Particle Swarm Optimization with Soft Search Space Partitioning for Video-Based Markerless Pose Tracking

详细信息    查看全文

• 作者：Patrick Fleischmann (21)
  Ivar Austvoll (22)
  Bogdan Kwolek (23)
  
• 关键词：Video Processing ; Particle Swarm Optimization ; Motion Capture
• 刊名：Lecture Notes in Computer Science
• 出版年：2012
• 出版时间：2012
• 年：2012
• 卷：7517
• 期：1
• 页码：491-502
• 全文大小：1120KB
• 参考文献：1. Balan, A., Sigal, L., Black, M.: A quantitative evaluation of video-based 3d person tracking. In: 2nd It. IEEE Int. Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance 2005, pp. 349鈥?56 (2005)
  2. Ballan, L., Cortelazzo, G.M.: Marker-less motion capture of skinned models in a four camera set-up using optical flow and silhouettes. In: 3DPVT (2008)
  3. Clerc, M., Kennedy, J.: The particle swarm - explosion, stability, and convergence in a multidimensional complex space. IEEE Trans. Evol. Comput.聽6(1), 58鈥?3 (2002) CrossRef
  4. Deutscher, J., Reid, I.: Articulated body motion capture by stochastic search. Int. J. Comput. Vision聽61, 185鈥?05 (2005) CrossRef
  5. Gall, J., Potthoff, J., Schn枚rr, C., Rosenhahn, B., Seidel, H.P.: Interacting and annealing particle filters: Mathematics and a recipe for applications. J. Math. Imaging Vision聽28, 1鈥?8 (2007) CrossRef
  6. Gall, J., Rosenhahn, B., Brox, T., Seidel, H.P.: Optimization and filtering for human motion capture. Int. J. Comput. Vision聽87, 75鈥?2 (2010) CrossRef
  7. Ivekovic, S., Trucco, E.: Human body pose estimation with pso. In: IEEE Congr. Evolutionary Computation, CEC 2006, pp. 1256鈥?263 (2006)
  8. John, V., Trucco, E., Ivekovic, S.: Markerless human articulated tracking using hierarchical particle swarm optimisation. Image Vision Comput.聽28(11), 1530鈥?547 (2010) CrossRef
  9. Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of the IEEE Int. Conf. on Neural Networks 1995, vol.聽4, pp. 1942鈥?948 (1995)
  10. Krzeszowski, T., Kwolek, B., Wojciechowski, K.: Model-Based 3D Human Motion Capture Using Global-Local Particle Swarm Optimizations. In: Burduk, R., Kurzy艅ski, M., Wo藕niak, M., 呕o艂nierek, A. (eds.) Computer Recognition Systems 4. AISC, vol.聽95, pp. 297鈥?06. Springer, Heidelberg (2011) CrossRef
  11. Kwolek, B., Krzeszowski, T., Wojciechowski, K.: Swarm Intelligence Based Searching Schemes for Articulated 3D Body Motion Tracking. In: Blanc-Talon, J., Kleihorst, R., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2011. LNCS, vol.聽6915, pp. 115鈥?26. Springer, Heidelberg (2011) CrossRef
  12. Moeslund, T., Hilton, A., Kr眉ger, V.: A survey of advances in vision-based human motion capture and analysis. Comput. Vision Image Understanding聽104(2-3), 90鈥?26 (2006) CrossRef
  13. Robertson, C., Trucco, E.: Human body posture via hierarchical evolutionary optimization. In: BMVC 2006, vol.聽3, p. 999 (2006)
  14. Sigal, L., Balan, A., Black, M.: HumanEva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vision聽87, 4鈥?7 (2010) CrossRef
  15. Sminchisescu, C., Triggs, B.: Covariance scaled sampling for monocular 3d body tracking. In: IEEE Computer Soc. on Conf. Computer Vision and Pattern Recognition, CVPR, vol.聽1, pp. I:447鈥揑:454. IEEE (2001)
  
• 作者单位：Patrick Fleischmann (21)
  Ivar Austvoll (22)
  Bogdan Kwolek (23)
  
  21. Institute for Communication Systems ICOM, University of Applied Sciences of Eastern Switzerland, 8640, Rapperswil, Switzerland
  22. Dept. of Electrical and Computer Engineering, University of Stavanger, N-4036, Stavanger, Norway
  23. Rzesz贸w University of Technology, 35-959, Rzesz贸w, Poland
  

文摘

This paper proposes a new algorithm called soft partitioning particle swarm optimization (SPPSO), which performs video-based markerless human pose tracking by optimizing a fitness function in a 31-dimensional search space. The fitness function is based on foreground segmentation and edges. SPPSO divides the optimization into two stages that exploit the hierarchical structure of the model. The first stage only optimizes the most important parameters, whereas the second is a global optimization which also refines the estimates from the first stage. Experiments with the publicly available Lee walk dataset showed that SPPSO performs better than the annealed particle filter at a frame rate of 20 fps, and equally well at 60 fps. The better performance at the lower frame rate is attributed to the explicit exploitation of the hierarchical model structure.