CN117315515A - Visual auxiliary inspection method and system for distribution line - Google Patents
Visual auxiliary inspection method and system for distribution line Download PDFInfo
- Publication number
- CN117315515A CN117315515A CN202311610508.9A CN202311610508A CN117315515A CN 117315515 A CN117315515 A CN 117315515A CN 202311610508 A CN202311610508 A CN 202311610508A CN 117315515 A CN117315515 A CN 117315515A
- Authority
- CN
- China
- Prior art keywords
- foreign matter
- target area
- line
- pixel point
- distribution line
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000007689 inspection Methods 0.000 title claims abstract description 39
- 230000000007 visual effect Effects 0.000 title claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 23
- 238000012216 screening Methods 0.000 claims abstract description 10
- 238000010586 diagram Methods 0.000 claims abstract description 3
- 230000006870 function Effects 0.000 claims description 9
- 230000007704 transition Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000035772 mutation Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000016507 interphase Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02G—INSTALLATION OF ELECTRIC CABLES OR LINES, OR OF COMBINED OPTICAL AND ELECTRIC CABLES OR LINES
- H02G1/00—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines
- H02G1/02—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines for overhead lines or cables
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a visual auxiliary inspection method and system for a distribution line, wherein the method acquires gray level images of the distribution line; identifying, screening and marking all straight lines of the image according to the characteristics of the distribution line; acquiring a target area of a distribution line diagram and a distribution line area; analyzing the difference between the target area and the distribution line area to construct a line foreign matter difference coefficient; analyzing texture features among pixel points of a target area, and constructing a foreign matter texture feature vector and a foreign matter line texture distinguishing degree; constructing a foreign matter significance coefficient; acquiring a foreign matter significant factor; constructing a foreign matter coverage rate of the target area; acquiring a foreign matter region; thereby accomplish the supplementary inspection of distribution lines, have distribution lines foreign matter discernment rate of accuracy height, the beneficial effect that the reliability is strong.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a visual auxiliary inspection method and system for a distribution line.
Background
Currently, the distribution line data in the power system of China is huge and incomplete. In order to ensure the normal operation of the power distribution network, operators of the power distribution network must regularly overhaul and maintain the power distribution network equipment each month, especially, the lines near the street and the garbage recycling station may be scraped by light matters of conductors and semiconductors caused by strong wind, and inter-phase faults of the lines may be caused, so that the fault rate of the lines is improved. The suspension of foreign matter on the line can lead to a shortened insulation distance to the ground of the line, which is easy to cause the tripping of the line. Therefore, the foreign matters can be identified in time and cleaned by taking measures, and the method has important significance for safe and stable operation of the power system.
The existing manual line inspection operation mode has high labor intensity and low efficiency, can not meet the requirements of modern power grid construction and development, and has inaccurate and low efficiency of manual inspection statistics, so that the inspection method needs to be improved.
In summary, the invention provides a visual auxiliary inspection method and system for a distribution line, which are combined with an image processing technology to identify suspended foreign matters on the distribution line, so that the inspection efficiency and the inspection quality of the distribution line are improved.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a visual auxiliary inspection method and system for a distribution line, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for visually assisting in inspecting a distribution line, including the following steps:
acquiring a gray level image of a distribution line;
acquiring all straight lines of the image by adopting a straight line extraction algorithm according to the gray level image of the distribution line; screening and marking all straight lines of the image according to the characteristics of the distribution line; obtaining a target area of the distribution line diagram and a distribution line area by adopting a segmentation algorithm according to the marked straight line; obtaining a line foreign matter difference coefficient of each pixel point of the target area according to the difference between the pixel points of the target area and the distribution line area; obtaining foreign matter texture feature vectors of all pixel points according to texture features between all pixel points and neighborhood pixel points in a target area; obtaining foreign matter line texture distinction degree between each pixel point and the neighborhood pixel points according to the foreign matter texture feature vector of each pixel point in the target area; obtaining a foreign matter significant coefficient of each pixel point of the target area according to the distribution of foreign matter line texture distinguishability between each pixel point and the neighborhood pixel points in the target area; acquiring foreign matter salient factors of all pixel points of the target area according to the foreign matter salient coefficients of all pixel points of the target area; acquiring the foreign matter coverage rate of the target area according to the foreign matter significant factors of each pixel point of the target area and the line difference coefficient;
acquiring a foreign object region according to the foreign object salient factors of each pixel point of the target region and the foreign object coverage rate of the target region; and (5) completing auxiliary inspection of the distribution line according to the foreign object area.
