Motion Extrapolation via Human Motion Analysis

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Journal Article > Item 987654321/59940

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/59940

Title:	Motion Extrapolation via Human Motion Analysis
Authors:	Tsai, Joseph C.;Hsu, Hui-Huang;Chang, Shih-Ming;Wang, Ying-Hong;Chao, Chia-Cheng;Shih, Timothy K.
Contributors:	淡江大學資訊工程學系
Keywords:	Motion analysis;Object tracking;Object segmentation;Motion extrapolation
Date:	2010-03
Issue Date:	2011-10-05 22:28:55 (UTC+8)
Publisher:	Paramus: Rinton Press, Inc.
Abstract:	We propose a novel motion analysis algorithm by using the mean-shift segmentation and motion estimation technique. Mean shift algorithm is frequently used to extract objects from video according to its efficiency and robustness of non-rigid object tracking. For diminishing the computational complexity in searching process, an efficient block matching algorithm: cross-diamond-hexagonal search algorithm was used. In the motion analysis procedure, the stick figure of object obtained by thinning process is treated as guidance to gather the statistics of motion information. The experimental results show that the proposed method can provide precise description of the behavior of object in several video sequences and extrapolate human motion seamlessly by combining different motion clips obtained from other video sequences.
Relation:	Journal of Mobile Multimedia 6(1), pp.63-72
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

Files in This Item:

File	Size	Format
Motion Extrapolation via Human Motion Analysis.html	0Kb	HTML	25	View/Open