Particle Filter with Constraints for Articulated Upper Body Tracking

Abstract:

For sophisticated background, a human body tracking algorithm using particle filter based on a 3D articulated body model is introduced. First, a high-fidelity biomechanical upper body model, which is accurate for representing varies complicated human poses and simple to be developed, has been built. Then sequences of images are obtained by using a stereo camera. After calibration, verification and background subtraction, depth map, foreground silhouette, arms skeleton are chosen to construct the likelihood function. The state vectors describing the human pose are computed by fitting the articulated body model to observed person using particle filter. In order to reduce the computational complexity and the number of particles, constraints are employed to restrict the state parameters. Experimental results show that the proposed algorithm can track human upper body with different poses, different person under different illumination conditions fast and accurately.

• Periodical: Key Engineering Materials (Volumes 439-440)
• Pages: 971-976
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.439-440.971
• Online since: June 2010
• Authors: Qiong Liu, Guang Zheng Peng
• Keywords: Articulated Body Model, Computer Vision, Human Body Tracking, Human Modeling, Human Motion Capture, Human-Computer Interaction (HCI)

References

[1] Rohr K. Human movement analysis based on explicit motion models. Motion-Based Recognition. Kluwer Academic Publishers, Dordrecht Boston, 1997: 171-198.

DOI: 10.1007/978-94-015-8935-2_8

[2] Niyogi S, Adelson E. Analyzing and recognizing walking figures in xyt. Proc. of IEEE Conference on Computer Vision and Pattern Recognition, 1994: 469-474.

DOI: 10.1109/cvpr.1994.323868

[3] Gordon N, Salmond D, Smith M, Novel approach to nonlinear/non-Gaussian Bayesian state estimation, Proc. Inst. Elect. Eng. F, v140, n2, (1993).

[4] Isard M , Blake A. Visual tracking by stochastic propagation of conditional density, ECCV 1996: 343-356.

[5] Sanjeev M, Maskell S. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking, IEEE Trans. Signal Processing, vol. 50, No. 2, Feb 2002: 174-188.

DOI: 10.1109/78.978374

[6] Deutscher J, Blake A, North B. Tracking through singularities and discontinuities by random sampling, ICCV 1999, vol. 2: 1144-1149.

[7] M. Sanjeev Arulampalam, S. Maskell, N. Gordon, T. Clapp, A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking, IEEE Trans. Signal Processing, vol. 50, No. 2, Feb 2002, 174-188.

DOI: 10.1109/78.978374

[8] Isard M , Blake A. Visual tracking by stochastic propagation of conditional density, ECCV 1996: 343-356.

[9] Isard M, Blake A. CONDENSATION-conditional density propagation for visual tracking, International Journal of Computer Vision, 1998, vol. 29: 5-28.