Motion Recognition Based on Spatial Temporal HMM and Improved KPCA

Abstract:

In order to solve the problem that traditional intelligent surveillance is easily influenced by blocking and the capture views is limited, this paper presents a new method with 3 Kinects. Kinects are used to capture the human skeleton data and extract motion features. Principle component of raw data is extracted by using improved KPCA. Classifier is generated by using spatial-temporal Hidden Markov Model. A set of specific motions is analyzed in monitoring area. Experimental results show that this method can efficiently solve the problems that blocking and skeleton data is incomplete. It can also improve the recognition accuracy. The improved KPCA can improve the cumulative contribution rate and reduce the motion recognition time.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 2919-2923
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.2919
• Online since: May 2014
• Authors: Zhen Yi Wang*, Rui Chen, Ao Shuang Dong
• Keywords: Classifier, Improved KPCA, Intelligent Surveillance, Skeleton Data, Spatial-Temporal HMM

References

[1] Emanuela Haller, Georgiana Scarlat, Irina Mocanu, and Mihai Trăscău. Human Activity Recognition Based on Multiple Kinects. Proceedings of communications in computer and information science. Springer Berlin Heidelberg Press, 2013: 386: 48-59.

DOI: 10.1007/978-3-642-41043-7_5

[2] G Tao, PS Archambault, MF Levin. Evaluation of Kinect Skeletal Tracking in a Virtual Reality Rehabilitation System for Upper Limb Hemiparesis. Proceedings of International Conference on Virtual Rehabilitation. Philadelphia, PA, USA: IEEE Press, 2013: 164-165.

DOI: 10.1109/icvr.2013.6662084

[3] Jian Xiang, Jianguang Weng, Yueting Zhuang, Fei Wu. Ensemble learning HMM for motion recognition and retrieval by Isomap dimension reduction. Journal of Zhejiang University SCIENCE A, 2006, 7(12): 2063-(2072).

DOI: 10.1631/jzus.2006.a2063

[4] Weiya Shi and Dexian Zhang. An Improved Kernel Principal Component Analysis for Large-Scale Data Set. Proceedings of 7th International Symposium on Neural Networks. Shanghai, China: Springer Berlin Heidelberg Press, 2010: Part II: 9-16.

DOI: 10.1007/978-3-642-13318-3_2

[5] Jia Li, Amir Najmi and Robert M. Gray. Image classification by a two dimensional Hidden Markov Model. Proceedings of 1999 IEEE International Conference on Acoustics, Speech and Signal Processing. Phoenix, Arizona, U.S. A: IEEE Press, 1999: 6: 3313-3316.

DOI: 10.1109/icassp.1999.757550

[6] Feiyang Yu and Horace H S IP. Automatic Semantic Annotation of Images Using Spatial Hidden Markov Model. Proceedings of 2006 IEEE International Conference on Multimedia and Expo. Toronto, Ont: IEEE Press, 2006: 305-308.

DOI: 10.1109/icme.2006.262459