CN117953434A - Intelligent gateway-based method and system for monitoring external damage of power transmission line - Google Patents
Intelligent gateway-based method and system for monitoring external damage of power transmission line Download PDFInfo
- Publication number
- CN117953434A CN117953434A CN202410354328.7A CN202410354328A CN117953434A CN 117953434 A CN117953434 A CN 117953434A CN 202410354328 A CN202410354328 A CN 202410354328A CN 117953434 A CN117953434 A CN 117953434A
- Authority
- CN
- China
- Prior art keywords
- edge
- line
- edge line
- power transmission
- effective
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000012544 monitoring process Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000012216 screening Methods 0.000 claims abstract description 13
- 230000009467 reduction Effects 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims description 64
- 230000006870 function Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 2
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 239000000758 substrate Substances 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a transmission line external damage monitoring method and system based on an intelligent gateway. The method comprises the steps of obtaining a gray level image of a power transmission line, obtaining a frame difference image of a current frame gray level image and an adjacent previous frame gray level image, and screening out effective edge lines according to the length of the edge lines; acquiring the actual skewness of the effective edge line according to the distance between the edge pixel point and other effective edge lines and the distance between the edge pixel point and the line segment of the corresponding effective edge line after the dimension reduction; determining target edge pixel points according to the number of the edge pixel points in the edge pixel point field; and screening out a target edge line according to the number, the length and the actual skewness of the target edge pixel points of the effective edge line, and monitoring the external damage of the current power transmission line. According to the method, the target edge line is obtained, so that the power transmission line is accurately marked, and the damage degree of external force to the power transmission line is accurately monitored in real time with high efficiency.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a transmission line external damage monitoring method and system based on an intelligent gateway.
Background
The transmission line works in a field environment for a long time, is subjected to the influence of severe weather, is also influenced by external force such as man-made force, is easy to damage, causes power to be unable to be used normally, and is harmful. Therefore, the external damage to the power transmission line needs to be accurately monitored in real time, and the power transmission line is processed in time, so that the power transmission line is ensured to work normally.
In the existing method, a visual detection system is used for collecting an image of the power transmission line in real time, the image of the power transmission line is automatically marked through a neural network, the marked power transmission line area is identified, and the condition that the power transmission line is damaged by external force is monitored in real time. However, in actual situations, when the power transmission line is damaged by external force, the power transmission line can shake, so that blurring is generated, the power transmission line area cannot be accurately marked, and then the real-time monitoring cannot be accurately and efficiently performed on the damage of the external force to the power transmission line.
Disclosure of Invention
In order to solve the technical problems that the power transmission line is not accurately marked due to the ambiguity generated by shaking of the power transmission line, and the external force damage to the power transmission line cannot be accurately and efficiently monitored in real time, the invention aims to provide a power transmission line external force damage monitoring method and system based on an intelligent gateway, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for monitoring external damage to a power transmission line based on an intelligent gateway, where the method includes the following steps:
acquiring a gray image of each frame of power transmission line;
Acquiring a target evaluation value of each edge pixel point according to the gray value of each edge pixel point on each edge line in each frame of gray image and the gradient direction change of the adjacent next edge pixel point;
Acquiring a frame difference image according to the gray level image of the current frame and the gray level image of the adjacent previous frame; screening out effective edge lines according to the length of each edge line in the frame difference image; correcting the deviation of the target evaluation value of each effective edge line according to the distance between each edge pixel point on each effective edge line in the frame difference image and other effective edge lines and the distance between each edge pixel point and the line segment of the corresponding effective edge line pca after the dimension reduction, and obtaining the actual deviation of each effective edge line;
Constructing a neighborhood of each edge pixel point on each effective edge line, and determining a target edge pixel point on each effective edge line according to the number of the edge pixel points in the neighborhood; acquiring a selected evaluation value of each effective edge line according to the number, the length and the actual skewness of the target edge pixel points of each effective edge line;
And screening out a target edge line according to the selected evaluation value, and monitoring the external damage to the current power transmission line according to the target edge line.
Further, the calculation formula of the target evaluation value is:
；
in the method, in the process of the invention, The target evaluation value of the ith edge pixel point on the L-th edge line; /(I)The gray value of the ith edge pixel point on the L-th edge line; /(I)The gray value average value of all edge pixel points on the L-th edge line; /(I)An included angle in the gradient direction between the ith edge pixel point and the (i+1) th edge pixel point on the L-th edge line; cos is a cosine function; /(I)Is a first preset constant, which is greater than 0; /(I)As a function of absolute value.
Further, the method for acquiring the frame difference image comprises the following steps:
And subtracting the gray level image of the previous frame from the gray level image of the current frame to perform frame difference processing, and obtaining a frame difference image.
