针对当前无人值守变电站遥视系统由人工监视的弊端,提出了在无人值守变电站遥视系统中加入视频分析的新构想,以提高监控水平和效果。在比较了当前多种常用视频分析算法优劣的基础上,择优选用了一种基于柯西分布统计模型的运动检测算法,并对模型的建立和维护进行了改进;采用ARM+Linux构成嵌入式系统进行了实验,实验结果表明这种系统具有较好的效果。 Aiming at the drawbacks of manual monitoring of remote monitoring system of unattended substation, a new idea of ​​adding video analysis to unmanned substation remote monitoring system was put forward to improve the monitoring level and effectiveness. Based on the comparison of the advantages and disadvantages of many commonly used video analysis algorithms, a motion detection algorithm based on Cauchy distributional statistical model is chosen as the best one, and the establishment and maintenance of the model are improved. The system experiments, the experimental results show that this system has good results.