set and strain clamp rectangular frame, at least one first target line straight line and second target line straight line are screened out;The first included angle of first target line straight line and X axis positive direction is calculated, the second included angle of second target line straight line and X axis positive direction is calculated;The third included angle of cross arm central axis direction and X axis positive direction is calculated;First included angle and second included angle are respectively with third included angle difference value calculation is carried out, obtains two difference value calculation results, according to two difference value calculation results, the intelligent detection of corner pole cross arm installation angle is carried out.This application can improve the intelligent detection accuracy and detection efficiency of corner pole cross arm installation angle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a method, system and device for intelligently detecting the installation angle of a corner pole cross arm, and a medium. BACKGROUND

[0002] In power line construction and operation, the installation angle of the cross arm of a corner pole tower directly affects the mechanical stress balance and long-term operation safety of the line. According to the requirements of the "Electrical Device Installation Engineering 66kV and Below Overhead Power Line Construction and Acceptance Specification GB50173-2014", the cross arm of the corner pole must be strictly installed on the angle bisector in the corner direction of the line. If the installation angle is not up to standard, it will lead to uneven distribution of conductor tension, accelerate the wear of fittings, and even cause tower collapse accidents in severe cases.

[0003] Currently, the detection methods for the installation angle of the cross arm mainly include manual measurement and image analysis. The manual measurement method uses theodolites or total stations to measure point by point, which is complex to operate and depends on the experience of technical personnel, and the detection efficiency is low. The image analysis method uses an angle measuring software to mark the angle after manually taking a photo at a fixed position, and the measurement result is greatly influenced by the shooting angle and the experience of personnel, and the repeatability is poor. At the same time, the above methods all need manual detection of each pole, and the detection efficiency is low. In complex terrain or when the observation position is limited, it is often difficult to obtain effective data, so it is difficult to obtain accurate detection results. SUMMARY

[0004] The present application aims to provide an intelligent detection method, system, device and medium for the installation angle of the cross arm of a corner pole, which can improve the intelligent detection accuracy and efficiency of the installation angle of the cross arm of a corner pole.

[0005] In a first aspect, an embodiment of the present application provides an intelligent detection method for the installation angle of the cross arm of a corner pole, which comprises:

[0006] performing instance segmentation on the collected corner pole image sample data to obtain a cross arm contour point set and a plurality of strain clamp contour point sets;

[0007] constructing a strain clamp rectangular frame corresponding to each strain clamp contour point set according to the plurality of strain clamp contour point sets;

[0008] constructing a polygonal region enveloped by the plurality of strain clamps, and constructing a first line coordinate point set according to the starting point coordinates and the end point coordinates of each line straight line on the power transmission side of the polygonal region, and constructing a second line coordinate point set according to the starting point coordinates and the end point coordinates of each line straight line on the power receiving side of the polygonal region;

[0009] According to the first line coordinate point set, the second line coordinate point set and the strain clamp rectangular frame, at least one first target line straight line and a second target line straight line are screened out;

[0010] According to the at least one first target line straight line and the second target line straight line, a first included angle between the first target line straight line and the positive direction of the X-axis is calculated, and a second included angle between the second target line straight line and the positive direction of the X-axis is calculated;

[0011] According to the cross arm contour point set, a third included angle between the cross arm central axis direction and the positive direction of the X-axis is calculated;

[0012] The first included angle and the second included angle are respectively subtracted from the third included angle to obtain two subtraction calculation results, and intelligent detection of the installation angle of the corner pole cross arm is performed according to the two subtraction calculation results.

[0013] Compared with the prior art, the first aspect of the present application has the following beneficial effects:

[0014] The method obtains a cross arm contour point set and a plurality of strain clamp contour point sets by performing instance segmentation on the collected corner pole image sample data; according to the plurality of strain clamp contour point sets, a strain clamp rectangular frame corresponding to each strain clamp contour point set is constructed; a polygonal region enveloped by the plurality of strain clamps is constructed, and according to the starting point coordinates and the end point coordinates of each line straight line on the power supply side of the polygonal region, a first line coordinate point set is constructed, and according to the starting point coordinates and the end point coordinates of each line straight line on the power receiving side of the polygonal region, a second line coordinate point set is constructed; according to the first line coordinate point set, the second line coordinate point set and the strain clamp rectangular frame, at least one first target line straight line and a second target line straight line are screened out; according to the at least one first target line straight line and the second target line straight line, a first included angle between the first target line straight line and the positive direction of the X-axis is calculated, and a second included angle between the second target line straight line and the positive direction of the X-axis is calculated; according to the cross arm contour point set, a third included angle between the cross arm central axis direction and the positive direction of the X-axis is calculated; the first included angle and the second included angle are respectively subtracted from the third included angle to obtain two subtraction calculation results, and intelligent detection of the installation angle of the corner pole cross arm is performed according to the two subtraction calculation results. In this way, through the collected corner pole image sample data, a series of subsequent calculations are performed, and then the first included angle, the second included angle and the third included angle obtained by calculation are used to intelligently detect the installation angle of the corner pole cross arm, without the need for total station measurement or manual angle measurement, which is not affected by complex terrain or observation position, and does not depend on the experience of technical personnel, thereby improving the intelligent detection accuracy and detection efficiency of the installation angle of the corner pole cross arm.