Further, the method for screening the effective edge line according to the length of each edge line in the frame difference image comprises the following steps:
Performing morphological closing operation on the edge line in the frame difference image to obtain the processed edge line as a characteristic edge line;
Taking the number of edge pixel points on each characteristic edge line as the length of each characteristic edge line;
the characteristic edge lines are arranged according to the sequence from the large length to the small length, and a characteristic edge line sequence is obtained;
acquiring the length difference between each characteristic edge line and the adjacent next characteristic edge line in the characteristic edge line sequence as a first difference;
dividing the characteristic edge line sequence into two parts;
and taking all the characteristic edge lines in the partial characteristic edge line sequence with the maximum length as effective edge lines.
Further, the calculation formula of the actual skewness is as follows:
；
in the method, in the process of the invention, The actual skewness of the K effective edge line; /(I)The total number of edge pixel points on the K effective edge line; /(I)The distance between the mth edge pixel point on the kth effective edge line and any other effective edge line; min is a function taking the minimum value; /(I)The distance between the mth edge pixel point on the kth effective edge line and the line segment of the kth effective edge line pca after dimension reduction is set; /(I)Is a second preset constant, greater than 0; /(I)The target evaluation value of the mth edge pixel point on the Kth effective edge line; /(I)The average value of the target evaluation values of all edge pixel points on the K effective edge line; The standard deviation of the target evaluation value of the edge pixel point on the K-th effective edge line.
Further, the method for obtaining the target edge pixel point comprises the following steps:
And when the number of the edge pixels in the neighborhood of the edge pixels is larger than the neighborhood side length, taking the corresponding edge pixels as target edge pixels.
Further, the calculation formula of the selected evaluation value is as follows:
；
in the method, in the process of the invention, Selecting an evaluation value for the K effective edge line; /(I)The number of target edge pixel points of the K effective edge line; /(I)The third preset quantity is more than 0; /(I)The total number of edge pixel points on the K effective edge line; /(I)The actual skewness of the K effective edge line; /(I)As a function of absolute value; e is a natural constant.
Further, the method for screening the target edge line according to the selected evaluation value comprises the following steps:
And carrying out normalization processing on the selected evaluation value, and taking the corresponding effective edge line as a target edge line when the normalized selected evaluation value is greater than or equal to a preset selected evaluation value threshold value.
Further, the method for monitoring the external damage to the current power transmission line according to the target edge line comprises the following steps:
Constructing a minimum circumscribed rectangle of a target edge line on an edge line corresponding to a gray level image of a current frame, and taking the minimum circumscribed rectangle as a target area;
and inputting the target area into a trained neural network for identification, and monitoring the damage of external force to the current power transmission line.
In a second aspect, another embodiment of the present invention provides an intelligent gateway-based power transmission line external damage monitoring system, including: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any one of the methods described above when executing the computer program.
The invention has the following beneficial effects:
According to the gray value of each edge pixel point on each edge line in each frame of gray image and the gradient direction change of the adjacent next edge pixel point, acquiring a target evaluation value of each edge pixel point, and preliminarily judging the possibility that each edge pixel point is a corresponding edge pixel point of the power transmission line, so as to prepare for the follow-up determination of the power transmission line area; in order to improve the efficiency of determining the corresponding edge line of the power transmission line, further obtaining a frame difference image according to the gray level image of the current frame and the gray level image of the adjacent previous frame, and removing the interference of the corresponding edge line of the fixed object; further, according to the length of each edge line in the frame difference image, effective edge lines are screened out, edge line interference caused by noise is avoided, and meanwhile the efficiency of determining the power transmission line area is improved; in order to accurately screen out the edge lines corresponding to the power transmission lines, further, correcting the deviation of the target evaluation value of each effective edge line according to the distance between each edge pixel point on each effective edge line in the frame difference image and other effective edge lines and the distance between each edge pixel point and the line segment of the corresponding effective edge line pca after dimension reduction, accurately acquiring the actual deviation of each effective edge line, and preparing for accurately determining the edge line of the power transmission line in the follow-up process; further constructing a neighborhood of each edge pixel point on each effective edge line, determining a target edge pixel point on each effective edge line according to the number of the edge pixel points in the neighborhood, indirectly showing the branching condition of each effective edge line, and further preparing for accurately determining the edge line corresponding to the power transmission line; and then according to the number, the length and the actual skewness of the target edge pixel points of each effective edge line, the selection evaluation value of each effective edge line is obtained, the target edge line is accurately screened out, and then according to the target edge line, the power transmission line region in the gray level image of the current frame is accurately marked, the external damage to the current power transmission line is accurately monitored, the power transmission line is timely processed, the normal operation of electric power is ensured, and the occurrence of hazard accidents is avoided.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for monitoring external damage to a power transmission line based on an intelligent gateway according to an embodiment of the present invention;
FIG. 2 is an edge image of a frame of gray scale image according to one embodiment of the present invention;
fig. 3 is a frame difference image according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects thereof of the method and system for monitoring the external damage of the power transmission line based on the intelligent gateway according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of an intelligent gateway-based power transmission line external damage monitoring method, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of a method for monitoring external damage to a power transmission line based on an intelligent gateway according to an embodiment of the invention is shown, and the method includes the following steps:
Step S1: and acquiring a gray image of each frame of power transmission line.
