Human behavior classification by analyzing periodic
motions
Human behavior classification by analyzing periodic
motions
Jiangtao WANG1,Debao CHEN1,Jingyu YANG2,
1.School of Physical and
Electronic Information, Huaibei Coal Industry Teachers College, Huaibei
235000, China; 2.School of Computer Science
and Technology, Nanjing University of Science and Technology, Nanjing
210094, China;
Abstract：Recognizing human action is a critical step in many computer vision applications. In this paper, the problem of human behavior classification is addressed from a periodic motion analysis viewpoint. Our approach uses human silhouettes as motion features that can be obtained efficiently, and then projected it into a lower dimensional space where matching is performed. After a periodic analysis, each action unit is represented as a closed loop in this lower dimensional space, and matching is done by computing the distances among these loops. The main contributions are twofold: (1) an efficient periodic action feature constructing method is introduced; and (2) the difference between action units with different phase is computed adaptively with a novel distance proposed in this work. To demonstrate the effectiveness of this approach, human behavior classification experiments were performed on an open dataset. Classification results are highly accurate and show that this approach is promising and efficient.
Hsieh J W, Hsu Y T, Liao H-Y M. Video-based human movement analysis andits application to surveillance systems. IEEE Transactions on Multimedia, 2008, 10(3): 372–384 doi: 10.1109/TMM.2008.917403
Lin W, Sun M T, Poovandran R. Activity recognition usinga combination of category components and local models for video surveillance. IEEE Transaction on Circuits and Systems for VideoTechnology, 2008, 18(8): 1128–1139 doi: 10.1109/TCSVT.2008.927111
Choi J, Cho Y I, Han T. A view-based real-time human action recognitionsystem as an interface for human computer interaction. In: Proceedings of 13th International Conference onVirtual Systems and Multimedia: 112–120
Su C W, Liao H-Y M, Tyan H R. Motion flow-based video retrieval. IEEE Transactions on Multimedia, 2007, 9(6): 1193–1201 doi: 10.1109/TMM.2007.902875
Aggarwal J K, Cai Q. Human motion analysis: a review. Computer Vision and Image Understanding, 1999, 73(3): 295–304 doi: 10.1006/cviu.1998.0744
Moeslund T, Granum E. A survey of computer vision based human motion capture. Computer Vision and Image Understanding, 2001, 81(3): 231–268 doi: 10.1006/cviu.2000.0897
Wang L, Hu W, Tan T. Recent developments in human motion analysis. Pattern Recognition, 2003, 36(3): 585–601 doi: 10.1016/S0031-3203(02)00100-0
Polana R, Nelson R. Detecting activities. In : Proceedings of ComputerVision and Pattern Recognition, 1993, 2–7
Niyogi S, Adelson E. Analyzing and recognizing walking figures in xyt. In: Proceedings of Computer Vision and Pattern Recognition, 1994, 469–474
Baumberg A, Hogg D. An efficient method for contour tracking using active shape models. In: Proceedings of IEEE Workshop on Motion of Non-Rigidand Articulated Objects, 1994, 194–199 doi: 10.1109/MNRAO.1994.346236
Park S, Aggarwal J K. Recognition of human interaction using multiple features in grayscaleimages. In: Proceedings of15th International Conference on Pattern Recognition, 2000, 1: 51–54
Dever J, da VitoriaLobo N, Shah M. Automatic visual recognitionof armed robbery. In: Proceedings of IEEE International Conference on Pattern Recognition, 2002, 451–455
Zelnik-Manor L, Irani M. Statistical analysis of dynamic actions. IEEE Transactions on Pattern Recognition and Machine Intelligence, 2006, 28(9): 1530–1535 doi: 10.1109/TPAMI.2006.194
Wang L, Suter D. Analyzing humanmovements from silhouettes using manifold learning. In: Proceedings of IEEE International Conference on Video and SignalBased Surveillance, 2006, 7–7 doi: 10.1109/AVSS.2006.25
Yacoob Y, Black M J. Parameterized modeling and recognition of activities. Computer Vision Image Understanding, 1999, 73(2): 232–247 doi: 10.1006/cviu.1998.0726
Murase H, Sakai R. Moving object recognition in eigenspace representation: gait analysis and lip reading. Pattern Recognition Letter, 1996, 17(2): 155–162. doi: 10.1016/0167-8655(95)00109-3
Masoud O, Papanikolopoulos N. A method for human action recognition. Image and Vision Computing, 2003, 21(8): 729–743 doi: 10.1016/S0262-8856(03)00068-4
Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking. In: Proceedings of the IEEE Computer Society Conference on Computer Visionand Pattern Recognition, 1999, 246–252
Cutler R, Davis L. Robust real-timeperiodic motion detection, analysis, and applications. IEEE Transactions on Pattern Recognition and Machine Intelligence, 2000, 22(8): 781–796 doi: 10.1109/34.868681
Rao C, Yilmaz A, Shah M. View-invariant representationand recognition of actions. International Journal of Computer Vision, 2002, 50(2): 203–226 doi: 10.1023/A:1020350100748
Turk M, Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 1991, 13(1): 71–86 doi: 10.1162/jocn.1991.3.1.71
