Probabilistic models of image motion for recognition of dynamic content in video

We present new probabilistic motion models of interest for the detection of meaningful dynamic contents (or events) in videos. We separately handle the dominant image motion assumed to be due to the camera motion and the residual image motion related to scene motion. These two motion components are then represented by different probabilistic models which are further recombined for the event detection task. Two solutions are investigated for the residual motion. The motion models (both for camera motion and scene motion) associated to pre-identified classes of meaningful events are learned from a training set of video samples. The detection scheme proceeds in two steps which exploit different kinds of information and allow us to progressively select the video segments of interest using Maximum Likelihood (ML) criteria. The efficiency of the proposed approach is demonstrated on sport videos.