Specifically, the monitoring equipment is arranged on a tower connected with the power transmission line, video of the power transmission line is obtained, the video of the power transmission line is transmitted to the central computer through equipment such as a communication gateway and the like, and each frame of power transmission line image is processed. In the embodiment of the invention, the video acquisition frequency is set to 24 frames per second, and an implementer can set the video acquisition frequency according to actual conditions without limitation. In order to facilitate the subsequent analysis, the gray level processing is performed on each frame of power transmission line image, so as to obtain the gray level image of each frame of power transmission line, and meanwhile, the edge line in each frame of gray level image is obtained through a canny edge detection algorithm, as shown in fig. 2, the edge image of one frame of gray level image is obtained. The graying processing and the canny edge detection algorithm are both the prior art, and are not described in detail.
The specific scene of the embodiment of the invention is as follows: in order to monitor whether the power transmission line is damaged by external force in real time, the embodiment of the invention analyzes the gray level image of the current frame, and at least one gray level image exists before the gray level image of the current frame.
The aim of the embodiment of the invention is as follows: when the transmission line is damaged by external force, shake can occur, blurring can be formed in the gray level image, so that the transmission line cannot be accurately marked, further, the damage degree of the external force received by the transmission line cannot be accurately analyzed, each transmission line cannot be processed in time, and safety accidents are easy to occur. Considering that when the power transmission line is damaged by external force, shaking occurs, so that difference can be generated between two adjacent frames of gray images, therefore, according to the gray image of the current frame and the gray image of the previous frame, a frame difference image is obtained, according to the characteristics of flatness and slimness of the power transmission line, edge lines in the frame difference image are analyzed, target edge lines which are corresponding to the edge lines of the power transmission line are screened out, further, the corresponding edge lines of the power transmission line in the gray image of the current frame are determined, the power transmission line area is determined, marking is performed accurately, and the external force damage to the current power transmission line is monitored accurately and efficiently.
Step S2: and acquiring a target evaluation value of each edge pixel point according to the gray value of each edge pixel point on each edge line in each frame of gray image and the gradient direction change of the adjacent next edge pixel point.
Specifically, due to the characteristic that the power transmission line is straight, the gradient directions of the adjacent edge points on the corresponding edge lines of the power transmission line are more consistent, so that when the gradient direction included angle between one edge pixel point and the adjacent next edge pixel point is smaller, the edge pixel point is more likely to be the edge pixel point corresponding to the power transmission line. Meanwhile, as can be seen from fig. 2, the power transmission line is suspended between the towers, and the ground information and the interference information of the towers are less, and the gray values of the edge pixel points corresponding to the power transmission line are similar, so when the difference between the gray value of one edge pixel point and the gray value average value of the edge pixel point used on the edge line is smaller, the more likely that the edge pixel point is the edge pixel point corresponding to the power transmission line is indicated. And further, according to the gray value of each edge pixel point on each edge line in each frame gray image and the gradient direction change of the adjacent next edge pixel point, acquiring a target evaluation value of each edge pixel point, wherein the larger the target evaluation value is, the more likely the corresponding pixel point is the edge pixel point corresponding to the power transmission line.
Taking the ith edge pixel point on the ith edge line in the gray level image of the current frame as an example, a calculation formula for obtaining the target evaluation value of the ith edge pixel point on the ith edge line is as follows:
；
in the method, in the process of the invention, The target evaluation value of the ith edge pixel point on the L-th edge line; /(I)The gray value of the ith edge pixel point on the L-th edge line; /(I)The gray value average value of all edge pixel points on the L-th edge line; /(I)An included angle in the gradient direction between the ith edge pixel point and the (i+1) th edge pixel point on the L-th edge line; cos is a cosine function; /(I)Is a first preset constant, which is greater than 0; /(I)As a function of absolute value.
Embodiments of the invention willSet to 1, avoid denominator to 0, and the practitioner can set/>, according to the actual situationIs not limited herein.
It should be noted that the number of the substrates,The smaller the description/>And/>The more equal,/>The larger the/>The larger the ith edge pixel point is, the more likely the ith edge pixel point is the edge pixel point corresponding to the power transmission line; /(I)The smaller the gradient direction of the ith edge pixel point and the (i+1) th edge pixel point on the L-th edge line is, the more consistent is the gradient direction of the ith edge pixel point and the (i+1) th edge pixel point is, and the greater the gradient direction of the ith edge pixel point isSmaller,/>The larger the/>The larger the ith edge pixel point is, the more likely the ith edge pixel point is the edge pixel point corresponding to the power transmission line; thus,/>The larger the L-th edge line is, the more likely the L-th edge line is the corresponding edge line of the power transmission line.