Further, the screening and marking are performed on all straight lines of the image according to the characteristics of the distribution line, specifically:
acquiring the lengths and angles of all straight lines of an image; acquiring the longest straight line length and the longest straight line angle of an image;
setting a length threshold and an angle threshold; removing lines with other straight line lengths smaller than a length threshold value of the image, and simultaneously calculating the difference value between other straight line angles of the image and the longest straight line angle; removing the straight lines with the difference value larger than an angle threshold value; the remaining straight lines are marked.
Further, the obtaining the line foreign matter difference coefficient of each pixel point of the target area according to the difference between the pixel points of the target area and the distribution line area specifically includes:
calculating the average value and the sum value of gray values of all pixel points in the distribution line area; calculating the absolute value of the difference between the average value and the gray value of each pixel point in the target area; calculating the product of the absolute value of the difference value and the number of the pixel points in the distribution line area; and taking the ratio of the product to the sum as a line foreign matter difference coefficient of each pixel point in the target area.
Further, the obtaining the foreign matter texture feature vector of each pixel according to the texture feature between each pixel and the neighboring pixel in the target area includes:
obtaining LBP feature descriptors of each pixel point of a target area; counting the number of times of changes of adjacent elements 0 to 1 and 1 to 0 in LBP descriptors of each pixel point, and storing the number of times as the transition times of line foreign matters; counting the occurrence times of two continuous 0 and 1 of adjacent elements in the LBP descriptors of each pixel point respectively, and sequentially storing the occurrence times as line continuation times and foreign matter continuation times; and taking the line foreign matter transition times, the line continuation times and the foreign matter continuation times of each pixel point as foreign matter texture characteristic vector elements of each pixel point.
Further, the obtaining the foreign object line texture distinction degree between each pixel point and the neighboring pixel point according to the foreign object texture feature vector of each pixel point in the target area includes:
acquiring the Hamming distance between each pixel point of the target area and LBP feature descriptors of the neighborhood pixel points; obtaining dot products between unitized foreign matter texture feature vectors of each pixel point of a target area and neighborhood pixel points; calculating cosine similarity between foreign matter texture feature vectors of each pixel point of the target area and the neighborhood pixel points; taking the cosine similarity as an index of an exponential function with a natural constant as a base; calculating a sum of the exponential function and the dot product; and taking the ratio of the Hamming distance to the sum value as the foreign matter line texture distinguishing degree between each pixel point and the neighborhood pixel points.
Further, the obtaining the foreign object significant coefficient of each pixel point in the target area according to the distribution of the foreign object line texture distinguishability between each pixel point in the target area and the neighboring pixel points specifically includes:
respectively obtaining extreme values, average values and maximum values of foreign matter line texture distinguishability between each pixel point of a target area and each neighborhood pixel point in a neighborhood window; calculating a difference between the maximum value and the average value; calculating the ratio of the extremum to the difference; and taking the product of the average value and the ratio as a foreign matter significant coefficient of each pixel point of the target area.
Further, the obtaining the foreign object significant factor of each pixel point of the target area according to the foreign object significant coefficient of each pixel point of the target area specifically includes:
obtaining information entropy of texture distinguishability of all foreign matters in a neighborhood window of each pixel point; and taking the product of the information entropy and the foreign matter significant coefficient as a foreign matter significant factor of each pixel point of the target area.
Further, the step of obtaining the coverage rate of the foreign object in the target area according to the foreign object significant factor and the line difference coefficient of each pixel point in the target area specifically includes:
dividing foreign matter significant factors and line foreign matter difference coefficients of each pixel point of a target area by adopting an Ojin threshold algorithm to obtain a foreign matter significant OTSU threshold and a line foreign matter difference OTSU threshold;
acquiring a difference value between the number of pixels in the target area and the number of pixels in the distribution line area; obtaining the sum value of the number of the pixels of the target area with the foreign matter significant factor larger than the foreign matter significant OTSU threshold and the number of the pixels of the target area with the line foreign matter difference coefficient larger than the line foreign matter difference OTSU threshold; and taking the ratio of the sum value to the difference value as the foreign matter coverage rate of the target area.
Further, the step of obtaining the foreign object region according to the foreign object coverage rate of the target region by combining the foreign object salient factors of each pixel point of the target region comprises the following specific steps:
taking foreign matter significant factors of each pixel point of the target area as the input of a DBSCAN clustering algorithm; taking the product of the total pixel number of the target area and the foreign object coverage rate as the neighborhood radius of the DBSCAN clustering algorithm; the output of the DBSCAN clustering algorithm is each clustering area;
setting a threshold value; and calculating the gray average value of each clustering area, and marking the clustering area with the gray average value larger than the threshold value as a foreign object area.
