With the rapid development of computer technology, video surveillance systems are spread all over the streets, bringing convenience to people's lives. Video is also becoming more and more intelligent. Among them, the identification, tracking and extraction of moving targets are the challenges faced by intelligent monitoring systems. Based on the movement of the quadruped, this paper proposes an algorithm for the extraction and background reconstruction of the quadruped animal Firstly, the moving target of the video sequence is detected by combining the background subtraction method and the interframe difference method, and then the target tracking is performed based on the moving target feature. In the extraction of moving targets, an algorithm for animal moving target extraction based on spatiotemporal saliency is proposed, and the background reconstruction based on probability and statistics theory is used. Through the experiments of two similar quadruped animals, such as dogs and wolves, the proposed method has better anti-interference and better results in the recognition and extraction of moving targets.