2D Articulated Body Tracking with Self-occultations Handling
Recently many methods for human articulated body tracking were proposed in the literature. These techniques are often computationally intensive and cannot be used for Human-Computer Interface. We propose in this article a real-time algorithm for upper body tracking with occultation handling. The tracking is based on an articulated body model, also used to automatically initialize the target. After an independent search of the most likely positions of each limb, a dynamic programming algorithm is used to find the best configuration according to the links between limbs. The self-occultations between the limbs are directly taken into account by the tracking algorithm and results show the interest of the proposed approach.
KeywordsTracking humanoid articulated model occultations handling dynamic programming real-time processing computer vision
Unable to display preview. Download preview PDF.
- 5.Ju, S.X., Black, M.J., Yacoob, Y.: Cardboard People: A Parameterized Model of Articulated Image Motion. In: Int. Conf. on Auto. Face and Gesture Recognition, pp. 38–44 (1996)Google Scholar
- 6.Demirdjian, D., Taycher, L., Shakhnarovich, G., Grauman, K., Darrell, T.: Avoiding the Streetlight Effect: Tracking by Exploring Likelihood Modes. In: IEEE Int. Conf. on Comput. Vis., vol. 1, pp. 357–364 (2005)Google Scholar
- 7.Sigal, L., Black, M.J.: Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation. IEEE Comput. Society Conf. on Comput. Vis. and Pattern Recognition 2, 2041–2048 (2006)Google Scholar
- 9.Bernier, O., Cheung-Mon-Chan, P.: Real-Time 3D Articulated Pose Tracking using Particle Filtering and Belief Propagation on Factor Graphs. In: British Machine Vision Conf. (2006)Google Scholar
- 10.Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient matching of pictorial structures. Comput. Vis. and Pattern Recognition 2, 66–73 (2000)Google Scholar