CN-122024150-A - Electrical equipment safety monitoring method and system for cradle head camera

CN122024150ACN 122024150 ACN122024150 ACN 122024150ACN-122024150-A

Abstract

The application relates to the technical field of image recognition, in particular to an electrical equipment safety monitoring method and system of a cradle head camera, wherein the method comprises the steps of continuously collecting images of electrical equipment to be monitored; the method comprises the steps of analyzing morphological characteristics of edges in an electrical equipment image to be monitored, determining edge analysis factors, grading gray value distribution in the electrical equipment image to be monitored, analyzing change characteristics of gray values of all pixel points in adjacent gray levels in the image along with position distribution of the pixel points, determining brightness distribution regularity, analyzing light and shade change conditions of all pixel points corresponding to the highest gray level in the current continuous electrical equipment image to be monitored, determining spark flicker possibility, analyzing edge definition in the electrical equipment image to be monitored, determining definition analysis factors, obtaining spark coefficients and obtaining safety monitoring results. The application aims to improve the reliability of safety monitoring of electrical equipment.

Inventors

LI XIAONA
LI JINGJING
LI HONGZHEN

Assignees

河北辰睿盛新能源科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260128

Claims (10)

1. An electrical equipment safety monitoring method of a pan-tilt camera is characterized by comprising the following steps: continuously acquiring an image of the electrical equipment to be monitored, and acquiring a corresponding normal operation image of the electrical equipment; Analyzing morphological characteristics of edges in the image of the electrical equipment to be monitored, comparing the morphological characteristics with the edge characteristics in the image of the normal operation of the electrical equipment, and determining edge analysis factors of the image of the electrical equipment to be monitored; grading the gray value distribution in the electrical equipment image to be monitored, analyzing the change characteristics of gray values of all pixel points in adjacent gray levels in the image along with the position distribution of the pixel points, comparing the change characteristics with the change characteristics in the electrical equipment normal operation image, and determining the brightness distribution regularity of the electrical equipment image to be monitored; Analyzing the brightness change conditions of all pixel points corresponding to the current highest gray level in the continuous to-be-monitored electrical equipment images, and determining the spark flicker possibility of the to-be-monitored electrical equipment; Analyzing the edge definition degree in the electrical equipment image to be monitored through the gray level difference, comparing the edge definition degree with the edge definition degree in the electrical equipment normal operation image, and determining a definition analysis factor of the electrical equipment image to be monitored; and (3) integrating the edge analysis factors, the gray level distribution regularity, the spark flicker possibility and the definition analysis factors, and obtaining the spark coefficient of the current electrical equipment to be monitored to obtain the safety monitoring result of the electrical equipment to be monitored.
2. The method for monitoring the safety of an electrical device by using a pan-tilt camera according to claim 1, wherein the determining the edge analysis factor of the image of the electrical device to be monitored is specifically Screening suspected spark edges according to gray value distribution characteristics of edge pixel points on each edge line aiming at an electrical equipment image to be monitored; Taking the overall distribution characteristics of the irregularity degree of all suspected spark edges in the electrical equipment image to be monitored as the irregularity coefficient of the image; And obtaining a difference value between the irregular coefficient of the electrical equipment image and the irregular coefficient of the standard electrical equipment image, multiplying the difference value with the irregular coefficient of the electrical equipment image, and normalizing to obtain an edge analysis factor.
3. The electrical equipment safety monitoring method of a pan-tilt camera according to claim 2, wherein the determining the degree of irregularity of the suspected spark edge is specifically: Counting the number of edge pixel points which are also suspected spark edges in the eight neighborhood range of each edge pixel point for each edge pixel point, and if the number is larger than a preset value, marking the edge pixel point as a characteristic pixel point; And counting the maximum value of the difference of the gradient modes between each edge pixel point of the suspected spark edge and the rest edge pixel points in the preset range, accumulating the maximum values obtained by all edge pixel points on the suspected spark edge, and carrying out forward fusion with the number of all characteristic pixel points on the suspected spark edge to obtain the irregularity degree of the suspected spark edge.
4. The method for monitoring the safety of an electrical device of a pan-tilt camera according to claim 1, wherein the determining the regularity of the brightness distribution of the image of the electrical device to be monitored is specifically: Obtaining a brightness center by using a centroid method for the pixel point with the highest gray level, and marking the brightness center as an optical center; Analyzing the change characteristics of gray scales of all pixel points in adjacent gray scales in the image along with the distance between the pixel points and the optical center, and determining the gray scale distribution regularity of the electrical equipment image to be monitored; And comparing the gray distribution regularity between the electrical equipment image to be monitored and the electrical equipment normal operation image, and combining the gray distribution regularity of the electrical equipment image to be monitored, and normalizing to obtain the brightness distribution regularity of the electrical equipment image to be monitored.
5. The method for monitoring the safety of electrical equipment of a pan-tilt camera according to claim 4, wherein the determining the gray level distribution regularity of the electrical equipment image to be monitored comprises the following steps: And calculating the difference between the average distances between all pixel points of two adjacent gray scales and the optical center, and counting the number of the difference less than 0 obtained by all the two adjacent gray scales as the gray distribution regularity of the electrical equipment image.
6. The method for monitoring safety of electrical equipment of a pan-tilt camera according to claim 1, wherein the determining the possibility of spark flicker of the electrical equipment to be monitored is specifically: extracting a preset number of frame images of the electrical equipment to be monitored, and performing curve fitting based on the gray integral distribution characteristics of all pixel points of the current highest gray level in each frame image; And calculating the gray difference value between each maximum value and the minimum value with the closest interval in the fitting curve, accumulating all the gray difference values obtained by the fitting curve, carrying out forward fusion with the number of the maximum values on the fitting curve, and normalizing to obtain the possibility of spark flicker of the electrical equipment to be monitored.
7. The method for monitoring the safety of an electrical device of a pan-tilt camera according to claim 1, wherein the determining a definition analysis factor of an image of the electrical device to be monitored specifically comprises: Calculating the difference between the gray values of the edge pixel points in the electrical equipment image to be monitored and all the pixel points in the neighborhood of the edge pixel points to be monitored, averaging to obtain average difference, calculating the average value of the average difference obtained by all the edge pixel points in the image, and normalizing to obtain the definition of the electrical equipment image to be monitored; The method comprises the steps of obtaining the definition difference between an electrical equipment image to be monitored and a normal operation image of the electrical equipment, and combining the definition of the electrical equipment image to be monitored to obtain a definition analysis factor of the electrical equipment image to be monitored, wherein the definition analysis factor and the definition of the electrical equipment image to be monitored form a positive correlation and a negative correlation.
8. The method for monitoring the safety of electrical equipment of a pan-tilt camera according to claim 1, wherein the step of obtaining the spark coefficient of the electrical equipment to be monitored comprises the following steps: And calculating the result of forward fusion of the edge analysis factor, the spark flicker possibility and the brightness distribution regularity, and taking the product of the negative correlation mapping result of the definition analysis factor and the forward fusion result as the spark coefficient of the current electrical equipment to be monitored.
9. The method for monitoring the safety of electrical equipment by using a pan-tilt camera according to claim 1, wherein the specific process of obtaining the safety monitoring result of the electrical equipment to be monitored is as follows: And counting the minimum value of the spark coefficient of the electrical equipment image with the spark in the history, judging that the electrical equipment has a safety problem if the spark coefficient of the electrical equipment to be monitored at present exceeds the minimum value, and if not, continuing to monitor.
10. An electrical equipment safety monitoring system of a pan-tilt camera, comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1-9 when executing the computer program.

