On-line intelligent visual identification algorithm of power equipment state under the complex environment based on SIFT

At present, the application of computer vision technology in power systems is increasing. The idea of using image processing and machine vision to monitor power equipment is not new. However, the research mainly focuses on the application of computer vision technology in the fields of transmission line environment and insulator detection. Combined the actual conditions of the intelligent grid substation and the need of construction, this paper proposed and studied a kind of identification algorithm based on intelligent computer vision technology, aiming at solving the problem of automatic identification of typical outdoor circuit breakers, disconnectors and indoor switchgear. First, using scale-invariant feature transform (scale invariant feature transform, SIFT) algorithm, the paper accurately positions the area to be detected; second, extracts isolating switch line information and switchgear circle information using randomized Hough transform, and through the k-NN (k-Nearest Neighbour) extracts and ferreting breaker character information; Finally, three kinds of electric power equipment are identified intelligently by threshold setting, and the identification effect and stability of the algorithm are validated in the disconnector and Qing He substation of a 500 kv substation in China.