Motion characterization by temporal slices analysis

• Main Authors: NGO, Chong-wah, PONG, Ting-Chuen, ZHANG, Hong-Jiang, CHIN, Roland T.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2000
• Subjects: Motion analysis; Cameras; Image analysis; Image motion analysis; Histograms; Tensile stress; Partitioning algorithms; Indexing; Layout; Algorithm design and analysis; Computer Sciences; Numerical Analysis and Scientific Computing; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/6377; https://ink.library.smu.edu.sg/context/sis_research/article/7380/viewcontent/motion_temporal_slice_analysis.pdf
• Institution: Singapore Management University

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 oriented 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.