Detection and segmentation of moving objects in complex scenes

Detecting and segmenting moving objects in dynamic scenes is a hard but essential task in a large number of applications such as surveillance. Most existing methods only give good results in the case of persistent or slowly changing background, or if both the objects and the background can be characterized by simple parametric motions. This paper aims at detecting and segmenting foreground moving objects in the absence of such constraints. The sequences we consider have highly dynamic backgrounds, illumination changes and low contrasts, and can have been shot by a moving camera. Three main steps compose the proposed method. First, moving points are selected within a sub-grid of image pixels. A descriptor is associated to each of these points. Clusters of points are then formed using a variable bandwidth mean shift with automatic bandwidth selection. Finally, segmentation of the object associated to a given cluster is performed using Graph cuts. Experiments and comparison to other motion detection methods on challenging sequences show the performance of the proposed method and its utility for video analysis in complex scenes