In a second aspect, an embodiment of the present invention further provides a power distribution line vision-assisted inspection system, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements the steps of any one of the above-mentioned power distribution line vision-assisted inspection methods when executing the computer program.
The invention has at least the following beneficial effects:
according to the invention, the accurate identification of the foreign matters on the distribution line is realized by analyzing the gray scale characteristics and the texture characteristics of the foreign matters on the distribution line, so that the distribution line inspection is assisted by workers, the inspection quality and the inspection efficiency of the distribution line are improved, and the safety of the workers is improved.
The invention mainly acquires a target area and a distribution line area in a distribution line image by combining the linear characteristics of the distribution line, and acquires a line foreign matter difference coefficient by combining the gray level differences among the areas; distinguishing between the distribution line and the foreign matter from the gray scale characteristics; constructing foreign matter line texture distinguishability and constructing a foreign matter saliency coefficient; acquiring a foreign matter significant factor; constructing a foreign matter coverage rate of the target area; judging the distribution line and the foreign matters from the texture characteristics; acquiring a foreign matter region by combining gray scale and texture features; the foreign matter on the distribution line can be accurately identified, and the reliability of the identification effect is ensured.
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 flowchart illustrating steps of a visual auxiliary inspection method for a distribution line according to an embodiment of the present invention;
fig. 2 is an abnormal region acquisition flowchart.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a power distribution line vision-aided inspection method and system according to the invention, and the detailed implementation, structure, characteristics and effects thereof are as follows. 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 visual auxiliary inspection method and a visual auxiliary inspection system for a distribution line.
Referring to fig. 1, a flowchart illustrating steps of a method for visual auxiliary inspection of a distribution line according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: and acquiring a distribution line image through an image acquisition device, and preprocessing.
And shooting aerial images of the distribution lines by using the unmanned aerial vehicle, wherein the aerial images of the distribution lines are color (RGB) images. In order to reduce the data amount of image processing and to improve the operation efficiency, the distribution line area is highlighted, and it is necessary to perform gradation processing on the distribution line image to convert it into a gradation image. Because the unmanned aerial vehicle-mounted imaging equipment is slightly swayed by the influence of air flow to cause the machine body to be fuzzy, the acquired image is also subjected to factors such as illumination, weather and image transmission process to be doped with noise, the distribution line image is preprocessed by a method of combining wiener filtering and median filtering to remove noise in the image, wherein the wiener filtering and the median filtering are the prior known technologies, and the embodiment is not repeated herein.
Thus, the denoised distribution line gray level image is obtained.
Step S002: and obtaining a line foreign matter difference coefficient of each pixel point according to the gray level characteristic of each pixel point, obtaining a foreign matter significant factor of each pixel point according to the texture characteristic of each pixel point, and obtaining the foreign matter coverage rate of the target area by combining the line foreign matter difference coefficient and the foreign matter significant factor of each pixel point.
For the distribution line gray level image, all straight lines in the image are acquired by utilizing a LSD (Line Segment Detector) straight line extraction algorithm, and because other pseudo targets with straight line characteristics exist in the distribution line gray level image besides distribution wires. It is therefore necessary to determine screening characteristics of the distribution lines based on the characteristics of the distribution lines: 1. firstly, a distribution line needs to be complete and has a certain length; 2. the distribution lines are a group of straight lines with similar dip angles. First, a length threshold is set according to feature 1Performing first straight line screening on the image, reserving straight lines with lengths larger than a threshold value, and marking the longest straight line in the reserved straight lines; on the basis of the first screening, the angle of the longest straight line is obtained, the second screening is carried out on the rest straight lines according to the characteristic 2, and the straight lines with larger difference are eliminated, specifically: the difference value between the angle of the screening straight line and the angle of the longest straight line is smaller than or equal to an angle threshold value, and the straight line with the difference value larger than the angle threshold value is removed; and then extracting a connected domain of the detected straight line, and marking the detected straight line in the distribution line image. It is to be noted that the length threshold +.>Is set to be the longest straight line detected +.>The angle threshold is +.>The implementation can be set by the implementation personnel according to the actual situation, and the embodiment is not limited to this.
And acquiring a target and a background of the distribution line image by using an OTSU Ojin threshold segmentation algorithm, and marking a target area in the distribution line image. The OTSU oxford threshold segmentation algorithm is a prior art, and is not described in detail in this embodiment.