[0015] In some embodiments, the filtering out of at least one first target line straight line and 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 comprises:

[0016] constructing a first line straight line equation according to the coordinate points in the first line coordinate point set;

[0017] constructing a second line straight line equation according to the coordinate points in the second line coordinate point set;

[0018] determining a plurality of first coordinate points of each line straight line corresponding to the first line coordinate point set according to the first line straight line equation;

[0019] determining a plurality of second coordinate points of each line straight line corresponding to the second line coordinate point set according to the second line straight line equation;

[0020] if any first coordinate point in the plurality of first coordinate points is in the strain clamp rectangular frame, taking the line straight line corresponding to the first coordinate point in the strain clamp rectangular frame as a first target line straight line, and obtaining at least one first target line straight line;

[0021] if any second coordinate point in the plurality of second coordinate points is in the strain clamp rectangular frame, taking the line straight line corresponding to the second coordinate point in the strain clamp rectangular frame as a second target line straight line, and obtaining at least one second target line straight line.

[0022] In some embodiments, the calculating of a third included angle between the cross arm central axis direction and the positive direction of the X axis according to the cross arm contour point set comprises:

[0023] calculating a cross arm centroid according to the cross arm contour point set;

[0024] centralizing each contour point data in the cross arm contour point set to obtain a centralization matrix;

[0025] calculating a principal axis direction vector according to the centralization matrix, and taking the principal axis direction vector as a cross arm central axis direction vector;

[0026] calculating the third included angle between the cross arm central axis direction vector and the positive direction of the X axis.

[0027] In some embodiments, the calculating of the principal axis direction vector according to the centralization matrix comprises:

[0028] constructing a covariance matrix according to the centralization matrix;

[0029] calculating eigenvalues in the covariance matrix to obtain all eigenvalues;

[0030] Select the largest eigenvalue from all the eigenvalues, calculate the target eigenvector, and use the target eigenvector as the principal axis direction vector.

[0031] In some implementations, selecting the largest eigenvalue from all eigenvalues ​​and calculating the target eigenvector includes:

[0032] ;

[0033] ;

[0034] in, Represents the covariance matrix. Represents the largest eigenvalue. Represents the identity matrix. This represents the target feature vector.

[0035] 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:

[0036] 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;

[0037] 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;

[0038] 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;

[0039] 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.

[0040] 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.

[0041] In some implementations, the intelligent detection of the angle bar crossarm installation angle based on the calculation results of the two differences includes:

[0042] 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.

[0043] Secondly, embodiments of this application also provide an intelligent detection system for the installation angle of an angle bar crossarm, the system comprising:

[0044] an instance segmentation unit, configured to perform instance segmentation on the collected angle pole image sample data to obtain a cross arm contour point set and a plurality of strain clamp contour point sets;

[0045] a first construction unit, configured to construct a strain clamp rectangular frame corresponding to each strain clamp contour point set according to the plurality of strain clamp contour point sets;

[0046] a second construction unit, configured to construct a polygonal region enveloping the plurality of strain clamps, and construct a first line coordinate point set according to start point coordinates and end point coordinates of each line straight line on a power supply side of the polygonal region, and construct a second line coordinate point set according to start point coordinates and end point coordinates of each line straight line on a power receiving side of the polygonal region;

[0047] a straight line screening unit, configured to screen at least one first target line straight line and a 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;

[0048] a first calculation unit, configured to calculate a first included angle between the first target line straight line and a positive direction of an X-axis, and calculate a second included angle between the second target line straight line and the positive direction of the X-axis, according to the at least one first target line straight line and the second target line straight line;

[0049] a second calculation unit, configured to calculate a third included angle between a cross arm central axis direction and the positive direction of the X-axis according to the cross arm contour point set;

[0050] an intelligent detection unit, configured to perform difference calculation on the first included angle and the second included angle respectively and the third included angle to obtain two difference calculation results, and perform intelligent detection on an angle pole cross arm installation angle according to the two difference calculation results.

[0051] In a third aspect, an electronic device is provided, including at least one control processor and a memory in communication connection with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to perform the intelligent detection method for the angle pole cross arm installation angle.

[0052] In a fourth aspect, a computer readable storage medium is provided, which stores computer executable instructions for causing a computer to perform the intelligent detection method for the angle pole cross arm installation angle.

