WANG Weihua, LIU Zhijing. A Learning Method for Pedestrian Activity Classification[J]. Chinese Journal of Electronics, 2014, 23(1): 129-134.
Citation: WANG Weihua, LIU Zhijing. A Learning Method for Pedestrian Activity Classification[J]. Chinese Journal of Electronics, 2014, 23(1): 129-134.

A Learning Method for Pedestrian Activity Classification

Funds:  This work is supported by the National Natural Science Foundation of China (No.61173091).
  • Received Date: 2012-01-01
  • Rev Recd Date: 2013-04-01
  • Publish Date: 2014-01-05
  • Analysis of human activity and online anomaly detection from video sequences is one of the hottest and difficult research areas in computer visions. This paper describes a method for pedestrian gait classification in video sequence and deals with the classification of human gait types based on the notion that gait types can be analyzed into a series of consecutive postures types. First, silhouettes are extracted using the Background subtraction method which is combined with the time-stepping method. Then a method using recursion method for establishment of the standard gait state sequence is proposed. Meanwhile, wavelet moment method is used to extract features of the human body image, and the result matrix leads to Discrete hidden Markov models. Finally, Discrete hidden Markov models is used for human posture training, modeling and activity matching to recognize the human activity. The experiment tests show some encouraging results also indicates the algorithm has very small leak-examining and mistake-examining-rate, also shows the capability of realtime performance, which indicate that the method could be a choice for solving the problem but more tests are required.
  • loading
  • R.C. González, A.M. López, J. Rodriguez-Uría, D. Ávarez, J.C. Alvarez,"Real-time gait event detection for normal subjects from lower trunk accelerations", Gait Posture, Vol.31, No.3, pp.322-325, 2010.
    K. Arai, R.A. Asunara,"Human gait gender classification in spatial and temporal reasoning", Journal of Advanced Research in Artificial Intelligence, Vol.1, No.6, pp.1-6, 2012.
    P. Felzenszwalb, R. Girshick, D. MeAllester and D. Ramanan,"Object detection with discriminatively trained part based models", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.32, No.9, pp.1627-1645, 2008.
    Jui-Hsin Lai, Chieh-Chi Kao and Shao-Yi Chien,"Superresolution sprite with foreground removal", IEEE International Conference on Multimedia and Expo, New York, USA, pp.13061309, 2009.
    C. Wang, Y. Liu and W. Li,"Research of unsupervised posture modeling and action recognition based on spatial-temporal interesting points", Chinese Journal of Electronics, Vol.39, No.8, pp.1751-1756, 2011.
    Hu Zhilan, Jiang Fan, Wang Guijin, Lin Xinggang, Yan Hong,"Anomaly detection based on motion direction", Acta Automatica Sinica, Vol.34, No.11, pp.1348-1357, 2008.
    C.C. Yu, Y.N. Chen, H.Y. Cheng, J.N. Hwang and K.C. Fan,"Connectivity based human body modeling and behavior analysis from monocular camera", Journal of Information Science and Engineering, Vol.26, No.3, pp.363-377, 2010.
    X. Sun, Q. Zhang and Y. Xu,"Application of segmentation based on optical flow for gait recognition", in Proc. 3rd IEEE International Conference on Advanced Computer Theory and Engineering, Chengdu, China, pp.567-571, 2010.
    S. Wen, F. Wang and C. Wu,"Realtime gait kinematics classification using LDA and SVM", in Control and Decision Conference, Chinese (CCDC), Mianyang, China, pp.592-595, 2011.
    M.K. Hu,"Visual pattern recognition by moment invariants", IEEE Transactions on Information Theory, Vol.8, No.1, pp.179-187, 1962.
    L. Lee and W.E.L. Grimson,"Gait appearance for recognition", In: Lecture Notes in Computer Science, Proceeding of the International ECCV Workshop Copenhagen on Biometric Authentication, Copenhagen, Denmark, Vol.2359, pp.143-154, 2002.
    J.D. Shutler and M.S. Nixon,"Zernike velocity moments for sequence-based description of moving features", Journal of Image and Vision Computing, Vol.24, No.4, pp.343-356, 2006.
    Preben Fihl and Thomas B. Moeslund,"Classification of gait types based on the duty-factor", Advanced Video and Signal Based Surveillance, AVSS, pp.318-323, 2007.
    Liang Wang and David Suter,"Visual learning and recognition of sequential data manifolds with applications to human movement analysis", Computer Vision and Image Understanding, Vol.110, No.2, pp.153-172, 2008.
    S. Huwer and H. Niemann,"Adaptive change detection for real-time surveillance applications", Proceedings 3rd IEEE International Workshop on Visual Surveillance, Dublin, Ireland, pp.37-46, 2000.
    S.Y. Chien, S.Y. Ma, L.G. Chen,"Efficient moving object segmentation algorithm using background registration technique", IEEE Trans Circuits and Systems, Vol.12, No.7, pp.577-586, 2002.
    Ismail Haritaoglu, David Harwood, Larry S. Davis,"W4 real-time surveillance of people and their activities", IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.22, No.8, pp.809-830, 2000.
    C.S. Chan, H. Liu, D.J. Brown,"Recognition of human motion from qualitative normalised templates", Journal of Intelligent and Robotic Systems, Vol.48, No.1, pp.79-95, 2007.
    G.Y. Zhao, Z.B. Li, Y. Deng,"Human motion recognition and simulation based on retrieval", Journal of Computer Research and Development, Vol.43, No.2, pp.368-374, 2006. (in Chinese)
    G.Y. Zhao, L. Cui, H. Li,"Combining wavelet velocity moments and reflective symmetry for gait recognition", IWBRS, Beijing. LNCS, pp.205-212, 2005.
  • 加载中


    通讯作者: 陈斌,
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (181) PDF downloads(1167) Cited by()
    Proportional views


    DownLoad:  Full-Size Img  PowerPoint