An edge-based approach to motion detection

This paper presents a simple technique for motion detection in steady-camera video sequences. It consists of three stages. Firstly, a coarse moving edge representation is computed by a set of arithmetic operations between a given frame and two equidistant ones (initially the nearest ones). Secondly, non-desired edges are removed by means of a filtering technique. The previous two stages are enough for detecting edges corresponding to objects moving in the image plane with a dynamics higher than the camera's capture rate. However, in order to extract moving edges with a lower dynamics, a scheme that repeats the previous two stages at different time scales is performed. This temporal scheme is applied over couples of equidistant frames and stops when no new information about moving edges is obtained or a maximum number of iterations is reached. Although the proposed approach has been tested on human body motion detection it can be used for detecting moving objects in general. Experimental results with scenes containing movements at different speeds are presented.