Improved region growing method for infrared image segmentation of power equipment

Abstract

The invention discloses an improved region growing method for infrared image segmentation of power equipment, and the method comprises the steps: converting an infrared image of power equipment into agray level image, employing an edge detection segmentation method to carry out the transverse and longitudinal differential operation of the gray level image, obtaining edge pixel points of the powerequipment, carrying out the matching, and preliminarily determining a possible region of the equipment; traversing the gray scale image of the area where the equipment is possibly located by using aneffectiveness detection operator to obtain an effective area, and completing preliminary division of the equipment area; automatically selecting seed points; and taking the access points obtained bydifferential operation in the transverse and longitudinal directions and the preliminarily divided equipment regions as constraints, carrying out equipment region growth operation, and removing burrsand gaps for the segmented image by utilizing morphological operation after growth is completed, thereby obtaining a final power equipment segmentation result. The method provided by the invention issimple in calculation process and good in effect, and can realize high-quality rapid automatic segmentation of large-scale infrared images in a power system.

Description

technical field [0001] The invention relates to the technical field of electric equipment detection, in particular to an improved region growing method for infrared image segmentation of electric equipment. Background technique [0002] In the status monitoring of power system equipment, infrared diagnosis technology is a widely used and effective technical means. Through infrared diagnosis technology, local overheating defects of equipment can be found, and potential failures can be avoided in time by targeted maintenance of local overheating areas, and According to the comparison of the local and global temperature of the equipment, it is judged whether there is a fault, so as to warn the operation and maintenance personnel in time, so as to avoid the occurrence of major safety operation accidents caused by untimely fault detection. Among them, image segmentation is an important link in the infrared diagnosis system of power equipment. This step provides an image basis for...

AI Technical Summary

Problems solved by technology

This method is more accurate in the selection of the gray threshold for distinguishing the target and the background, but often the selection of a threshold cannot completely distinguish the target and the background, and in most cases it can only determine a part of the background area, so it often requires multiple iterative selections of the threshold manually. The stop of its operation depends on manual intervention, which makes it impossible to solve the automatic segmentation of infrared images of large-scale power equipment common in power systems

The image segmentation method based on region growing has the problem of selecting the seed point. The traditional region growing algorithm needs to manually select the seed point through the interactive interface, and it is also unable to realize automatic positioning. It also exists when applying to the infrared image segmentation of large-scale power equipment. The problem of excessive workload and the need for manual cooperation

The method based on edge detection first uses different edge detection operators to perform convolution traversal on the infrared image, and divides the convolution results into two categories according to the value. Generally, the pixels corresponding to the positions with larger values ​​are marked as edges. The edge connection divides the image into different regions, and performs statistical analysis on the regional characteristics, so as to judge which regions belong to the target and which part of the region belongs to the background, and then complete the segmentation. For power equipment that is not high enough, it is often difficult to connect the edge pixels. If the edge pixels cannot be correctly connected into a closed curve, it is impossible to divide the area to realize the segmentation of the infrared image of the power equipment.

Images