[0053] It can be understood that the beneficial effects of the second aspect to the fourth aspect compared with the related art are the same as the beneficial effects of the first aspect compared with the related art, and can be seen from the related description in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0054] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the description of the embodiments, taken in conjunction with the following drawings in which:

[0055] Figure 1 is a flowchart of an embodiment of the intelligent detection method for the installation angle of a corner pole cross arm provided by the present application;

[0056] Figure 2 is an image instance segmentation result schematic diagram in the best embodiment of the intelligent detection method for the installation angle of a corner pole cross arm provided by the present application;

[0057] Figure 3 is a line straightness detection result schematic diagram in the best embodiment of the intelligent detection method for the installation angle of a corner pole cross arm provided by the present application;

[0058] Figure 4 is a target line straightness screening result schematic diagram in the best embodiment of the intelligent detection method for the installation angle of a corner pole cross arm provided by the present application;

[0059] Figure 5 is a cross arm central axis direction schematic diagram in the best embodiment of the intelligent detection method for the installation angle of a corner pole cross arm provided by the present application;

[0060] Figure 6 is a structural schematic diagram of an embodiment of the intelligent detection system for the installation angle of a corner pole cross arm provided by the present application;

[0061] Figure 7 is a structural schematic diagram of an embodiment of the electronic device provided by the present application. DETAILED DESCRIPTION

[0062] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0063] In the description of the present application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or the sequence of indicated technical features.

[0064] In the description of the present application, it should be understood that the orientation description, such as the orientation or position relationship indicated by the upper, lower and the like, is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0065] In the description of the present application, it should be noted that, unless otherwise explicitly limited, the words such as setting, installation, connection and the like should be understood in a broad sense, and the person skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0066] At present, the detection methods of cross arm installation angle mainly include manual measurement method and image analysis method, wherein the manual measurement method uses theodolite or total station instrument to measure point by point, which is complex in operation and depends on the experience of technical personnel, and the detection efficiency is low; the image analysis method marks the angle by using protractor software after manually taking photos at a fixed position, and the measurement result is greatly influenced by the shooting angle and the experience of personnel, and the repeatability is poor. At the same time, the above methods all need manual detection rod by rod, and the detection efficiency is low, and in complex terrain or observation position is limited, it is often difficult to obtain effective data, therefore, it is difficult to obtain accurate detection result.

[0067] In order to solve the problems of low detection efficiency and detection accuracy of cross arm installation angle in the prior art, the present application provides an intelligent detection method, system, equipment and medium for the installation angle of a corner pole cross arm.

[0068] Reference Figure 1 The intelligent detection method for the installation angle of a corner pole cross arm provided by the embodiments of the present application. The intelligent detection method for the installation angle of a corner pole cross arm is applied to an electronic device, which can be a server or a mobile terminal, etc. As shown in Figure 1 The intelligent detection method for the installation angle of a corner pole cross arm can include the following steps:

[0069] Step S101, performing instance segmentation on the collected corner pole image sample data to obtain a cross arm contour point set and a plurality of strain clamp contour point sets;

[0070] Step S102, constructing a strain clamp rectangular frame corresponding to each strain clamp contour point set according to the plurality of strain clamp contour point sets;

[0071] Step S103, constructing a polygonal region enveloped by the plurality of strain clamps, and constructing a first line coordinate point set according to the starting point coordinates and the end point coordinates of each line straight line on the power supply side of the polygonal region, and constructing a second line coordinate point set according to the starting point coordinates and the end point coordinates of each line straight line on the power receiving side of the polygonal region;

[0072] Step S104, according to the first line coordinate point set, the second line coordinate point set and the strain clamp rectangular frame, at least one first target line straight line and the second target line straight line are screened out;

[0073] Step S105, according to at least one first target line straight line and the second target line straight line, the first included angle of the first target line straight line with the positive direction of X axis is calculated, and the second included angle of the second target line straight line with the positive direction of X axis is calculated;

[0074] Step S106, according to the cross arm contour point set, the third included angle of the cross arm central axis direction with the positive direction of X axis is calculated;

[0075] Step S107, the first included angle and the second included angle are respectively subtracted from the third included angle to obtain two difference calculation results, and the intelligent detection of the installation angle of the corner pole cross arm is carried out according to the two difference calculation results.

[0076] In the embodiment, the cross arm contour point set and the plurality of strain clamp contour point sets are obtained by instance segmentation on the collected corner pole image sample data; the strain clamp rectangular frame corresponding to each strain clamp contour point set is constructed according to the plurality of strain clamp contour point sets; the polygon region enveloped by the plurality of strain clamps is constructed, and the first line coordinate point set is constructed according to the starting point coordinates and the end point coordinates of each line straight line on the power supply side of the polygon region, and the second line coordinate point set is constructed according to the starting point coordinates and the end point coordinates of each line straight line on the power receiving side of the polygon region; at least one first target line straight line and the second target line straight line are screened out according to the first line coordinate point set, the second line coordinate point set and the strain clamp rectangular frame; the first included angle of the first target line straight line with the positive direction of X axis is calculated, and the second included angle of the second target line straight line with the positive direction of X axis is calculated according to at least one first target line straight line and the second target line straight line; the third included angle of the cross arm central axis direction with the positive direction of X axis is calculated according to the cross arm contour point set; the first included angle and the second included angle are respectively subtracted from the third included angle to obtain two difference calculation results, and the intelligent detection of the installation angle of the corner pole cross arm is carried out according to the two difference calculation results. In this way, through the collected corner pole image sample data, a series of subsequent calculations are carried out, and then the intelligent detection of the installation angle of the corner pole cross arm is carried out according to the first included angle, the second included angle and the third included angle obtained by calculation, which can be batch intelligent detection according to the image, without total station measurement or manual angle measurement, is not affected by complex terrain or observation position, and does not depend on the experience of technical personnel, thereby improving the intelligent detection accuracy and detection efficiency of the installation angle of the corner pole cross arm.

