Method for automatic key posture information abstraction

作者: Duan-Yu Chen , Hong-Yuan Liao

DOI:

关键词:

摘要: The method for automatic key posture information abstraction of this invention comprises the steps of: Abstracting from a series continuous digitized images spatial features objects contained in said images; abstracting shape using probability calculation; detecting entropy removing redundant postures; mating obtained postures with templates stored codebook; and encoding mated postures.

参考文章(9)
Monique Thonnat, François Bremond, Bernard Boulay, Human Posture Recognition in Video Sequence IEEE International Workshop on VS-PETS, Visual Surveillance and Performance Evaluation of Tracking and Surveillance. ,(2003)
Michael J. Swain, Frederic Dufaux, System for selecting a keyframe to represent a video ,(2004)
Serhan Dagtas, Tomas Brodsky, Vasanth Philomin, Mi-Suen Lee, Miroslav Trajkovic, Srinivas Gutta, Hugo Strubbe, Yun-Ting Lin, Method and apparatus for detecting an event based on patterns of behavior ,(2002)
I. Haritaoglu, D. Harwood, L.S. Davis, Ghost: a human body part labeling system using silhouettes international conference on pattern recognition. ,vol. 1, pp. 77- 82 ,(1998) , 10.1109/ICPR.1998.711084
Yuusuke Nakano, Yuichi Kawakami, Youichi Kawakami, Daisaku Horie, Method for detecting object formed of regions from image ,(2003)
Tao Zhao, R. Nevatia, Fengjun Lv, Segmentation and tracking of multiple humans in complex situations computer vision and pattern recognition. ,vol. 2, pp. 194- 201 ,(2001) , 10.1109/CVPR.2001.990958
A.F. Bobick, J.W. Davis, The recognition of human movement using temporal templates IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 23, pp. 257- 267 ,(2001) , 10.1109/34.910878