A novel fitting algorithm using the ICP and the particle filters for robust 3d human body motion tracking

ABSTRACT

This paper proposes a novel fitting algorithm using the iterative closest point (ICP) registration algorithm and the particle filters for robust 3D human body motion tracking. We use the ICP registration algorithm that fits the 3D human body model to the 3D articulation data in a hierarchical manner. However, it often can not fit under the rapidly moving human body motion. To solve this problem, we combine the modified particle filter with the ICP algorithm. It can search the most appropriate motion parameters by using the observation model based on the surface normal vector and the binary valued function and the state transitional model based on the motion history information. Experimental results show that the proposed combined fitting algorithm provides accurate fitting performance and high convergence rate.

REFERENCES

• 1: Paul J. Besl , Neil D. McKay, A Method for Registration of 3-D Shapes, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.14 n.2, p.239-256, February 1992 [doi>10.1109/34.121791]
• 2: C. Bregler , J. Malik, Tracking People with Twists and Exponential Maps, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p.8, June 23-25, 1998
• 3: Yang Chen , Gérard Medioni, Object modelling by registration of multiple range images, Image and Vision Computing, v.10 n.3, p.145-155, April 1992 [doi>10.1016/0262-8856(92)90066-C]
• 4: Quentin Delamarre , Olivier Faugeras, 3D Articulated Models and Multi-View Tracking with Silhouettes, Proceedings of the International Conference on Computer Vision-Volume 2, p.716, September 20-25, 1999
• 5: D. Demirdjian. Enforcing constraints for human body tracking. In Workshop on Multiple Object Tracking pages 102--1093, 2003.
• 6: J. Deutscher, A. Davision, and I. Reid. Articulated body motion capture by annealed particle filtering. In Proc. of Computer Vision and Pattern Recognition pages 126--133, 2000.
• 7: Arnaud Doucet , Simon Godsill , Christophe Andrieu, On sequential Monte Carlo sampling methods for Bayesian filtering, Statistics and Computing, v.10 n.3, p.197-208, July 2000 [doi>10.1023/A:1008935410038]
• 8: W. Liang, H. Weiming, and T. Tieniu. Recent developments in human motion analysis. Pattern Recognition 36(3):585--601, 2003.
• 9: Thomas B. Moeslund , Adrian Hilton , Volker Krüger, A survey of advances in vision-based human motion capture and analysis, Computer Vision and Image Understanding, v.104 n.2, p.90-126, November 2006 [doi>10.1016/j.cviu.2006.08.002]
• 10: Olaf Munkelt , Christof Ridder , David Hansel , Walter Hafner, A Model Driven 3D Image Interpretation System Applied to Person Detection in Video Images, Proceedings of the 14th International Conference on Pattern Recognition-Volume 1, p.70, August 16-20, 1998
• 11: K. Okuma, A. Taleghani, N. Freitas, J. Little, and D. Lowe. A boosted particle filter: multitarget detection and tracking. In Proc. of European Conference on Computer Vision pages 28--39, 2004.
• 12: K. Rohr, Towards model-based recognition of human movements in image sequences, CVGIP: Image Understanding, v.59 n.1, p.94-115, Jan. 1994 [doi>10.1006/ciun.1994.1006]
• 13: S. Rusinkiewicz and M. Levoy. Efficient variants of the ICP algorithm. In Proc. of International Conference on 3D Digital Imaging and Modeling pages 145--152, 2001.
• 14: Hedvig Sidenbladh , Michael J. Black , David J. Fleet, Stochastic Tracking of 3D Human Figures Using 2D Image Motion, Proceedings of the 6th European Conference on Computer Vision-Part II, p.702-718, June 26-July 01, 2000

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: Motion

General Terms:
Algorithms, Experimentation, Performance

Keywords:
human body motion tracking, icp, particle filter