According to the method for acquiring the target evaluation value of the ith edge pixel point on the L-th edge line in the gray level image of the current frame, acquiring the target evaluation value of each edge pixel point in each gray level image. It should be noted that, the last edge pixel point of each edge line does not have an adjacent next edge pixel point, and therefore, the last edge pixel point of each edge line is not analyzed.
Step S3: acquiring a frame difference image according to the gray level image of the current frame and the gray level image of the adjacent previous frame; screening out effective edge lines according to the length of each edge line in the frame difference image; and correcting the deviation of the target evaluation value of each effective edge line according to the distance between each edge pixel point on each effective edge line in the frame difference image and other effective edge lines and the distance between each edge pixel point and the line segment of the corresponding effective edge line pca after the dimension reduction, and obtaining the actual deviation of each effective edge line.
Specifically, in order to analyze the damage of external force to the power transmission line in real time, the embodiment of the invention analyzes the gray level image of the current frame. When the transmission line is damaged by external force, the transmission line can generate displacement, and meanwhile, the influence of the external force on the transmission line is not constant, so that when the transmission line in the gray level image of the current frame is positioned, interference generated by a plurality of similar edge lines can exist, and the transmission line cannot be accurately positioned. In order to accurately and efficiently locate a power transmission line area in a gray level image of a current frame, the embodiment of the invention subtracts a gray level image of a previous frame from the gray level image of the current frame to perform frame difference processing, and obtains a frame difference image. The tower in the gray level image and other objects on the ground belong to fixed objects, and cannot be moved in two adjacent frames of gray level images, and can be removed in the frame difference image. When the frame difference image does not contain the edge pixel points, the current power transmission line is not affected by external force. When a plurality of edge lines exist in the frame difference image, the current power transmission line is indicated to be influenced by external force or noise. Fig. 3 is a frame difference image of a transmission line affected by an external force. Because of the interference of the background, the situation that the edge line is disconnected exists in the frame difference image, so that the edge line cannot be accurately analyzed, and therefore, the embodiment of the invention carries out morphological closing operation on the edge line in the frame difference image, and ensures the integrity of the edge line in the frame difference image. The morphological closing operation is a well-known technique, and will not be described in detail. In order to reduce interference caused by edge line analysis corresponding to a power transmission line due to noise interference, and improve efficiency of accurately positioning the edge line corresponding to the power transmission line, the embodiment of the invention screens out effective edge lines in a frame difference image according to the length of each edge line in the frame difference image, and removes the edge lines caused by noise in the frame difference image.
Preferably, the method for acquiring the effective edge line is as follows: performing morphological closing operation on the edge line in the frame difference image to obtain the processed edge line as a characteristic edge line; and taking the number of edge pixel points on each characteristic edge line as the length of each characteristic edge line, wherein the larger the length is, the more likely the corresponding characteristic edge line is the edge line corresponding to the power transmission line is. The characteristic edge lines are arranged according to the sequence from the large length to the small length, and a characteristic edge line sequence is obtained; acquiring the length difference between each characteristic edge line and the adjacent next characteristic edge line in the characteristic edge line sequence as a first difference; the first difference must be greater than or equal to 0. Wherein the last feature edge line in the sequence of feature edge lines does not have an adjacent next feature edge line, and therefore the last feature edge line in the sequence of feature edge lines is not analyzed. As can be seen from fig. 3, the difference in length between the edge line corresponding to the power transmission line and the edge line caused by noise is very large, so that the two feature edge lines corresponding to the largest first difference are divided, and the feature edge line sequence is divided into two parts; and (3) taking all the characteristic edge lines in the partial characteristic edge line sequence with the maximum length as effective edge lines, defaulting the characteristic edge lines in the rest part of characteristic edge line sequences to noise edge lines, and removing the noise edge lines from the frame difference image, namely filling the gray value of the edge pixel point corresponding to the noise edge lines to be 0. When at least two maximum first differences exist, segmentation is performed between two feature edge lines corresponding to the first-occurring maximum first differences.