[0077] The above-mentioned collected corner pole image sample data can be corner pole image sample data collected by a camera carried by a drone.

[0078] The polygon region surrounded by the plurality of strain clamps can be connected in a clockwise or counterclockwise order.

[0079] The power transmission side can be a side of the cross arm close to a power source (such as a transformer substation).

[0080] The power receiving side can be a side of the cross arm close to a load (such as a user).

[0081] In some embodiments, according to the first line coordinate point set, the second line coordinate point set, and the strain clamp rectangular frame, at least one first target line straight line and a second target line straight line are screened out, including:

[0082] According to the coordinate points in the first line coordinate point set on the power receiving side, a first line straight line equation is constructed;

[0083] According to the coordinate points in the second line coordinate point set on the power receiving side, a second line straight line equation is constructed;

[0084] According to the first line straight line equation on the power receiving side, a plurality of first coordinate points of each line straight line corresponding to the first line coordinate point set on the power receiving side are determined;

[0085] According to the second line straight line equation on the power receiving side, a plurality of second coordinate points of each line straight line corresponding to the second line coordinate point set on the power receiving side are determined;

[0086] If there is any first coordinate point in the plurality of first coordinate points on the power receiving side in the strain clamp rectangular frame on the power receiving side, the line straight line corresponding to the first coordinate point in the strain clamp rectangular frame on the power receiving side is taken as a first target line straight line, and at least one first target line straight line is obtained.

[0087] If there is any second coordinate point in the plurality of second coordinate points on the power receiving side in the strain clamp rectangular frame on the power receiving side, the line straight line corresponding to the second coordinate point in the strain clamp rectangular frame on the power receiving side is taken as a second target line straight line, and at least one second target line straight line is obtained.

[0088] In this embodiment, the line straight line corresponding to the coordinate point that meets the line straight line equation and is in the strain clamp rectangular frame is screened out, which can improve the accuracy of screening the target line straight line. Since some line straight lines are not installed on the cross arm, the line straight lines that affect the accuracy of the cross arm installation angle detection are removed, the target line straight line is screened out, a good data foundation is laid for the later calculation of the first and second angles, and the accuracy of the intelligent detection of the cross arm installation angle is improved.

[0089] The plurality of first coordinate points and the plurality of second coordinate points can be coordinate points on an extension line of each line, and the purpose is to determine whether there is an intersection between the line and the rectangular frame. Only the line with the intersection is the line installed on the cross arm, that is, the target line.

[0090] In some embodiments, the third included angle between the cross arm central axis direction and the positive direction of the X axis is calculated according to the cross arm contour point set, including:

[0091] The centroid of the cross arm is calculated according to the cross arm contour point set.

[0092] The centralization matrix is obtained by centralizing each contour point data in the cross arm contour point set.

[0093] The principal axis direction vector is calculated according to the centralization matrix, and the principal axis direction vector is taken as the cross arm central axis direction vector.

[0094] The third included angle between the cross arm central axis direction vector and the positive direction of the X axis is calculated.

[0095] In this embodiment, due to reasons such as image distortion of the unmanned aerial vehicle, cross arm segmentation model precision, etc., the cross arm contour cannot be guaranteed to be a complete rectangle. Therefore, by centralizing each contour point data in the cross arm contour point set to obtain a centralization matrix, then calculating a principal axis direction vector according to the centralization matrix, and taking the principal axis direction vector as the cross arm central axis direction vector, and finally calculating the third included angle between the cross arm central axis direction vector and the positive direction of the X axis, the accuracy of the cross arm central axis calculation can be improved, thereby improving the intelligent detection accuracy of the cross arm installation angle of the corner rod.

[0096] The centroid of the cross arm can be calculated by summing and averaging all contour point coordinates in the cross arm contour point set.

[0097] In some embodiments, the principal axis direction vector is calculated according to the centralization matrix, including:

[0098] The covariance matrix is constructed according to the centralization matrix.

[0099] The eigenvalues in the covariance matrix are calculated to obtain all eigenvalues.

[0100] The maximum eigenvalue is selected from all eigenvalues, and the target eigenvector is calculated, and the target eigenvector is taken as the principal axis direction vector.

[0101] In this embodiment, the maximum eigenvalue is selected from all eigenvalues, and the target eigenvector is calculated, and the target eigenvector is taken as the principal axis direction vector, which can improve the accuracy of the principal axis direction vector calculation.

