Motion detection with spatiotemporal sequences

In this paper we propose a new method to detect motion in a greyscale video. In our algorithm, several spatiotemporal sequences with different lengths are used to filter the frames in the video. Then these filtered images are combined together to get the real motion. The performance of our algorithm is tested with several human action datasets in which different actions are performed. The detected results of our algorithm are compared with previous works and the targets we extract manually. The experimental results show that the responses of our filter are close to the real action of the human in the original video.