A Hybrid Framework for 3-D Human Motion Tracking

• Published in: IEEE transactions on circuits and systems for video technology Vol. 18; no. 8; pp. 1075 - 1084
• Main Authors: Bingbing Ni, Kassim, A.A., Winkler, S.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-08-2008; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Articulated 3-D human motion tracking; Biological system modeling; Cameras; Efficiency; Humans; Optimization methods; particle filter; Particle tracking; Robustness; Sampling methods; simulated physical force/moment; Stochastic processes; Studies; Surveillance; Target tracking; vector quantization principal component analysis (VQPCA); Articulated 3D human motion tracking; particle filter; simulated physical force/moment; vector quantization principal component analysis
• DOI: 10.1109/TCSVT.2008.927108
• EISSN: 1558-2205
• ISSN: 1051-8215

In this paper, we present a hybrid framework for articulated 3-D human motion tracking from multiple synchronized cameras with potential uses in surveillance systems. Although the recovery of 3-D motion provides richer information for event understanding, existing methods based on either deterministic search or stochastic sampling lack robustness or efficiency. We therefore propose a hybrid sample-and-refine framework that combines both stochastic sampling and deterministic optimization to achieve a good compromise between efficiency and robustness. Similar motion patterns are used to learn a compact low-dimensional representation of the motion statistics. Sampling in a low-dimensional space is implemented during tracking, which reduces the number of particles drastically. We also incorporate a local optimization method based on simulated physical force/moment into our framework, which further improves the optimality of the tracking. Experimental results on several real human motion sequences show the accuracy and robustness of our method, which also has a higher sampling efficiency than most particle filtering-based methods.