Estimation of Composite Object and Camera Image Motion

An approach for estimating composite independent object and camera image motions is proposed. The approach employs spatio-temporal ow models learned through observing typical movements of the object, to decompose image motion into independent object and camera motions. The spatio-temporal ow models of the object motion are represented as a set of orthogonal ow bases that are learned using principal component analysis of instantaneous ow measurements from a stationary camera. These models are then employed in scenes with a moving camera to extract motion trajecto-ries relative to those learned. The performance of the algorithm is demonstrated on several image sequences of rigid and articulated bodies in motion.