The target evaluation value of each edge pixel point on the edge line corresponding to the same power transmission line should be larger and similar, so that the deviation of the target evaluation value of the edge line corresponding to the same power transmission line should be smaller, wherein the method for obtaining the deviation is a known technology and will not be described in detail. Considering that the line transmission circuit which shakes can generate blurring and cause a plurality of effective edge lines to be generated, the embodiment of the invention obtains the distance between each edge pixel point on each effective edge line in the frame difference image and other effective edge lines as the first distance. When the minimum first distance is larger, the interference of other effective edges on the corresponding edge pixel points is smaller, the occupation ratio of the corresponding edge pixel points in acquiring the skewness is larger, and the skewness of the corresponding edge lines is more accurate. In order to further accurately acquire the skewness of the effective edge lines, the embodiment of the invention carries out dimension reduction processing on each effective edge line through a principal component analysis algorithm (PRINCIPAL COMPONENT ANALYSIS, pca) to acquire line segments of each effective edge line after corresponding dimension reduction. And acquiring the distance between each edge pixel point on each effective edge line and the line segment of the corresponding effective edge line after dimension reduction as a second distance, wherein the smaller the second distance is, the more stable the corresponding effective edge line is, and the more likely the corresponding effective edge line is the edge line corresponding to the line transmission circuit. And further, the ratio of the first distance to the second distance is obtained, the skewness of the effective edge lines is corrected, and the actual skewness of each effective edge line is obtained. The principal component analysis algorithm and the method for obtaining the distance between the points and the lines are known techniques, and will not be described in detail.
Taking the kth effective edge line as an example, a calculation formula for obtaining the actual skewness of the kth effective edge line is as follows:
；
in the method, in the process of the invention, The actual skewness of the K effective edge line; /(I)The total number of edge pixel points on the K effective edge line; /(I)The distance between the mth edge pixel point on the kth effective edge line and any other effective edge line; min is a function taking the minimum value; /(I)The distance between the mth edge pixel point on the kth effective edge line and the line segment of the kth effective edge line pca after dimension reduction is set; /(I)Is a second preset constant, greater than 0; /(I)The target evaluation value of the mth edge pixel point on the Kth effective edge line; /(I)The average value of the target evaluation values of all edge pixel points on the K effective edge line; The standard deviation of the target evaluation value of the edge pixel point on the K-th effective edge line.
Embodiments of the invention willSet to 1, avoid denominator to 0, and the practitioner can set/>, according to the actual situationIs not limited herein.
It should be noted that the number of the substrates,The larger the target evaluation value is, the smaller the interference of the mth edge pixel point on the Kth effective edge line to other effective edge lines is, the more accurate the target evaluation value of the mth edge pixel point on the Kth effective edge line is; the smaller the pixel point is, the more likely the pixel point of the mth edge on the K effective edge line is the pixel point corresponding to the power transmission line is; thus,/> The larger the target evaluation value of the mth edge pixel point on the Kth effective edge line is, the more accurate the target evaluation value is, byCorrecting the skewness of the K-th effective edge line so as to/>The more accurate. Wherein/>The more 0 is trended to, the more stable the target evaluation value of each edge pixel point on the Kth effective edge line is, the more likely the Kth effective edge line is the edge line corresponding to the power transmission line.
And acquiring the actual skewness of each effective edge line according to the method for acquiring the actual skewness of the K effective edge line.
Step S4: constructing a neighborhood of each edge pixel point on each effective edge line, and determining a target edge pixel point on each effective edge line according to the number of the edge pixel points in the neighborhood; and acquiring a selected evaluation value of each effective edge line according to the number, the length and the actual skewness of the target edge pixel points of each effective edge line.
Specifically, a method is constructed by taking each edge pixel point on each effective edge line as the centerThe size of the neighborhood may be set by the practitioner according to the actual situation, and is not limited herein. No analysis is performed for the first edge pixel, the second edge pixel, the penultimate edge pixel, and the penultimate edge pixel of each effective edge line. The known line circuits are straight, so the number of edge pixels in each field should be consistent with the edge length of the neighborhood, i.e. the number of edge pixels in the neighborhood should be 5. When the number of the edge pixel points in a certain area is larger than the neighborhood side length, the fact that edge branches possibly exist in the neighborhood of the corresponding edge pixel points is indicated, and the lower the corresponding effective edge line is, the less likely the corresponding edge line is the edge line of the power transmission line. In order to accurately analyze the effective edge lines, when the number of edge pixel points in the neighborhood of the edge pixel points is larger than the neighborhood side length, the corresponding edge pixel points are used as target edge pixel points, and when the target edge pixel points on a certain effective edge line are smaller, the more likely that the effective edge line is the edge line corresponding to the power transmission line is indicated. The edge line corresponding to the power transmission line is longer in the frame difference image, so that when the effective edge line is longer, the more likely that the corresponding effective edge line is the edge line corresponding to the power transmission line is indicated. Therefore, according to the number, the length and the actual skewness of the target edge pixel points of each effective edge line, the selected evaluation value of each effective edge line is obtained. The larger the evaluation value is selected, the more likely the corresponding effective edge line is the edge line corresponding to the power transmission line.