To this end, can obtainTo a target area marked in the distribution line image. The target area includes a distribution line area, and in addition, the target area also includes a foreign object area on the distribution line, which needs to be identified in this embodiment, and the position where the foreign object area is marked is a line fault position, and the marked position is timely transmitted to a worker for maintenance. For the foreign matters existing on the distribution line, two situations exist, one is a silk ribbon, plastic paper and the like with larger gray scale difference with the distribution line, and the other is a branch and the like with very close gray scale with the distribution line, so that for each pixel point of the target area, a line foreign matter difference coefficient of each pixel point of the target area is constructed for the two situations, and the specific expression of the line foreign matter difference coefficient is as follows:
in the method, in the process of the invention,representing the target area->Line foreign matter difference coefficient of each pixel point, +.>Indicating distribution line area->Gray value of each pixel, +.>Representing the number of pixels in the distribution line area, < +.>Representing the target area->Gray values of individual pixels.
Wherein the method comprises the steps ofRepresenting the average value of gray values of all pixel points in the distribution line area, thereby representing the standard gray value of the distribution line, and the +.>The larger the difference between the individual pixel points and the standard gray value, the more +.>The more likely a pixel is a foreign object pixel, the greater the line foreign object difference coefficient.
The line foreign matter difference coefficient of all pixel points in the target area can be roughly distinguished to obtain the pixel points with larger gray scale difference between the target area and the distribution line, but the foreign matters with the gray scale similar to that of the distribution line are difficult to identify, because the common electric wires in the distribution line are usually conductors made of copper or aluminum and other metals and are covered with insulating materials, the line surface texture is smooth and clean under the normal condition, and the foreign matter surface texture is greatly different from the line surface texture, so that the pixel points in the target area are takenNeighborhood, in this embodiment->The practitioner can set up himself for each pixel at +.>The LBP feature descriptors in the neighborhood, wherein the mutation from 0 to 1 and the mutation from 1 to 0 are marked as line foreign matter transition, two continuous 0 s are marked as line continuation, two continuous 1 s are marked as foreign matter continuation, and the number of times of occurrence of line foreign matter transition points, line continuation points and foreign matter continuation points in the LBP feature descriptors of each pixel point is counted to form a foreign matter texture feature vector of each pixel point.
The foreign matter texture characteristic vector of each pixel point is expressed asWhereinIs pixel dot +.>Is described as the number of times of occurrence of line foreign matter transitions in the sub-processor, < >>Is pixel dot +.>Is described in terms of the number of times the circuit continuation occurs,/-for the LBP feature description of (a)>Is pixel dot +.>The number of times that foreign matter continues to appear in the LBP signature descriptor. For example, if pixel i is 11010010, the foreign texture feature vector of pixel i is denoted as +.>。
According to the difference of texture characteristics between the line and the foreign pixel point in the target area, the difference degree of textures between the pixel points is obtained, and for any pixel point in the target area, the method comprises the steps ofIn the present embodiment +.>The practitioner can set up according to the actual situation by himself, calculate the pixel +.>And->Foreign matter line texture distinguishing degree between pixel points, wherein the specific expression of the foreign matter line texture distinguishing degree is as follows：
In the method, in the process of the invention,is pixel dot +.>And pixel point in neighborhood->Foreign matter line texture distinction between +.>Is pixel dot +.>Foreign matter texture feature vector, ">Is pixel dot +.>Foreign matter texture feature vector, ">LBP feature descriptor for pixel i,/->Is pixel dot +.>LBP feature descriptor of->The hamming distance function is represented by a hamming distance function,representing cosine similarity function,/->Modulo representing vector, ++>Representing natural constants.
The LBP feature descriptors of the pixel points represent texture features around the pixel points, and when the Hamming distance between the LBP feature descriptors of the two pixel points is larger, the difference between the texture features around the two pixel points is larger, and the foreign matter line texture distinction degree of the two pixel points is larger; the foreign matter texture feature vector of the pixel point represents the texture mutation feature around the pixel point, and when the unit dot product of the foreign matter texture feature vector of the two pixel points is larger, the more similar the texture mutation feature around the two pixel points is, the smaller the foreign matter line texture distinction degree of the two pixel points is.
