Detection of moving objects in natural scenes by a stochastic multi-feature analysis of video sequences

A new technique for the detection and description of moving objects in natural scenes is presented which is based on an object-oriented, statistical multi-feature analysis of video sequences. In most conventional schemes for the detection of moving objects, temporal differences of subsequent images from a video sequence are evaluated in a block based manner by so called change detection algorithms. These methods are based on the assumption that significant temporal changes of an image signal are caused by moving objects in the scene. However, as temporal changes of an image signal can as well be caused by many other sources (camera noise, varying illumination, small camera motion, trees in motion), such systems are afflicted with the dilemma of either causing many false alarms or failing to detect relevant events. To scope with this problem, the additional features texture and motion beyond temporal signal differences are extracted and evaluated in the new algorithm. Furthermore, these features are evaluated in an object-oriented instead of a block oriented fashion to increase the reliability of detection. The adaption of this method to normal fluctuations of the observed scene is performed by a time-recursive space-variant estimation of the temporal probability distributions of the different features (signal difference, texture and motion). Feature data which differ significantly from the estimated distributions are interpreted to be caused by moving objects.