An Identification Method of Abnormal Patterns for Video Surveillance in Unmanned Substation

With the improvement of substation automatic level, video surveillance systems are widely used in the substation. In order to improve the intelligent level of monitoring and timely detect abnormalities, an identification method of abnormal patterns of surveillance video in unmanned substation environment is proposed in this paper. The method involves the following work: obtain moving objects by background subtraction, extract features for people and flame and use hierarchical SVMs classification to identify people and flame. Simulation experiment using actual video data is implemented, and experimental results show that the proposed method can correctly identify people and flame and eliminate interferences such as the impact of incandescent lamps. It can provide the necessary conditions for truly unattended substation.