Thermal Defect Identification Method for Power Equipment Based on Redundancy Features

In order to meet the requirement of thermal defect detection of power equipment, a thermal defect identification method based on redundancy features is proposed in thispaper. Firstly, the spectral residual transform model is constructed according to the redundancy features of natural background in the infrared image of power equipment and the significance features of thermal defect target, and the spectral residual transform is carried out on the infrared image of power equipment to generate the initial thermal defect recognition diagram with significant information. Then, the guided filtering technology is used to process the initial recognition results, and temperature difference information and spatial structure information in infrared images are combined to improve the recognition rate of thermal defects and generate the final recognition result map. The experimental results show that compared with other traditional thermal defect identification methods, the proposed method has significant advantages in recognition accuracy and recognition efficiency, and can meet the application requirements of electric power equipment thermal defect detection.