Foreign matter salient coefficient of each pixel point in the central pixel point, namely the target area, is calculated according to foreign matter texture distinguishing degree of the central pixel point in the neighborhood of the pixel point and other pixel points in the neighborhood, and the specific expression of the foreign matter salient coefficient is as follows:
in the method, in the process of the invention,foreign matter saliency coefficient representing pixel point i, < ->Representing +.>Mean value of texture distinctiveness of all foreign lines in neighborhood window, +.>A set representing the foreign matter line texture distinguishability of other pixel points in the neighborhood of the pixel point i and the pixel point i, < ->Representing a maximum function>Representation ofTaking a minimum function.
The larger the pixel point i, the larger the average value of the foreign object line texture discrimination degree in the neighborhood of the pixel point i is, and the more likely the pixel point is the foreign object pixel point, so that the larger the foreign object significance coefficient of the pixel point i is, namely, the extremely poor of the foreign object line texture discrimination degree in the neighborhood of the pixel point i is->The larger the difference of foreign matter line texture distinctiveness between the pixel points in the neighborhood of the pixel point is, the more likely the foreign matter region is contained in the neighborhood of the pixel point, so that the larger the foreign matter significant coefficient of the pixel point is, the more the foreign matter significant coefficient is>The smaller the distribution of the foreign matter line texture distinguishability in the neighborhood of the pixel point is, the more concentrated the distribution is, and the more stable the change is, the larger the foreign matter significant coefficient of the pixel point is.
Calculating foreign matter salient factors of all pixel points in a target area according to the foreign matter salient coefficients, wherein the specific expression of the foreign matter salient factors is as follows:
in the method, in the process of the invention,foreign matter saliency factor representing pixel i, < ->Representing +.>The information entropy of the texture discrimination degree of all foreign lines in the neighborhood window is the information entropy of the prior art, and the detailed description of the embodiment is omitted here.
When the entropy value of the foreign matter line texture distinguishing degree in the neighborhood of the pixel point is larger, the distribution of the foreign matter line texture distinguishing degree in the neighborhood is more disordered, so that the foreign matter significant factor of the pixel point i is larger.
Comprehensively considering the texture characteristics and gray characteristics of each pixel point of a target area to judge the possibility of existence of foreign matters, calculating the foreign matter coverage rate of the target area according to the foreign matter significant factors and the line foreign matter difference coefficients of each pixel point, firstly dividing the line foreign matter difference coefficients of each pixel point of the target area by utilizing an Otsu threshold segmentation algorithm, and obtaining the line foreign matter difference OTSU threshold; and the foreign matter significant factors of each pixel point of the target area are segmented by utilizing the Ojin threshold value to obtain a foreign matter significant OTSU threshold value, and the specific expression of the foreign matter coverage rate is as follows according to the analysis:
in the method, in the process of the invention,foreign matter coverage indicating target area, ++>The number of pixels representing the target area,the number of pixels representing the distribution line area, < +.>The number of pixels of which the foreign matter significant factor is larger than the foreign matter significant OTSU threshold value is represented, and the number of pixels is +.>And the number of pixels with the line foreign matter difference coefficient larger than the line foreign matter difference OTSU threshold value is represented.
Step S003: and combining foreign matter significant factors of all pixel points and a DBSCAN clustering algorithm to finish the visual auxiliary inspection of the distribution line.
Taking the foreign matter significant factor of each pixel point in the target area as input data of a DBSCAN clustering algorithm, taking the product of the total number of pixel points in the target area and the foreign matter coverage rate as the neighborhood radius of the DBSCAN clustering algorithm, and taking the minimum neighborhood as the neighborhood radius of the DBSCAN clustering algorithmThe number of domains isIn this embodiment +.>The implementer can set according to the actual situation by himself, the embodiment does not limit the situation, and then the DBSCAN clustering algorithm is utilized to cluster the target area in the distribution line image, so as to obtain a clustered area. The DBSCAN clustering algorithm is a known technology, and this embodiment is not described herein.
Acquiring each clustering area by a DBSCAN clustering algorithm, calculating the gray average value of each clustering cluster, and setting a threshold valueAnd marking the area with the gray average value larger than the threshold value as a foreign matter area, reminding a worker to carry out important inspection and investigation on the foreign matter area, and determining to remove the foreign matter. Threshold +.>The embodiment may be set by the practitioner according to the actual situation, and the embodiment is not limited thereto. The acquisition of the abnormal region is shown in fig. 2.
Thus, the auxiliary inspection of the distribution line is completed.
Based on the same inventive concept as the above method, the embodiment of the invention also provides a distribution line vision-aided inspection system, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor realizes the steps of any one of the above distribution line vision-aided inspection methods when executing the computer program.
