Zhang, X. and Li, C. and Tong, X. and Hu, W. and Maybank, Stephen J. and Zhang, Y. (2009) Efficient human pose estimation via parsing a tree structure based human model. In: IEEE 12th International Conference on Computer Vision: (ICCV 2009), 29 Sep - 02 Oct 2009, Kyoto, Japan.Full text not available from this repository.
Human pose estimation is the task of determining the states (location, orientation and scale) of each body part. It is important for many vision understanding applications, e.g. visual interactive gaming, immersive virtual reality, content-based image retrieval, etc. However, it remains a challenging task because of unknown image background, presence of clutter, partial occlusion and especially the high dimensional state space (usually 30+ dimensions). In this paper, we contribute to human pose estimation in two aspects. First, we design two efficient Markov Chain dynamics under the data-driven Markov Chain Monte Carlo (DDMCMC) framework to effectively explore the complex solution space. Second, we parse the tree structure state space into a lexicographic order according to the image observations and body topology, and the optimization process is conducted in this order. This realizes a much more efficient exploration than the sampling based search and exhaustive search, and thus achieves a tremendous speed-up. Experimental results demonstrate the efficiency and effectiveness of the proposed method in estimating various kinds of human poses, even with cluttered background , poor illumination or partial self-occlusion.
|Item Type:||Conference or Workshop Item (Paper)|
|Keyword(s) / Subject(s):||Biological system modeling, Content based retrieval, Humans, Image retrieval, Monte Carlo methods, State estimation, State-space methods, Topology, Tree data structures, Virtual reality|
|School or Research Centre:||Birkbeck Schools and Research Centres > School of Business, Economics & Informatics > Computer Science and Informatics|
|Date Deposited:||05 Nov 2012 11:24|
|Last Modified:||17 Apr 2013 12:26|
Archive Staff Only (login required)