REAL-TIME 3D MULTIPLE HUMAN TRACKING WITH ROBUSTNESS ENHANCEMENT THROUGH MACHINE LEARNING

Suraj Nair, Emmanuel Dean-Leon, Alois Knoll

2012

Abstract

This paper presents a novel and robust vision-based real-time 3D multiple human tracking system. It is capable of automatically detecting and tracking multiple humans in real-time even when they occlude each other. Furthermore, it is robust towards drastically changing lighting conditions. The system consists of 2 parts, 1. a vision based human tracking system using multiple visual cues with a robust occlusion handling module, 2. a machine learning based module for intelligent multi-modal fusion and self adapting the system towards drastic light changes. The paper also proposes an approach to validate the system through zero-error ground truth data obtained by virtual environments. The system is also validated in real-world scenarios.

References

  1. Bhattacharyya, A. (1943). On a measure of divergence between two statistical populations defined by their probability distributions. Bulletin of the Calcutta Mathematical Society, 35:99-109.
  2. Cai, Q. and Aggarwal, J. (1996). Tracking human motion using multiple cameras. In Pattern Recognition, 1996., Proceedings of the 13th International Conference on, volume 3, pages 68-72. IEEE.
  3. Chang, T. and Gong, S. (2001). Tracking multiple people with a multi-camera system. womot, page 0019.
  4. Crammer, K. and Singer, Y. (2001). On the algorithmic implementation of multi-class svms. In JMLR.
  5. Dockstader, S. and Tekalp, A. (2001). Multiple camera tracking of interacting and occluded human motion. Proceedings of the IEEE, 89(10):1441-1455.
  6. Dollár, P., Wojek, C., Schiele, B., and Perona, P. (2009). Pedestrian detection: A benchmark. In CVPR.
  7. Eshel, R. and Moses, Y. (2008). Homography based multiple camera detection and tracking of people in a dense crowd. In CVPR 2008. IEEE.
  8. Fleuret, F., Berclaz, J., Lengagne, R., and Fua, P. (2008). Multicamera people tracking with a probabilistic occupancy map. pattern analysis and machine intelligence. IEEE Transactions on, 30(2):267-282.
  9. Focken, D. and Stiefelhagen, R. (2002). Towards visionbased 3-d people tracking in a smart room. In Multimodal Interfaces, 2002. IEEE Computer Society.
  10. Francois, J. B., Berclaz, J., Fleuret, F., and Fua, P. (2006). Robust people tracking with global trajectory optimization. In In Conference on Computer Vision and Pattern Recognition, pages 744-750.
  11. Hu, W., Hu, M., Zhou, X., Tan, T., Lou, J., and Maybank, S. (2006). Principal axis-based correspondence between multiple cameras for people tracking. pattern analysis and machine intelligence. IEEE Transactions on, 28(4):663-671.
  12. Isard, M. and Blake, A. (1998). Condensation - conditional density propagation for visual tracking. International Journal of Computer Vision (IJCV), 29(1):5-28.
  13. Khan, S. and Shah, M. (2008). Tracking multiple occluding people by localizing on multiple scene planes. IEEE transactions on pattern analysis and machine intelligence, pages 505-519.
  14. Kim, K. and Davis, L. (2006). Multi-camera tracking and segmentation of occluded people on ground plane using search-guided particle filtering. Computer VisionECCV 2006, pages 98-109.
  15. Roosendaal, T. and Selleri, S. (2004). The Official Blender 2.3 Guide: Free 3D Creation Suite for Modeling, Animation, and Rendering. No Starch Press.
  16. Santos, T. T. and Morimoto, C. H. (2011). Multiple camera people detection and tracking using support integration. Pattern Recognition Letters, 32(1):47-55.
  17. Soto, C., Song, B., and Roy-Chowdhury, A. (2009). Distributed multi-target tracking in a self-configuring camera network. In CVPR 2009. IEEE.
  18. Zhao, T., Aggarwal, M., Kumar, R., and Sawhney, H. (2005). Real-time wide area multi-camera stereo tracking. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society.
Download


Paper Citation


in Harvard Style

Nair S., Dean-Leon E. and Knoll A. (2012). REAL-TIME 3D MULTIPLE HUMAN TRACKING WITH ROBUSTNESS ENHANCEMENT THROUGH MACHINE LEARNING . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-04-4, pages 359-366. DOI: 10.5220/0003824203590366


in Bibtex Style

@conference{visapp12,
author={Suraj Nair and Emmanuel Dean-Leon and Alois Knoll},
title={REAL-TIME 3D MULTIPLE HUMAN TRACKING WITH ROBUSTNESS ENHANCEMENT THROUGH MACHINE LEARNING},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={359-366},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003824203590366},
isbn={978-989-8565-04-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2012)
TI - REAL-TIME 3D MULTIPLE HUMAN TRACKING WITH ROBUSTNESS ENHANCEMENT THROUGH MACHINE LEARNING
SN - 978-989-8565-04-4
AU - Nair S.
AU - Dean-Leon E.
AU - Knoll A.
PY - 2012
SP - 359
EP - 366
DO - 10.5220/0003824203590366