In summary, according to the embodiment of the invention, the accurate identification of the foreign matters on the distribution line is realized by analyzing the gray scale characteristics and the texture characteristics of the foreign matters on the distribution line, so that the distribution line inspection is assisted by the staff, the inspection quality and the inspection efficiency of the distribution line are improved, and the safety of the staff is improved.
The embodiment of the invention mainly acquires a target area and a distribution line area in a distribution line image by combining the linear characteristics of the distribution line, and acquires a line foreign matter difference coefficient by combining the gray scale differences among the areas; distinguishing between the distribution line and the foreign matter from the gray scale characteristics; constructing foreign matter line texture distinguishability and constructing a foreign matter saliency coefficient; acquiring a foreign matter significant factor; constructing a foreign matter coverage rate of the target area; judging the distribution line and the foreign matters from the texture characteristics; acquiring a foreign matter region by combining gray scale and texture features; the foreign matter on the distribution line can be accurately identified, and the reliability of the identification effect is ensured.
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. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures 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.
The foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. The visual auxiliary inspection method for the distribution line is characterized by comprising the following steps of:
acquiring a gray level image of a distribution line;
acquiring all straight lines of the image by adopting a straight line extraction algorithm according to the gray level image of the distribution line; screening and marking all straight lines of the image according to the characteristics of the distribution line; obtaining a target area of the distribution line diagram and a distribution line area by adopting a segmentation algorithm according to the marked straight line; obtaining a line foreign matter difference coefficient of each pixel point of the target area according to the difference between the pixel points of the target area and the distribution line area; obtaining foreign matter texture feature vectors of all pixel points according to texture features between all pixel points and neighborhood pixel points in a target area; obtaining foreign matter line texture distinction degree between each pixel point and the neighborhood pixel points according to the foreign matter texture feature vector of each pixel point in the target area; obtaining a foreign matter significant coefficient of each pixel point of the target area according to the distribution of foreign matter line texture distinguishability between each pixel point and the neighborhood pixel points in the target area; acquiring foreign matter salient factors of all pixel points of the target area according to the foreign matter salient coefficients of all pixel points of the target area; acquiring the foreign matter coverage rate of the target area according to the foreign matter significant factors of each pixel point of the target area and the line difference coefficient;
acquiring a foreign object region according to the foreign object salient factors of each pixel point of the target region and the foreign object coverage rate of the target region; and (5) completing auxiliary inspection of the distribution line according to the foreign object area.
2. The method for assisting in inspecting the visual sense of the distribution line according to claim 1, wherein the screening and marking are performed on all straight lines of the image according to the characteristics of the distribution line, specifically:
acquiring the lengths and angles of all straight lines of an image; acquiring the longest straight line length and the longest straight line angle of an image;
setting a length threshold and an angle threshold; removing lines with other straight line lengths smaller than a length threshold value of the image, and simultaneously calculating the difference value between other straight line angles of the image and the longest straight line angle; removing the straight lines with the difference value larger than an angle threshold value; the remaining straight lines are marked.
3. The method for assisting in inspecting the distribution line vision according to claim 1, wherein the obtaining the line foreign matter difference coefficient of each pixel point of the target area according to the difference between the pixel points of the target area and the distribution line area is specifically as follows:
calculating the average value and the sum value of gray values of all pixel points in the distribution line area; calculating the absolute value of the difference between the average value and the gray value of each pixel point in the target area; calculating the product of the absolute value of the difference value and the number of the pixel points in the distribution line area; and taking the ratio of the product to the sum as a line foreign matter difference coefficient of each pixel point in the target area.
4. The method for visual auxiliary inspection of a distribution line according to claim 1, wherein the step of obtaining a foreign matter texture feature vector of each pixel according to texture features between each pixel of a target area and a neighboring pixel comprises:
obtaining LBP feature descriptors of each pixel point of a target area; counting the number of times of changes of adjacent elements 0 to 1 and 1 to 0 in LBP descriptors of each pixel point, and storing the number of times as the transition times of line foreign matters; counting the occurrence times of two continuous 0 and 1 of adjacent elements in the LBP descriptors of each pixel point respectively, and sequentially storing the occurrence times as line continuation times and foreign matter continuation times; and taking the line foreign matter transition times, the line continuation times and the foreign matter continuation times of each pixel point as foreign matter texture characteristic vector elements of each pixel point.