[0102] In some embodiments, the maximum eigenvalue is selected from all eigenvalues, the target eigenvector is calculated, including:

[0103] ;

[0104] ;

[0105] wherein, represents the covariance matrix, represents the maximum eigenvalue, represents the unit matrix, represents the target eigenvector.

[0106] In some embodiments, according to at least one first target line and second target line, the first angle between the first target line and the positive direction of the X-axis is calculated, and the second angle between the second target line and the positive direction of the X-axis is calculated, including:

[0107] Obtaining the first number of the first target line, and obtaining the second number of the second target line;

[0108] Summing up the angle between each first target line and the positive direction of the X-axis to obtain the first angle sum;

[0109] Summing up the angle between each second target line and the positive direction of the X-axis to obtain the second angle sum;

[0110] Dividing the first angle sum by the first number to obtain the first angle between the first target line and the positive direction of the X-axis;

[0111] Dividing the second angle sum by the second number to obtain the second angle between the second target line and the positive direction of the X-axis.

[0112] In this embodiment, if there are multiple first target lines and multiple second target lines, the average angle between the multiple first target lines and the multiple second target lines and the positive direction of the X-axis will be obtained, and the average angle is taken as the first angle or the second angle, which 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 cross arm installation angle.

[0113] In some embodiments, the intelligent detection of the cross arm installation angle of the corner rod is performed according to two difference calculation results, including:

[0114] The two difference calculation results are subjected to difference absolute value calculation, and if the difference absolute value is less than a preset value, it indicates that the cross arm installation angle is detected by the intelligent detection of the cross arm installation angle of the corner rod.

[0115] In the embodiment, the intelligent detection of the installation angle of the cross arm of the corner pole is performed by calculating the installation angle of the cross arm of the corner pole according to two difference calculation results, without the need for total station measurement or manual angle measurement throughout the whole process, so that the intelligent detection is fully automated, and the detection efficiency of the installation angle of the cross arm of the corner pole is improved.

[0116] To facilitate the understanding of those skilled in the art, a set of best embodiments is provided below:

[0117] In power line construction and operation, the installation angle of the cross arm of the corner pole directly affects the mechanical stress balance and long-term operation safety of the line. According to the requirements of “Electrical Device Installation Engineering 66kV and Below Overhead Power Line Construction and Acceptance Specification GB50173-2014”, the cross arm of the corner pole must be strictly installed on the angle bisector in the corner direction of the line. If the installation angle is not up to standard, it will lead to uneven distribution of wire tension, accelerate the wear of fittings, and even cause tower collapse accidents in severe cases.

[0118] At present, the detection methods of the installation angle of the cross arm mainly include manual measurement method and image analysis method. The manual measurement method uses the theodolite or total station to measure point by point, which is complex in operation and depends on the experience of technical personnel, and the efficiency is low. The image analysis method uses the protractor software to mark the angle after manually taking photos at a fixed position, and the measurement result is greatly affected by the shooting angle and the experience of personnel, and the repeatability is poor. At the same time, the above methods all need manual detection of each pole, which has low detection efficiency and high labor intensity. In complex terrain or limited observation position, it is often difficult to obtain effective data, so it is difficult to obtain accurate detection results.

[0119] To solve the problems existing in the prior art, the embodiment proposes an intelligent detection method for the installation angle of the cross arm of the corner pole, which aims to automatically identify the cross arm in the image, calculate other materials and equipment required for the installation angle of the cross arm through deep learning technology, and post-process the image, so as to calculate the data required for the process point of the installation angle of the cross arm, realize the accurate measurement of the installation angle of the cross arm through contour recognition, mathematical processing and morphological analysis, and solve the deficiencies of the installation angle of the cross arm of the corner pole in the prior art. The invention automatically calculates the installation angle of the cross arm of the corner pole through deep learning algorithm and image processing, without the need for total station measurement or manual angle measurement, which not only solves the subjectivity in the measurement process of manual measurement, but also greatly improves the measurement speed. At the same time, cooperating with the automatic image acquisition of the unmanned aerial vehicle, the situation that the detection cannot be performed due to complex terrain or limited observation position is avoided, the batch detection of the process points of the whole line is realized, and the detection efficiency and scene applicability are greatly improved.

[0120] The technical scheme of the embodiment specifically includes the following contents:

[0121] (1) The camera carried by the unmanned aerial vehicle collects the image sample data of the angle pole. The angle is preferably selected from the front 90° of the pole, and secondly from the horizontal line direction of the pole 2 / 3 height. Based on the instance segmentation model framework, the instance segmentation model of the cross arm and the strain clamp is constructed to realize the instance segmentation of the cross arm and the strain clamp, and the cross arm contour point set and the strain clamp contour point set are obtained. Then, the maximum value and the minimum value of all contour points in the strain clamp contour point set are obtained as the coordinates of the left upper and right lower points of the rectangular frame, respectively. According to the coordinates of the two points, the rectangular frame of the strain clamp is constructed. The instance segmentation results of the cross arm and the strain clamp are shown in . Figure 2

[0122] It should be noted that the instance segmentation model of the present embodiment can use the instance segmentation model commonly used in the prior art, and the present embodiment will not be described in detail.

