Human action recognition using distribution of oriented rectangular patches
作者： Nazlı İkizler , Pınar Duygulu
DOI: 10.1007/978-3-540-75703-0_19
关键词: Artificial intelligence 、 Classifier (UML) 、 Data structure 、 Histogram 、 Mathematics 、 Blank 、 Dynamic time warping 、 Gesture recognition 、 Iterative reconstruction 、 Support vector machine 、 Computer vision
摘要: We describe a "bag-of-rectangles" method for representing and recognizing human actions in videos. In this method, each pose an action sequence is represented by oriented rectangular patches extracted over the whole body. Then, spatial histograms are formed to represent distribution of these patches. order carry information from domain described bag-of-rectangles descriptor temporal recognition actions, four different methods proposed. These namely, (i) frame voting, which recognizes matching descriptors frame, (ii) global histogramming, extends idea Motion Energy Image proposed Bobick Davis patches, (iii) classifier based approach using SVMs, (iv) adaptation Dynamic Time Warping on representation descriptor. The detailed experiments carried out dataset Blank et. al. High success rates (100%) prove that with very simple compact representation, we can achieve robust compared complex representations.
hacettepe.edu.tr
springer.com
sci-hub.st 参考文章(27)
Thomas Leung, Jitendra Malik, Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons International Journal of Computer Vision. ,vol. 43, pp. 29- 44 ,(2001) , 10.1023/A:1011126920638
Jeffrey Mark Siskind, Reconstructing force-dynamic models from video sequences Artificial Intelligence. ,vol. 151, pp. 91- 154 ,(2003) , 10.1016/S0004-3702(03)00112-7
Yu-Gang Jiang, Chong-Wah Ngo, Jun Yang, Towards optimal bag-of-features for object categorization and semantic video retrieval conference on image and video retrieval. pp. 494- 501 ,(2007) , 10.1145/1282280.1282352
M. Blank, L. Gorelick, E. Shechtman, M. Irani, R. Basri, Actions as space-time shapes international conference on computer vision. ,vol. 2, pp. 1395- 1402 ,(2005) , 10.1109/ICCV.2005.28
C. Sminchisescu, A. Kanaujia, Zhiguo Li, D. Metaxas, Conditional models for contextual human motion recognition international conference on computer vision. ,vol. 2, pp. 1808- 1815 ,(2005) , 10.1109/ICCV.2005.59
Deva Ramanan, David A. Forsyth, Leslie Ikemoto, James F. O'Brien, Okan Arikan, Computational Studies of Human Motion ,(2006)
Fei-Fei Li, P. Perona, A Bayesian hierarchical model for learning natural scene categories computer vision and pattern recognition. ,vol. 2, pp. 524- 531 ,(2005) , 10.1109/CVPR.2005.16
C.S. Pinhanez, A.F. Bobick, Human action detection using PNF propagation of temporal constraints computer vision and pattern recognition. pp. 898- 904 ,(1998) , 10.1109/CVPR.1998.698711
A.D. Wilson, A.F. Bobick, Parametric hidden Markov models for gesture recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 21, pp. 884- 900 ,(1999) , 10.1109/34.790429
W. Hu, T. Tan, L. Wang, S. Maybank, A survey on visual surveillance of object motion and behaviors systems man and cybernetics. ,vol. 34, pp. 334- 352 ,(2004) , 10.1109/TSMCC.2004.829274