5. The method for visual auxiliary inspection of a distribution line according to claim 1, wherein the step of obtaining the foreign object line texture discrimination between each pixel and the neighboring pixel according to the foreign object texture feature vector of each pixel in the target area comprises the steps of:
acquiring the Hamming distance between each pixel point of the target area and LBP feature descriptors of the neighborhood pixel points; obtaining dot products between unitized foreign matter texture feature vectors of each pixel point of a target area and neighborhood pixel points; calculating cosine similarity between foreign matter texture feature vectors of each pixel point of the target area and the neighborhood pixel points; taking the cosine similarity as an index of an exponential function with a natural constant as a base; calculating a sum of the exponential function and the dot product; and taking the ratio of the Hamming distance to the sum value as the foreign matter line texture distinguishing degree between each pixel point and the neighborhood pixel points.
6. The method for assisting in inspecting the distribution line vision according to claim 1, wherein the obtaining the foreign object significant coefficient of each pixel point in the target area according to the distribution of the foreign object line texture distinguishability between each pixel point and the neighboring pixel points in the target area specifically comprises:
respectively obtaining extreme values, average values and maximum values of foreign matter line texture distinguishability between each pixel point of a target area and each neighborhood pixel point in a neighborhood window; calculating a difference between the maximum value and the average value; calculating the ratio of the extremum to the difference; and taking the product of the average value and the ratio as a foreign matter significant coefficient of each pixel point of the target area.
7. The method for visual auxiliary inspection of a distribution line according to claim 1, wherein the step of obtaining the foreign object significant factor of each pixel point of the target area according to the foreign object significant factor of each pixel point of the target area comprises the following steps:
obtaining information entropy of texture distinguishability of all foreign matters in a neighborhood window of each pixel point; and taking the product of the information entropy and the foreign matter significant coefficient as a foreign matter significant factor of each pixel point of the target area.
8. The method for assisting in inspecting the power distribution line vision according to claim 1, wherein the step of obtaining the coverage rate of the foreign matter in the target area according to the foreign matter significant factor and the line difference coefficient of each pixel point in the target area comprises the following specific steps:
dividing foreign matter significant factors and line foreign matter difference coefficients of each pixel point of a target area by adopting an Ojin threshold algorithm to obtain a foreign matter significant OTSU threshold and a line foreign matter difference OTSU threshold;
acquiring a difference value between the number of pixels in the target area and the number of pixels in the distribution line area; obtaining the sum value of the number of the pixels of the target area with the foreign matter significant factor larger than the foreign matter significant OTSU threshold and the number of the pixels of the target area with the line foreign matter difference coefficient larger than the line foreign matter difference OTSU threshold; and taking the ratio of the sum value to the difference value as the foreign matter coverage rate of the target area.
9. The method for visual auxiliary inspection of a distribution line according to claim 1, wherein the step of obtaining the foreign object area according to the foreign object salient factors of each pixel point of the target area and the foreign object coverage of the target area comprises the following specific steps:
taking foreign matter significant factors of each pixel point of the target area as the input of a DBSCAN clustering algorithm; taking the product of the total pixel number of the target area and the foreign object coverage rate as the neighborhood radius of the DBSCAN clustering algorithm; the output of the DBSCAN clustering algorithm is each clustering area;
setting a threshold value; and calculating the gray average value of each clustering area, and marking the clustering area with the gray average value larger than the threshold value as a foreign object area.