[0123] (2) Based on the polygon region surrounded by multiple strain clamps in Figure 2 , the power transmission side of the left boundary and the power receiving side of the right boundary of the region are selected as the left and right line direction calculation ranges, respectively. Image enhancement, edge detection and Hough transform straight line detection are used to obtain the starting point coordinates and end point coordinates of each wire in the line. The line straight line detection result is shown in Figure 3 , Figure 3 The dashed line in

[0124] (1);

[0125] (2);

[0126] Wherein, represents the number of power transmission side line straight lines, represents the number of power receiving side line straight lines, and may be equal or not equal, which needs to be determined according to the situation presented in the collected angle pole image, and are the sets of cross arm power transmission side and power receiving side line straight lines (the set of cross arm power transmission side line straight lines is the first line coordinate point set, and the set of cross arm power receiving side line straight lines is the second line coordinate point set), , and​​​​​​​​ Two coordinate points on the line straight line, two coordinate points include the starting coordinate point and the terminal coordinate point.

[0127] It should be noted that the image enhancement, edge detection and Hough transform straight line detection of the embodiment are all adopted by the prior art known to those skilled in the art, and the embodiment will not be described in detail.

[0128] (3) Based on the position relationship between the line straight line and the rectangular frame where the strain clamp is located, the target line straight line (including at least one first target line straight line and second target line straight line) is screened out, and it is ensured that the extension line of the line straight line and the rectangular frame where the strain clamp is located have intersection points, as follows:

[0129] (3);

[0130] (4);

[0131] Wherein, formula (3) is a line straight line equation, To meet the line straight line equation (3) for any coordinate point, formula (4) is a strain clamp rectangular frame boundary, And The coordinates of the upper left and lower right of the strain clamp rectangular frame are respectively. By combining the above equations, there are Satisfy That is, the line straight line and the rectangular frame where the strain clamp is located have intersection points. Satisfying formula (3) and formula (4) can indicate that the line straight line and the rectangular frame have intersection points, which is the target line straight line that needs to be retained in the embodiment. The target line straight line screening result is shown in Figure 4 Figure 4 The dashed line in the above figure is the target line straight line detected.

[0132] (4) Calculate the direction of the cross arm center axis. Due to the distortion of the unmanned aerial vehicle shooting image, the cross arm segmentation model precision and other reasons, the cross arm contour cannot guarantee to be a complete rectangle. In order to improve the calculation precision of the cross arm center axis, the principal component analysis method is adopted to calculate the principal axis direction of the cross arm as the center axis direction, and the specific calculation steps are as follows:

[0133] 1) The cross arm contour point set obtained in step (1) contains contour point coordinates , as follows:

[0134] (5);

[0135] 2) Calculate the centroid of the cross arm , that is, summing up the contour point coordinates and then averaging to obtain the average coordinate value​ as follows:

[0136] (6);

[0137] 3) Centralize each profile point data of the cross arm profile point set to form a centralized matrix, as follows:

[0138] (7);

[0139] 4) Calculate the principal axis direction vector. First, construct the covariance matrix as follows:

[0140] (8);

[0141] wherein, , , .

[0142] Calculate the eigenvalues of the covariance matrix, as follows:

[0143] (9);

[0144] wherein, denotes the determinant.

[0145] All eigenvalues can be obtained by the above formula , and the maximum eigenvalue is selected.

[0146] (10);

[0147] (11);

[0148] Calculate the angle between the principal axis direction vector and the positive direction of the X axis (i.e., the third angle), as follows:

[0149] (12);

[0150] wherein, denotes the direction vector in the principal axis direction vector, denotes the direction vector in the principal axis direction vector. The direction of the central axis of the cross arm is shown as follows: Figure 5

[0151] (5) Calculate the average angle ​(i.e., the first included angle) and the average included angle (i.e., the second included angle).

[0152] (13);

[0153] (14);

[0154] 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 .

[0155] (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:

[0156] (15);

[0157] (16);

[0158] (17);

[0159] 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°.

[0160] Reference Figure 6 This 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:

[0161] The instance segmentation unit 601 is configured to perform instance segmentation on the collected angle pole image sample data to obtain a cross arm contour point set and a plurality of strain clamp contour point sets;

[0162] The first construction unit 602 is configured to construct a strain clamp rectangular frame corresponding to each strain clamp contour point set according to the plurality of strain clamp contour point sets.

[0163] The second construction unit 603 is configured to construct a polygonal region enveloped by the plurality of strain clamps, and construct a first line coordinate point set according to the starting point coordinates and the end point coordinates of each line straight line on the power supply side of the polygonal region, and construct a second line coordinate point set according to the starting point coordinates and the end point coordinates of each line straight line on the power receiving side of the polygonal region.

[0164] The straight line screening unit 604 is configured to screen at least one first target line straight line and a 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.

