Human Behavior Classification Using Multi-Class Relevance Vector Machine

Problem statement: In computer vision and robotics, one of the typica l tasks is to identify specific objects in an image and to determine each object's position and orientation relative to coordinate system. This study presented a Multi-cla ss Relevance Vector machine (RVM) classification algorithm which classifies different human poses fr om a single stationary camera for video surveillanc e applications. Approach: First the foreground blobs and their edges are obta ined. Then the relevance vector machine classification scheme classified the normal and abnormal behavior. Results: The performance proposed by our method was compared with Support Vector Machine (SVM) and multi-class support vector machine. Experimental re sults showed the effectiveness of the method. Conclusion: It is evident that RVM has good accuracy and lesse r computational than SVM.

[1]  Edoardo Ardizzone,et al.  Pose classification using support vector machines , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[2]  Nikos Paragios,et al.  Motion-based background subtraction using adaptive kernel density estimation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[3]  Massimo Piccardi,et al.  Background subtraction techniques: a review , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[4]  Nizar Bouguila,et al.  A Robust Video Foreground Segmentation by Using Generalized Gaussian Mixture Modeling , 2007, Fourth Canadian Conference on Computer and Robot Vision (CRV '07).

[5]  Andrew Blake,et al.  A sparse probabilistic learning algorithm for real-time tracking , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Ankur Agarwal,et al.  Monocular Human Motion Capture with a Mixture of Regressors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[7]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[8]  B. Triggs,et al.  3D human pose from silhouettes by relevance vector regression , 2004, CVPR 2004.

[9]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[10]  Michael E. Tipping.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001, J. Mach. Learn. Res..

[11]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Björn Stenger,et al.  Pose estimation and tracking using multivariate regression , 2008, Pattern Recognit. Lett..

[13]  Bao-Liang Lu,et al.  Multi-view Gender Classification Using Local Binary Patterns and Support Vector Machines , 2006, ISNN.

[14]  Hao Tang,et al.  Sparse Bayesian approach to classification , 2005, Proceedings. 2005 IEEE Networking, Sensing and Control, 2005..

[15]  Peng Zhang,et al.  Vision-Based Human-Computer System Using Hand Gestures , 2009, 2009 International Conference on Computational Intelligence and Security.