Title :
Learned temporal models of image motion
Author :
Yacob, Y. ; Davis, Larry
Author_Institution :
Comput. Vision Lab., Maryland Univ., College Park, MD, USA
Abstract :
An approach for learning and estimating temporal-flow models from image sequences is proposed. The temporal-flow models are represented as a set of orthogonal temporal-flow bases that are learned using principal component analysis of instantaneous flow measurements. Spatial constraints on the temporal-flow are also developed for modeling the motion of regions in rigid and coordinated motion. The performance of these models is demonstrated on several long image sequences of rigid and articulated bodies in motion
Keywords :
image sequences; learning (artificial intelligence); motion estimation; estimating; image motion; image sequences; learning; temporal-flow bases; temporal-flow models; Biological system modeling; Computer vision; Humans; Image sequences; Leg; Motion analysis; Motion control; Motion estimation; Principal component analysis; Tracking;
Conference_Titel :
Computer Vision, 1998. Sixth International Conference on
Conference_Location :
Bombay
Print_ISBN :
81-7319-221-9
DOI :
10.1109/ICCV.1998.710757