[0165] The first calculation unit 605 is configured to calculate a first included angle between the first target line straight line and the positive direction of the X-axis, and calculate a second included angle between the second target line straight line and the positive direction of the X-axis, according to the at least one first target line straight line and the second target line straight line.

[0166] The second calculation unit 606 is configured to calculate a third included angle between the direction of the cross arm central axis and the positive direction of the X-axis according to the cross arm contour point set.

[0167] The intelligent detection unit 607 is configured to perform difference calculation on the first included angle and the second included angle respectively with the third included angle to obtain two difference calculation results, and perform intelligent detection on the installation angle of the cross arm of the angle pole according to the two difference calculation results.

[0168] It should be noted that, since the intelligent detection system of the installation angle of the cross arm of the angle pole in the embodiment and the intelligent detection method of the installation angle of the cross arm of the angle pole described above are based on the same inventive concept, the corresponding contents in the method embodiment are also applicable to the system embodiment, which will not be described in detail here.

[0169] With reference to Figure 7 The electronic device provided in the embodiment of the present application includes:

[0170] at least one memory;

[0171] at least one processor;

[0172] at least one program;

[0173] The program is stored in the memory, and the processor executes at least one program to implement the intelligent detection method of the installation angle of the corner pole cross arm described above.

[0174] The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a vehicle-mounted computer, and the like.

[0175] The electronic device of the embodiment of the present application is described in detail below.

[0176] The processor 1600 can be implemented in a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, and the like, and is used to execute related programs to implement the technical solutions provided by the embodiments of the present application.

[0177] The memory 1700 can be implemented in the form of a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1700 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 1700 and are called and executed by the processor 1600 to implement the intelligent detection method of the installation angle of the corner pole cross arm.

[0178] The input / output interface 1800 is used to realize information input and output.

[0179] The communication interface 1900 is used to realize the communication interaction between the device and other devices. The communication can be realized by a wired manner (for example, a USB, a network cable, and the like) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, and the like).

[0180] The bus 2000 is used to transmit information between various components (for example, the processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900) of the device.

[0181] The processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900 are connected to each other through the bus 2000 to realize the communication connection between them inside the device.

[0182] The embodiment of the present disclosure further provides a storage medium, which is a computer readable storage medium, and stores computer executable instructions for causing a computer to execute the intelligent detection method for the installation angle of the corner pole cross arm.

[0183] The memory, as a non-transitory computer readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0184] The embodiments described in the embodiments of the present disclosure are for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0185] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present disclosure, and can include more or fewer steps than the figures, or combine certain steps, or different steps.

[0186] The device embodiments described above are merely schematic, and the units described as separate components can or can not be physically separated, that is, can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the embodiments of the present disclosure.

[0187] Those skilled in the art can understand that all or some steps in the above disclosed method, the functional modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0188] The terms "first", "second", "third", "fourth", and the like in the description of this application and in the claims hereof, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so termed herein is solely for the convenience of the reader and does not limit the scope of the application. It is also to be understood that the description and examples in this application are intended to cover all possible combinations where any of the several elements can represent one or more elements.

[0189] It should be understood that, in the application, "at least one" means one or more, "multiple" means two or more. "And / or" is used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one 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.

[0190] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0191] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the embodiment of the application.

[0192] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0193] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media. The embodiments of the present application are described in detail above in combination with the drawings, but the present application is not limited to the above embodiments, and various changes can be made within the knowledge range of those skilled in the art without departing from the purpose of the present application.

[0194] The embodiments of the present application are described in detail above in combination with the drawings, but the present application is not limited to the above embodiments, and various changes can be made within the knowledge range of those skilled in the art without departing from the purpose of the present application.

Claims

1. An intelligent detection method for the installation angle of a corner pole cross arm, characterized in that, The method comprises: instance segmentation is performed on the collected angle pole image sample data to obtain a cross arm contour point set and a plurality of strain clamp contour point sets; a strain clamp rectangular frame corresponding to each strain clamp contour point set is constructed according to the plurality of strain clamp contour point sets; a polygonal region enveloped by the plurality of strain clamps is constructed, a first line coordinate point set is constructed according to the starting point coordinates and the end point coordinates of each line straight line on the power supply side of the polygonal region, and a second line coordinate point set is constructed according to the starting point coordinates and the end point coordinates of each line straight line on the power receiving side of the polygonal region; at least one first target line straight line and a second target line straight line are screened out according to the first line coordinate point set, the second line coordinate point set and the strain clamp rectangular frame; a first included angle between the first target line straight line and the positive direction of the X-axis is calculated, and a second included angle between the second target line straight line and the positive direction of the X-axis is calculated according to at least one of the first target line straight line and the second target line straight line; a third included angle between the direction of the cross arm central axis and the positive direction of the X-axis is calculated according to the cross arm contour point set; the first included angle and the second included angle are respectively subtracted from the third included angle to obtain two subtraction calculation results, and intelligent detection of the cross arm installation angle of the angle pole is performed according to the two subtraction calculation results, which comprises: the two subtraction calculation results are subjected to absolute value subtraction, and if the absolute value of the subtraction is less than a preset value, it is indicated that the cross arm installation angle passes the intelligent detection of the cross arm installation angle of the angle pole.

