Method and system for monitoring transformer composite insulator sleeve based on computer vision

The invention relates to a method and a system for monitoring a transformer composite insulator sleeve based on computer vision. The method is characterized in that cameras are respectively installed at portal frames above each transformer, photographed images are transmitted to a server side, and image acquisition, image pre-processing, image region segmentation, sleeve dirty staged processing and sleeve operating condition defect identification are carried out at the server side. According to the invention, the operating reliability of the transformers is improved by using visible light image identifying and processing technologies, defects are discovered in time, and dirty conditions of the sleeve are staged; and operating conditions of the sleeve are monitored and judged, and the operating reliability of the sleeve is improved. The method and the system provided by the invention can be widely applied to monitoring for transformer sleeves with various voltage grades. 种基于计算机视觉的变压器复合绝缘子套管监测方法及系统，在各变压器上空龙门架处分