Title :
Motion characterization by temporal slices analysis
Author :
Ngo, Chong-Wah ; Pong, Ting-Chuen ; Zhang, Hong-Jiang ; Chin, Roland T.
Author_Institution :
Dept. of Comput. Sci., Hong Kong Univ. of Sci. & Technol., Kowloon, UK
Abstract :
This paper describes an approach to characterize camera and object motions based on the analysis of spatio-temporal image volumes. In the spatio-temporal slices of image volumes, motion is depicted as oriented patterns. We propose a tensor histogram computation algorithm to represent these patterns. The motion trajectories in a histogram are tracked to describe both the camera and object motions. In addition, we exploit the similarity of the temporal slices in a volume to reliably partition a volume into motion tractable units
Keywords :
image motion analysis; video signal processing; camera motion characterisation; motion tractable units; motion trajectories; object motion characterisation; oriented patterns; spatio-temporal image volume slices; temporal slice similarity; tensor histogram computation algorithm; Algorithm design and analysis; Cameras; Histograms; Image analysis; Image motion analysis; Indexing; Layout; Motion analysis; Partitioning algorithms; Tensile stress;
Conference_Titel :
Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on
Conference_Location :
Hilton Head Island, SC
Print_ISBN :
0-7695-0662-3
DOI :
10.1109/CVPR.2000.854952