Human Pose Tracking For Video Using SURF features

Abstract:

In this paper, a novel method based on SURF features method for tracking human motion in monocular videos is proposed. With a initial human skeleton joint point template, we use the probability density propagation of the particle filers through the model. This algorithm can automatically achieve right human motion figure from tracking failures, such as occlusion and auto-occlusion problem. Experimental results from 20 classes monocular videos show that the new Based on SURF method is robust and the tracking results are good.

• Periodical: Applied Mechanics and Materials (Volume 39)
• Pages: 203-209
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.39.203
• Online since: November 2010
• Authors: Ou Yang Yi
• Keywords: Human Motion, Monocular Video, SURF, Video Tracking

References

[1] H. Bay, T. Tuytelaars, and L. Van Gool. Surf: Speeded up robust features. European Conference on Computer Vision, 1: 404–417, (2006).

DOI: 10.1007/11744023_32

[2] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE, vol. 86, p.2278–2324, November (1998).

DOI: 10.1109/5.726791

[3] C. K. Liu, A. Hertzmann, and Z. Popovic, Learning physics-based motion style with nonlinear inverse optimization, ACM Trans. Graph., vol. 24, no. 3, p.1071–1081, (2005).

DOI: 10.1145/1073204.1073314

[4] O. Arikan, D. A. Forsyth, and J. F. O'Brien, Motion synthesis from annotations, in Proc. SIGGRAPH, (2002).

[5] M. Brand and A. Hertzmann, Style machines., in Proc. SIGGRAPH, p.183–192, (2000).

[6] R. Urtasun, P. Glardon, R. Boulic, D. Thalmann, and P. Fua, Style-based Motion Synthesis, Computer Graphics Forum, vol. 23, no. 4, p.1–14, (2004).

DOI: 10.1111/j.1467-8659.2004.00809.x

[7] Pavlovic V，Rehg J M ，Chain T J，el al, A dynamic Bayesian network approach to figure tracking using learned dynamic models, Proceedings of the 7th Internalional Conference on Conaputer Vision，Corfu, 1999．94~101.

DOI: 10.1109/iccv.1999.791203

[8] Howe N R, Leventon M E，Freeman W T． Bayesian reconstruction of 3D hunmn motion from single camera video, Advances in Neural lnfornmtion Processing Systems, Cambridge, Massachusetts: MIT Press, 2000，12：820~826.

[9] Sidenbtadh H，Black M J, Fleet D J．Stochastic tracking of 3D human figures using 2D image motion, Proceedings of the 6th European Conference on Computer Vision, Dublin, 2000, 702~7I8.

DOI: 10.1007/3-540-45053-x_45

[10] Zhao T, Wang T S, Shum H Y． Learning a highly struetured motion for 3D human tracking, Proceedings of the 5th Asian Conference on Computer Vision, Melbourne，2002, 144~149.

[11] Chain T J，Rehg J M．A multiple hypothesis approach to figure tracking, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, I999, 239~245.

[12] Ramanan, D., Forsyth, D. A., and Zisserman, A. Strike a Pose: Tracking People by Finding Stylized Poses., Computer Vision and Pattern Recognition (CVPR), San Diego, CA, June (2005).

DOI: 10.1109/cvpr.2005.335