Description

Electrical equipment safety monitoring method and system for cradle head camera Technical Field The application relates to the technical field of image recognition, in particular to an electrician equipment safety monitoring method and system of a cradle head camera. Background With the development of industrial automation, smart grids and smart cities, the operation safety, reliability and intelligence level of power systems are increasingly emphasized. The electrical equipment is used as a core component of the power system, and the running state of the electrical equipment is directly related to the safety and stability of the whole power grid. Monitoring of electrical equipment security based on pan-tilt cameras has made significant progress in recent years. The cradle head camera has the functions of remote controllable horizontal/vertical rotation and optical zooming, can flexibly aim at a plurality of monitoring targets, and can realize automatic identification and early warning of risk factors such as abnormal appearance, abnormal temperature, smog flame, personnel illegal operation and the like of electrical equipment by combining technologies such as image identification, infrared thermal imaging, edge calculation and the like. Currently, many methods for extracting spark fault characteristics of electrical equipment through a pan-tilt camera mainly rely on brightness information of images to judge and identify faults. However, this method has a certain limitation in that it often ignores factors such as lighting conditions, which may have a significant impact on the accuracy of the electrical equipment spark failure recognition. Disclosure of Invention In view of the foregoing, it is necessary to provide a method and a system for monitoring safety of an electrical device of a pan-tilt camera, which solve the above problems. The first aspect of the application provides an electrical equipment safety monitoring method of a pan-tilt camera, which comprises the following steps: continuously acquiring an image of the electrical equipment to be monitored, and acquiring a corresponding normal operation image of the electrical equipment; Analyzing morphological characteristics of edges in the image of the electrical equipment to be monitored, comparing the morphological characteristics with the edge characteristics in the image of the normal operation of the electrical equipment, and determining edge analysis factors of the image of the electrical equipment to be monitored; grading the gray value distribution in the electrical equipment image to be monitored, analyzing the change characteristics of gray values of all pixel points in adjacent gray levels in the image along with the position distribution of the pixel points, comparing the change characteristics with the change characteristics in the electrical equipment normal operation image, and determining the brightness distribution regularity of the electrical equipment image to be monitored; Analyzing the brightness change conditions of all pixel points corresponding to the current highest gray level in the continuous to-be-monitored electrical equipment images, and determining the spark flicker possibility of the to-be-monitored electrical equipment; Analyzing the edge definition degree in the electrical equipment image to be monitored through the gray level difference, comparing the edge definition degree with the edge definition degree in the electrical equipment normal operation image, and determining a definition analysis factor of the electrical equipment image to be monitored; and (3) integrating the edge analysis factors, the gray level distribution regularity, the spark flicker possibility and the definition analysis factors, and obtaining the spark coefficient of the current electrical equipment to be monitored to obtain the safety monitoring result of the electrical equipment to be monitored. Wherein the determining of the edge analysis factor of the electrical equipment image to be monitored is specifically that Screening suspected spark edges according to gray value distribution characteristics of edge pixel points on each edge line aiming at an electrical equipment image to be monitored; Taking the overall distribution characteristics of the irregularity degree of all suspected spark edges in the electrical equipment image to be monitored as the irregularity coefficient of the image; And obtaining a difference value between the irregular coefficient of the electrical equipment image and the irregular coefficient of the standard electrical equipment image, multiplying the difference value with the irregular coefficient of the electrical equipment image, and normalizing to obtain an edge analysis factor. The determining the irregular degree of the suspected spark edge specifically comprises the following steps: Counting the number of edge pixel points which are also suspected spark edges in the eight neighborhood range of each edge pixel