Separation of Moving Regions from Background in an Image Sequence Acquired with a Mobil Camera

We present a statistical method to detect regions whose apparent motion in the image is not conforming to the dominant motion of the background resulting from the camera movement. Alternatively, the same scheme can be used to track a particular region of interest of the scene. The apparent motion induced by the camera motion is represented by a 2D parametric motion model, and compensated for using the values of the motion model parameters estimated by a multiresolution robust statistical technique. Then, regions whose motion cannot be described by this global model estimated over the entire image, are extracted. The detection of these non conforming regions is achieved through a statistical regularization approach based on multiscale Markov random field (MRF) models. We have paid a particular attention to the definition of the energy function involved and to the observations taken into account. To gain robustness, information is integrated over time. This method has been validated by experiments carried out on many real image sequences.