Taking the kth effective edge line in step S3 as an example, a calculation formula for obtaining the selected evaluation value of the kth effective edge line is as follows:；
in the method, in the process of the invention, Selecting an evaluation value for the K effective edge line; /(I)The number of target edge pixel points of the K effective edge line; /(I)The third preset quantity is more than 0; /(I)The total number of edge pixel points on the K effective edge line; /(I)The actual skewness of the K effective edge line; /(I)As a function of absolute value; e is a natural constant.
Embodiments of the invention willSet to 1, avoid denominator to 0, and the practitioner can set/>, according to the actual situationIs not limited herein.
It should be noted that the number of the substrates,Smaller, the less likely that edge branches are present for the kth valid edge line,The larger the/>The larger; /(I)The larger the K-th valid edge line, the longer the/(the greater)The larger; /(I)The smaller, i.e./>The more tends to 0, the more likely the Kth effective edge line is the edge line corresponding to the transmission line,/>The larger the/>The larger; thus,/>The larger the K-th effective edge line is, the more likely the K-th effective edge line is the edge line corresponding to the power transmission line.
And acquiring the selection evaluation value of each effective edge line according to the method for acquiring the selection evaluation value of the K effective edge line.
Step S5: and screening out a target edge line according to the selected evaluation value, and monitoring the external damage to the current power transmission line according to the target edge line.
Specifically, in order to determine a power transmission line which is possibly damaged by external force in a gray level image of a current frame, the embodiment of the invention normalizes the selected evaluation value, and when the normalized selected evaluation value is greater than or equal to a preset selected evaluation value threshold, the corresponding effective edge line is taken as a target edge line. In the embodiment of the invention, the preset selected evaluation value threshold is set to be 0.75, and the operator can set the preset selected evaluation value threshold according to the actual situation, so that the method is not limited. The target edge line is the edge line corresponding to the power transmission line. In order to accurately monitor external damage to a current power transmission line, the embodiment of the invention constructs a minimum circumscribed rectangle of a target edge line on an edge line corresponding to a gray level image of a current frame, and takes the minimum circumscribed rectangle as a target area, namely, the mark of the edge line corresponding to the power transmission line in the gray level image of the current frame is completed, and a power transmission line area possibly damaged by external force in the gray level image of the current frame is accurately determined. Further, the target area is identified on the trained CNN neural network, and the damage of external force to the current transmission line is accurately and efficiently monitored. The CNN neural network is input as follows: a current frame gray level image with a target area mark; the output is: classification results of all target areas in the gray level image of the current frame; wherein, the classification results are respectively 0,1 and 2; wherein 0 represents that the transmission line is not damaged by external force; 1 represents that the transmission line is damaged by light external force; 2 represents that the transmission line is severely damaged by external force; the loss function of the CNN neural network is a cross entropy loss function. The CNN neural network is a known technology, and will not be described in detail.
The method comprises the steps of obtaining a classification result output by a CNN neural network, when the classification result is 1 or 2, indicating that the power transmission line in the current corresponding target area is damaged by external force, at the moment, outputting an alarm signal to an alarm processing module through an intelligent gateway, analyzing the alarm signal transmitted by the received intelligent gateway by the alarm processing module, alarming through sound and light flashing types, timely sending alarm notification to staff, and enabling the staff to quickly take action to handle abnormal conditions, timely process the power transmission line, determine normal operation of electric power and simultaneously avoid dangerous accidents.
The present invention has been completed.
In summary, the embodiment of the invention obtains the gray level image of the power transmission line, obtains the frame difference image between the gray level image of the current frame and the gray level image of the adjacent previous frame, and screens out the effective edge line according to the length of the edge line; acquiring the actual skewness of the effective edge line according to the distance between the edge pixel point and other effective edge lines and the distance between the edge pixel point and the line segment of the corresponding effective edge line after the dimension reduction; determining target edge pixel points according to the number of the edge pixel points in the edge pixel point field; and screening out a target edge line according to the number, the length and the actual skewness of the target edge pixel points of the effective edge line, and monitoring the external damage of the current power transmission line. According to the method, the target edge line is obtained, so that the power transmission line is accurately marked, and the damage degree of external force to the power transmission line is accurately monitored in real time with high efficiency.