10. A distribution line vision-aided inspection system comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, implements the steps of a distribution line vision-aided inspection method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311610508.9A CN117315515B (en) | 2023-11-29 | 2023-11-29 | Visual auxiliary inspection method and system for distribution line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311610508.9A CN117315515B (en) | 2023-11-29 | 2023-11-29 | Visual auxiliary inspection method and system for distribution line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117315515A true CN117315515A (en) | 2023-12-29 |
| CN117315515B CN117315515B (en) | 2024-03-15 |
Family
ID=89285205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311610508.9A Active CN117315515B (en) | 2023-11-29 | 2023-11-29 | Visual auxiliary inspection method and system for distribution line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117315515B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005147751A (en) * | 2003-11-12 | 2005-06-09 | Anritsu Sanki System Co Ltd | Foreign matter detection method, foreign matter detection program, and foreign matter detector |
| CN105205781A (en) * | 2015-08-24 | 2015-12-30 | 电子科技大学 | Power transmission line aerial photographing image splicing method |
| JP2016123162A (en) * | 2014-12-24 | 2016-07-07 | 株式会社ダイヘン | Non-contact power supply system, power transmitter, and foreign matter detection method |
| CN108956640A (en) * | 2018-04-04 | 2018-12-07 | 山东鲁能智能技术有限公司 | Vehicle-mounted detection apparatus and detection method suitable for distribution line inspection |
| CN109936080A (en) * | 2019-03-28 | 2019-06-25 | 郑州大学 | A kind of method of unmanned plane inspection transmission line of electricity |
| CN112837313A (en) * | 2021-03-05 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Image segmentation method for foreign matters in power transmission line |
| CN114022763A (en) * | 2021-10-28 | 2022-02-08 | 国家能源集团广西电力有限公司 | Foreign matter detection method and device for high-voltage overhead line and readable storage medium |
| CN116758423A (en) * | 2023-06-19 | 2023-09-15 | 合肥工业大学 | Power transmission line foreign matter detection method based on white point rate method |
-
2023
- 2023-11-29 CN CN202311610508.9A patent/CN117315515B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005147751A (en) * | 2003-11-12 | 2005-06-09 | Anritsu Sanki System Co Ltd | Foreign matter detection method, foreign matter detection program, and foreign matter detector |
| JP2016123162A (en) * | 2014-12-24 | 2016-07-07 | 株式会社ダイヘン | Non-contact power supply system, power transmitter, and foreign matter detection method |
| CN105205781A (en) * | 2015-08-24 | 2015-12-30 | 电子科技大学 | Power transmission line aerial photographing image splicing method |
| CN108956640A (en) * | 2018-04-04 | 2018-12-07 | 山东鲁能智能技术有限公司 | Vehicle-mounted detection apparatus and detection method suitable for distribution line inspection |
| CN109936080A (en) * | 2019-03-28 | 2019-06-25 | 郑州大学 | A kind of method of unmanned plane inspection transmission line of electricity |
| CN112837313A (en) * | 2021-03-05 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Image segmentation method for foreign matters in power transmission line |
| CN114022763A (en) * | 2021-10-28 | 2022-02-08 | 国家能源集团广西电力有限公司 | Foreign matter detection method and device for high-voltage overhead line and readable storage medium |
| CN116758423A (en) * | 2023-06-19 | 2023-09-15 | 合肥工业大学 | Power transmission line foreign matter detection method based on white point rate method |
Non-Patent Citations (1)
| Title |
|---|
| 王万国 等: ""基于无人机图像的输电线断股与异物缺陷检测方法"", 《计算机应用》, vol. 35, no. 8, pages 2404 - 2408 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117315515B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112837290B (en) | Crack image automatic identification method based on seed filling algorithm | |
| CN110264448B (en) | Insulator fault detection method based on machine vision | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN111814686A (en) | Vision-based power transmission line identification and foreign matter invasion online detection method | |
| CN110189344A (en) | A kind of line segment extraction method in power knife switch image | |
| CN111144325A (en) | Fault identification and positioning method, device and equipment for power equipment of transformer substation | |
| CN112365475A (en) | Power transmission line icing monitoring method and system based on image processing mode | |
| CN112819784A (en) | Method and system for detecting broken strands and scattered strands of wires of distribution line | |
| CN112001317A (en) | Lead defect identification method and system based on semantic information and terminal equipment | |
| CN113888462A (en) | Crack identification method, system, readable medium and storage medium | |
| CN114581764A (en) | Underground structure crack disease distinguishing method based on deep learning algorithm | |
| CN111008967B (en) | Insulator RTV coating defect identification method | |
| CN115330790A (en) | Image-based cable strand quality detection method and system | |
| CN114882400A (en) | Aggregate detection and classification method based on AI intelligent machine vision technology | |
| CN115690012A (en) | Detection method for wrong connection line of electric energy meter | |
| CN112069894A (en) | Wire strand scattering identification method based on fast-RCNN model | |
| CN110276747B (en) | Insulator fault detection and fault rating method based on image analysis | |
| CN111667473A (en) | Insulator hydrophobicity grade judging method based on improved Canny algorithm | |
| CN115239646A (en) | Defect detection method and device for power transmission line, electronic equipment and storage medium | |
| Xuan et al. | Intelligent identification method of insulator defects based on CenterMask | |
| CN112734637B (en) | Thermal infrared image processing method and system for monitoring temperature of lead | |
| CN117315515B (en) | Visual auxiliary inspection method and system for distribution line | |
| CN112991432A (en) | Icing shape identification method based on image processing | |
| CN115083008A (en) | Moving object detection method, device, equipment and storage medium | |
| CN103996266A (en) | Tailing reservoir safety monitoring device based on video analysis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |