1.School of Life Sciences and Technology,Xidian University,Xian 710071 2.College of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003
Abstract:Human motion analysis is one of the most active subjects in computer vision. Two improved dynamic texture models are proposed for human motion sequence description, binary dynamic texture model and tensor subspace dynamic texture model. A binary image is supposed to submit to Bernoulli distribution, and the logistic principle component analysis is used to learn the parameters of the binary dynamic texture model. In tensor subspace dynamic texture model, a binary image is treated as a tensor with dimensions of column and row reduced by tensor subspace analysis, and then it is transformed to a low-dimensional gray image. The dynamic texture model is applied to describe the gray image sequence. Experimental results on human activity and gait databases show the validity of the two proposed improved dynamic texture models.
[1] Wang Liang, Hu Weiming, Tan Tieniu. Recent Developments in Human Motion Analysis. Pattern Recognition, 2003, 36(3): 585-601 [2] Wang Ling, Suter D. Visual Learning and Recognition of Sequential Data Manifolds with Applications to Human Movement Analysis. Computer Vision and Image Understanding , 2008, 110(2): 153-172 [3] Polana R, Nelson R. Low Level Recognition of Human Motion // Proc of the IEEE Workshop on Motion of Non-Rigid and Articulated Objects. Austin, USA, 1994: 77-82 [4] Bobick A, Davis J. Real-Time Recognition of Activity Using Temporal Templates // Proc of the IEEE Workshop on Applications of Computer Vision. Sarasota, USA, 1996: 39-42 [5] Davis J W, Bobick A F. The Representation and Recognition of Action Using Temporal Templates. Technical Report, 402, Cambridge, USA: MIT Media Lab, 1997 [6] Yamato J, Ohya J, Ishii K. Recognizing Human Action in Time-Sequential Images Using Hidden Markov Model // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Champaign, USA, 1992: 379-385 [7] Bregler C. Learning and Recognizing Human Dynamics in Video Sequences // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. San Juan, Puerto Rico, 1997: 568-574 [8] Johnson A Y, Bobick A F. A Multi-View Method for Gait Recognition Using Static Body Parameters // Proc of the 3rd International Conference on Audio-and Video-Based Biometric Person Authentication. Halmstad, Netherlands, 2001: 301-311 [9] BenAbdelkader C, Cutler R, Davis L. Stride and Cadence as a Biometric in Automatic Person Identification and Verification // Proc of the IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 372-377 [10] Lee L, Grimson W E L. Gait Analysis for Recognition and Classification // Proc of the 5th IEEE International Conference on Face and Gesture Recognition. Washington, USA, 2002: 148-155 [11] Huang P S. Automatic Gait Recognition via Statistical Approaches for Extended Template Features. IEEE Trans on Systems, Man and Cybernetics, 2001, 31(5): 818-824 [12] Liu Yanxi, Collins R, Tsin Y. Gait Sequence Analysis Using Frieze Patterns // Proc of the 7th European Conference on Computer Vision. Copenhagen, Denmark, 2002: 657-671 [13] Phillips P J, Sarkar S, Robledo I, et al. Baseline Results for the Challenge Problem of Human ID Using Gait Analysis // Proc of the IEEE International Conference on Automatic Face and Gesture Recognition. Washington, USA, 2002: 137-143 [14] Fujita K, Nayar S K. Recognition of Dynamic Textures Using Impulse Responses of State Variables // Proc of the 3rd International Workshop on Texture Analysis and Synthesis. Nice, France, 2003: 31-36 [15] Liu Chebing, Lin R S, Ahuja N. Modeling Dynamic Textures Using Subspace Mixtures // Proc of the IEEE International Conference on Multimedia Expo. Amsterdam, Netherlands, 2005: 1378-1381 [16] Chan A B, Vasconcelos N. Layered Dynamic Textures. IEEE Trans on Pattern Analysis and Machine Intelligence, 2009, 31(10): 1862-1879 [17] Doretto G, Chiuso A, Soatto S, et al. Dynamic Textures. Inrernational Journal of Computer Vision, 2003, 51(2): 91-109 [18] Bissacco A, Chiuso A, Ma Y, et al. Recognition of Human Gaits // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii, USA, 2001, Ⅱ: 52-57 [19] Bissacco A, Saisan P, Soatto S. Gait Recognition Using Dynamic Affine Invariants // Proc of the International Symposium on Mathematical Theory of Networks and Systems. Leuven, Belgium, 2004: 1-7 [20] Mazzaro C, Sznaier M, Camps O, et al. A Model (in)Validation Approach to Gait Recognition // Proc of the 1st International Symposium on 3D Data Processing Visualization and Transmission. Thessaloniki, Greece, 2002: 700-703 [21] Schein A I, Popescul A, Ungar L, et al. A Generalized Linear Model for Principal Component Analysis of Binary Data // Proc of the 9th International Workshop on Artificial Intelligence and Statistics. Key West, USA, 2003: 14-21 [22] He Xiaofei, Cai Deng, Niyogi P. Tensor Subspace Analysis // Proc of the 9th Annual Conference on Neural Information Processing Systems. Whistler, USA, 2005: 513-520 [23] Chan A B, Vasconcelos N. Classifying Video with Kernel Dynamic Textures // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007: 1-6 [24] de Cock K, de Moor B. Subspace Angles between Linear Stochastic Models // Proc of the 39th IEEE Conference on Decision and Control. Sydney, Australia, 2000: 1561-1566 [25] Blank M, Gorelick L, Shechtman E, et al. Action as Space-Time Shapes // Proc of the International Conference on Computer Vision. Beijing, China, 2005, Ⅱ: 1395-1402 [26] Gross R, Shi J. The CMU Motion of Body (MoBo) Database. Technical Report, CMU-RI-TR-01-18, Pittsburgh, USA: Carnegie Mellon University. Robotics Institute, 2001