Based on the same inventive concept as the method embodiment, the embodiment of the invention also provides a transmission line external damage monitoring system based on an intelligent gateway, which comprises: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the steps in the embodiment of the intelligent gateway-based transmission line external damage monitoring method are realized when the processor executes the computer program, for example, the steps shown in fig. 1. The method for monitoring the external damage of the power transmission line based on the intelligent gateway is described in detail in the above embodiments, and will not be repeated.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. The method for monitoring the external damage of the power transmission line based on the intelligent gateway is characterized by comprising the following steps of:
acquiring a gray image of each frame of power transmission line;
Acquiring a target evaluation value of each edge pixel point according to the gray value of each edge pixel point on each edge line in each frame of gray image and the gradient direction change of the adjacent next edge pixel point;
Acquiring a frame difference image according to the gray level image of the current frame and the gray level image of the adjacent previous frame; screening out effective edge lines according to the length of each edge line in the frame difference image; correcting the deviation of the target evaluation value of each effective edge line according to the distance between each edge pixel point on each effective edge line in the frame difference image and other effective edge lines and the distance between each edge pixel point and the line segment of the corresponding effective edge line pca after the dimension reduction, and obtaining the actual deviation of each effective edge line;
Constructing a neighborhood of each edge pixel point on each effective edge line, and determining a target edge pixel point on each effective edge line according to the number of the edge pixel points in the neighborhood; acquiring a selected evaluation value of each effective edge line according to the number, the length and the actual skewness of the target edge pixel points of each effective edge line;
And screening out a target edge line according to the selected evaluation value, and monitoring the external damage to the current power transmission line according to the target edge line.
2. The method for monitoring the external damage of the power transmission line based on the intelligent gateway as claimed in claim 1, wherein the calculation formula of the target evaluation value is as follows:
；
in the method, in the process of the invention, The target evaluation value of the ith edge pixel point on the L-th edge line; /(I)The gray value of the ith edge pixel point on the L-th edge line; /(I)The gray value average value of all edge pixel points on the L-th edge line; /(I)An included angle in the gradient direction between the ith edge pixel point and the (i+1) th edge pixel point on the L-th edge line; cos is a cosine function; /(I)Is a first preset constant, which is greater than 0; /(I)As a function of absolute value.
3. The method for monitoring the external damage of the power transmission line based on the intelligent gateway as claimed in claim 1, wherein the method for acquiring the frame difference image is as follows:
And subtracting the gray level image of the previous frame from the gray level image of the current frame to perform frame difference processing, and obtaining a frame difference image.
4. The method for monitoring the external damage of the power transmission line based on the intelligent gateway according to claim 1, wherein the method for screening out the effective edge line according to the length of each edge line in the frame difference image is as follows:
Performing morphological closing operation on the edge line in the frame difference image to obtain the processed edge line as a characteristic edge line;
Taking the number of edge pixel points on each characteristic edge line as the length of each characteristic edge line;
the characteristic edge lines are arranged according to the sequence from the large length to the small length, and a characteristic edge line sequence is obtained;
acquiring the length difference between each characteristic edge line and the adjacent next characteristic edge line in the characteristic edge line sequence as a first difference;
dividing the characteristic edge line sequence into two parts;
and taking all the characteristic edge lines in the partial characteristic edge line sequence with the maximum length as effective edge lines.
5. The method for monitoring the external damage of the power transmission line based on the intelligent gateway as claimed in claim 1, wherein the calculation formula of the actual skewness is as follows:
；
in the method, in the process of the invention, The actual skewness of the K effective edge line; /(I)The total number of edge pixel points on the K effective edge line; /(I)The distance between the mth edge pixel point on the kth effective edge line and any other effective edge line; min is a function taking the minimum value; /(I)The distance between the mth edge pixel point on the kth effective edge line and the line segment of the kth effective edge line pca after dimension reduction is set; /(I)Is a second preset constant, greater than 0; /(I)The target evaluation value of the mth edge pixel point on the Kth effective edge line; /(I)The average value of the target evaluation values of all edge pixel points on the K effective edge line; /(I)The standard deviation of the target evaluation value of the edge pixel point on the K-th effective edge line.
6. The method for monitoring the external damage of the power transmission line based on the intelligent gateway as claimed in claim 1, wherein the method for obtaining the target edge pixel point is as follows:
And when the number of the edge pixels in the neighborhood of the edge pixels is larger than the neighborhood side length, taking the corresponding edge pixels as target edge pixels.
7. The method for monitoring the external damage of the power transmission line based on the intelligent gateway according to claim 1, wherein the calculation formula of the selected evaluation value is as follows:
；
in the method, in the process of the invention, Selecting an evaluation value for the K effective edge line; /(I)The number of target edge pixel points of the K effective edge line; /(I)The third preset quantity is more than 0; /(I)The total number of edge pixel points on the K effective edge line; /(I)The actual skewness of the K effective edge line; /(I)As a function of absolute value; e is a natural constant.
8. The method for monitoring the external damage of the power transmission line based on the intelligent gateway according to claim 1, wherein the method for screening out the target edge line according to the selected evaluation value is as follows:
And carrying out normalization processing on the selected evaluation value, and taking the corresponding effective edge line as a target edge line when the normalized selected evaluation value is greater than or equal to a preset selected evaluation value threshold value.
