Swarm Intelligence Based Searching Schemes for Articulated 3D Body Motion Tracking
We investigate swarm intelligence based searching schemes for effective articulated human body tracking. The fitness function is smoothed in an annealing scheme and then quantized. This allows us to extract a pool of candidate best particles. The algorithm selects a global best from such a pool. We propose a global-local annealed particle swarm optimization to alleviate the inconsistencies between the observed human pose and the estimated configuration of the 3D model. At the beginning of each optimization cycle, estimation of the pose of the whole body takes place and then the limb poses are refined locally using smaller number of particles. The investigated searching schemes were compared by analyses carried out both through qualitative visual evaluations as well as quantitatively through the use of the motion capture data as ground truth. The experimental results show that our algorithm outperforms the other swarm intelligence searching schemes. The images were captured using multi-camera system consisting of calibrated and synchronized cameras.
KeywordsParticle Swarm Optimization Particle Swarm Optimization Algorithm Motion Capture Swarm Intelligence Motion Capture Data
Unable to display preview. Download preview PDF.
- 1.Arsic, D., Lyutskanov, A., Rigoll, G., Kwolek, B.: Multi camera person tracking applying a graph-cuts based foreground segmentation in a homography framework. In: IEEE Int. Workshop on Performance Evaluation of Tracking and Surveillance, pp. 30–37. IEEE Press, Piscataway (2009)Google Scholar
- 3.Deutscher, J., Blake, A., Reid, I.: Articulated body motion capture by annealed particle filtering. In: IEEE Int. Conf. on Pattern Recognition, pp. 126–133 (2000)Google Scholar
- 9.Krzeszowski, T., Kwolek, B., Wojciechowski, K.: Model-based 3D human motion capture using global-local particle swarm optimizations. In: Burduk, R., Kurzyński, M., Woźniak, M., Żołnierek, A. (eds.) Computer Recognition Systems 4. Advances in Intelligent and Soft Computing, vol. 95, pp. 297–306. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 11.Schmidt, J., Fritsch, J., Kwolek, B.: Kernel particle filter for real-time 3D body tracking in monocular color images. In: IEEE Int. Conf. on Face and Gesture Rec., pp. 567–572. IEEE Computer Society Press, Southampton (2006)Google Scholar
- 14.Sminchisescu, C., Kanaujia, A., Li, Z., Metaxas, D.: Discriminative density propagation for 3D human motion estimation. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition, pp. I:390–I:397 (2005)Google Scholar
- 15.Zhang, X., Hu, W., Wang, X., Kong, Y., Xie, N., Wang, H., Ling, H., Maybank, S.: A swarm intelligence based searching strategy for articulated 3D human body tracking. In: IEEE Workshop on 3D Information Extraction for Video Analysis and Mining in Conjuction with CVPR, pp. 45–50. IEEE, Los Alamitos (2010)Google Scholar