Estimation of composite object and camera image motion

TitleEstimation of composite object and camera image motion
Publication TypeConference Papers
Year of Publication1999
AuthorsYacoob Y, Davis LS
Conference NameThe Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999
Date Published1999///
ISBN Number0-7695-0164-8
Keywordsarticulated bodies, camera image motion, camera image motions, CAMERAS, composite independent object, composite object estimation, Computer vision, Educational institutions, Image sequences, instantaneous flow measurements, Laboratories, Layout, Motion analysis, Motion estimation, motion trajectories, orthogonal flow bases, Principal component analysis, spatio-temporal flow models, tracking, Vehicles

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