9. The method for monitoring the external damage of the power transmission line based on the intelligent gateway according to claim 1, wherein the method for monitoring the external damage of the current power transmission line according to the target edge line is as follows:
Constructing a minimum circumscribed rectangle of a target edge line on an edge line corresponding to a gray level image of a current frame, and taking the minimum circumscribed rectangle as a target area;
and inputting the target area into a trained neural network for identification, and monitoring the damage of external force to the current power transmission line.
10. An intelligent gateway-based power transmission line external damage monitoring system, comprising a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor, when executing the computer program, realizes the steps of the intelligent gateway-based power transmission line external damage monitoring method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410354328.7A CN117953434A (en) | 2024-03-27 | 2024-03-27 | Intelligent gateway-based method and system for monitoring external damage of power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410354328.7A CN117953434A (en) | 2024-03-27 | 2024-03-27 | Intelligent gateway-based method and system for monitoring external damage of power transmission line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117953434A true CN117953434A (en) | 2024-04-30 |
Family
ID=90801878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410354328.7A Pending CN117953434A (en) | 2024-03-27 | 2024-03-27 | Intelligent gateway-based method and system for monitoring external damage of power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117953434A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102891966A (en) * | 2012-10-29 | 2013-01-23 | 珠海全志科技股份有限公司 | Focusing method and device for digital imaging device |
| CN109215020A (en) * | 2018-08-30 | 2019-01-15 | 国网黑龙江省电力有限公司佳木斯供电公司 | Ultra-high-tension power transmission line fault recognition method based on computer vision |
| US20190197373A1 (en) * | 2014-06-18 | 2019-06-27 | Canon Kabushiki Kaisha | Image processing apparatus image processing method and program |
| CN115049669A (en) * | 2022-08-16 | 2022-09-13 | 如皋富美龙金属制品有限公司 | Metal defect identification method |
| CN117237747A (en) * | 2023-11-14 | 2023-12-15 | 深圳市明鸿五金制品有限公司 | Hardware defect classification and identification method based on artificial intelligence |
-
2024
- 2024-03-27 CN CN202410354328.7A patent/CN117953434A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102891966A (en) * | 2012-10-29 | 2013-01-23 | 珠海全志科技股份有限公司 | Focusing method and device for digital imaging device |
| US20190197373A1 (en) * | 2014-06-18 | 2019-06-27 | Canon Kabushiki Kaisha | Image processing apparatus image processing method and program |
| CN109215020A (en) * | 2018-08-30 | 2019-01-15 | 国网黑龙江省电力有限公司佳木斯供电公司 | Ultra-high-tension power transmission line fault recognition method based on computer vision |
| CN115049669A (en) * | 2022-08-16 | 2022-09-13 | 如皋富美龙金属制品有限公司 | Metal defect identification method |
| CN117237747A (en) * | 2023-11-14 | 2023-12-15 | 深圳市明鸿五金制品有限公司 | Hardware defect classification and identification method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| CN111402248A (en) | Transmission line lead defect detection method based on machine vision | |
| CN110650316A (en) | Intelligent patrol and early warning processing method and device, electronic equipment and storage medium | |
| US20230005176A1 (en) | Throwing position acquisition method and apparatus, computer device and storage medium | |
| CN115018840B (en) | Method, system and device for detecting cracks of precision casting | |
| CN108318773B (en) | Transmission conductor strand breakage detection method and system | |
| CN113469974B (en) | Method and system for monitoring state of grate plate of pellet grate | |
| CN116485779A (en) | Adaptive wafer defect detection method and device, electronic equipment and storage medium | |
| CN114943841A (en) | Method and device for assisting operation safety control based on image recognition | |
| CN115083008A (en) | Moving object detection method, device, equipment and storage medium | |
| CN115359449B (en) | Automatic identification method and system for turnout notch image of point switch | |
| CN115063739B (en) | Abnormal behavior detection method, device, equipment and computer storage medium | |
| CN117953434A (en) | Intelligent gateway-based method and system for monitoring external damage of power transmission line | |
| CN115880365A (en) | Double-station automatic screw screwing detection method, system and device | |
| CN113643234B (en) | Composite insulator damage detection method, terminal equipment and readable storage medium | |
| CN114757905A (en) | Vision-based rope winding abnormity detection device and method | |
| CN112241707A (en) | Wind-powered electricity generation field intelligence video identification device | |
| CN109193935B (en) | Power distribution room monitoring method and system based on image processing | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN115578405B (en) | Remote monitoring method for numerical control processing platform of aluminum alloy furniture | |
| CN114879621B (en) | Furniture spraying machining control method, system and device | |
| CN115861321B (en) | Production environment detection method and system applied to industrial Internet | |
| CN114663750B (en) | Submarine cable filling strip fracture identification method based on machine vision and deep learning | |
| CN118037722B (en) | Copper pipe production defect detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |