Human Activity Recognition Based on R Transform

This paper addresses human activity recognition based on a new feature descriptor. For a binary human silhouette, an extended radon transform, R transform, is employed to represent low-level features. The advantage of the R transform lies in its low computational complexity and geometric invariance. Then a set of HMMs based on the extracted features are trained to recognize activities. Compared with other commonly-used feature descriptors, R transform is robust to frame loss in video, disjoint silhouettes and holes in the shape, and thus achieves better performance in recognizing similar activities. Rich experiments have proved the efficiency of the proposed method.

[1]  Deepak Gangadharan,et al.  Application of the wavelet-based Radon transform , 1998, Other Conferences.

[2]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[3]  M. Thonnat,et al.  Video sequence interpretation for visual surveillance , 2000, Proceedings Third IEEE International Workshop on Visual Surveillance.

[4]  Ramakant Nevatia,et al.  Video-based event recognition: activity representation and probabilistic recognition methods , 2004, Comput. Vis. Image Underst..

[5]  M. Teague.  Image analysis via the general theory of moments , 1980 .

[6]  Thomas Sikora,et al.  Comparison of static background segmentation methods , 2005, Visual Communications and Image Processing.

[7]  Guojun Lu,et al.  Study and evaluation of different Fourier methods for image retrieval , 2005, Image Vis. Comput..

[8]  Tieniu Tan,et al.  Recent developments in human motion analysis , 2003, Pattern Recognit..

[9]  John K. Tsotsos,et al.  Detecting abnormal gait , 2005, The 2nd Canadian Conference on Computer and Robot Vision (CRV'05).

[10]  Richard J. Prokop,et al.  A survey of moment-based techniques for unoccluded object representation and recognition , 1992, CVGIP Graph. Model. Image Process..

[11]  Filiberto Pla,et al.  Extracting Motion Features for Visual Human Activity Representation , 2005, IbPRIA.

[12]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Laurent Wendling,et al.  A new shape descriptor defined on the Radon transform , 2006, Comput. Vis. Image Underst..

[14]  PhD V. F. Leavers BSc.  Shape Detection in Computer Vision Using the Hough Transform , 1992, Springer London.

[15]  C.-C. Jay Kuo,et al.  Wavelet descriptor of planar curves: theory and applications , 1996, IEEE Trans. Image Process..

[16]  Dinggang Shen,et al.  Discriminative wavelet shape descriptors for recognition of 2-D patterns , 1999, Pattern Recognit..

[17]  Howard D. Wactlar,et al.  Dining activity analysis using a hidden Markov model , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[18]  Roland T. Chin,et al.  On image analysis by the methods of moments , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[20]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[21]  Guojun Lu,et al.  Shape-based image retrieval using generic Fourier descriptor , 2002, Signal Process. Image Commun..