2. The intelligent detection method for the installation angle of the corner pole cross arm according to claim 1, characterized in that, The screening of at least one first target line straight line and a 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 comprises: a first line straight line equation is constructed according to the coordinate points in the first line coordinate point set; a second line straight line equation is constructed according to the coordinate points in the second line coordinate point set; a plurality of first coordinate points of each line straight line corresponding to the first line coordinate point set are determined according to the first line straight line equation; a plurality of second coordinate points of each line straight line corresponding to the second line coordinate point set are determined according to the second line straight line equation; if any first coordinate point in the plurality of first coordinate points is in the strain clamp rectangular frame, the line straight line corresponding to the first coordinate point in the strain clamp rectangular frame is taken as the first target line straight line to obtain at least one first target line straight line; if any second coordinate point in the plurality of second coordinate points is in the strain clamp rectangular frame, the line straight line corresponding to the second coordinate point in the strain clamp rectangular frame is taken as the second target line straight line to obtain at least one second target line straight line.

3. The intelligent detection method for the installation angle of the corner pole cross arm according to claim 1, characterized in that, The calculation of the third included angle between the direction of the cross arm central axis and the positive direction of the X-axis according to the cross arm contour point set comprises: the centroid of the cross arm is calculated according to the cross arm contour point set; the centering matrix is obtained by centering each contour point data in the cross arm contour point set; According to the central matrix, a principal axis direction vector is calculated, and the principal axis direction vector is taken as a cross arm central axis direction vector; A third included angle between the cross arm central axis direction vector and the positive direction of the X axis is calculated.

4. The intelligent detection method for the installation angle of the corner pole cross arm according to claim 3, characterized in that, The calculation of the principal axis direction vector according to the central matrix comprises: According to the central matrix, a covariance matrix is constructed; Eigenvalues in the covariance matrix are calculated to obtain all eigenvalues; The maximum eigenvalue is selected from the all eigenvalues, and a target eigenvector is calculated, and the target eigenvector is taken as the principal axis direction vector.

5. The intelligent detection method for the installation angle of the corner pole cross arm according to claim 4, characterized in that, The calculation of the target eigenvector from the maximum eigenvalue comprises: ； ； wherein denotes the covariance matrix, denotes the largest eigenvalue, denotes the identity matrix, denotes the target eigenvector.

6. The intelligent detection method for the installation angle of the corner pole cross arm according to claim 1, characterized in that, The calculation of the first included angle and the second included angle according to at least one of the first target line straight line and the second target line straight line comprises: A first quantity of the first target line straight lines is obtained, and a second quantity of the second target line straight lines is obtained; The included angles between each of the first target line straight lines and the positive direction of the X axis are summed to obtain a first included angle sum; The included angles between each of the second target line straight lines and the positive direction of the X axis are summed to obtain a second included angle sum; The first included angle sum is divided by the first quantity to obtain the first included angle of the first target line straight line with the positive direction of the X axis; The second included angle sum is divided by the second quantity to obtain the second included angle of the second target line straight line with the positive direction of the X axis.

7. An intelligent detection system for the installation angle of a corner pole cross arm, characterized by, The system comprises: An instance segmentation unit is configured to perform instance segmentation on the collected angle rod image sample data to obtain a cross arm contour point set and a plurality of strain clamp contour point sets; A first construction unit is configured to construct a strain clamp rectangular frame corresponding to each strain clamp contour point set according to the plurality of strain clamp contour point sets; A second construction unit is configured to construct a polygonal region enveloped by the plurality of strain clamps, construct a first line coordinate point set according to the starting point coordinates and the end point coordinates of each line straight line on the power supply side of the polygonal region, and construct a second line coordinate point set according to the starting point coordinates and the end point coordinates of each line straight line on the power receiving side of the polygonal region; A straight line screening unit is configured to screen at least one first target line straight line and a 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; A first calculation unit is configured to calculate a first included angle of the first target line straight line with the positive direction of the X axis and a second included angle of the second target line straight line with the positive direction of the X axis according to at least one of the first target line straight line and the second target line straight line; A second calculation unit is configured to calculate a third included angle between a cross arm central axis direction and the positive direction of the X axis according to the cross arm contour point set; An intelligent detection unit is configured to perform difference calculation on the first included angle and the second included angle with the third included angle respectively to obtain two difference calculation results, and perform intelligent detection on the installation angle of the cross arm of the angle rod according to the two difference calculation results, comprising: The two difference calculation results are subjected to difference absolute value calculation, and if the difference absolute value is less than a preset value, it is indicated that the cross arm installation angle is detected intelligently through the corner rod cross arm installation angle.

8. An electronic device, comprising: The control system comprises at least one control processor and a memory connected in communication with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to perform the intelligent detection method of the corner rod cross arm installation angle according to any one of claims 1 to 6.

9. 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 of the corner rod cross arm installation angle according to any one of claims 1 to 6.

Images