DETECTING AND TRACKING PEOPLE IN MOTION - A Hybrid Approach Combining 3D Reconstruction and 2D Description

Peter Holzer, Chunming Li, Axel Pinz

2011

Abstract

We analyze the most difficult case of visual surveillance, when people in motion are observed by a moving camera. Our solution to this problem is a hybrid system that combines the online 3D reconstruction of stationary background structure, camera trajectory, and moving foreground objects with more established techniques in the 2D domain. Once this 3D part has succeeded in focusing the attention on a particular, moving foreground object, we continue in the 2D image domain using a state-of-the art shape-based person detector, and meanshift-based object tracking. Our results show various benefits of this hybrid approach beyond improved detection rate and reduced false alarms. In particular, each individual algorithmic component can benefit from the results of the other components, by gathering a richer foreground description, improved self-diagnosis capabilities, and by an explicit use of the available 3D information.

References

  1. Comaniciu, D. and Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. PAMI, 24:603-619.
  2. Comaniciu, D., Ramesh, V., and Meer, P. (2003). Kernelbased object tracking. PAMI, 25:564-577.
  3. Costeira, J. and Kanade, T. (1995). A multi-body factorization method for motion analysis. In ICCV, pages 1071-1076.
  4. Costeira, J. P. and Kanade, T. (1998). A multibody factorization method for independently moving objects. IJCV, 29:159-179.
  5. Dalal, N. and Triggs, B. (2005). Histogram of oriented gradients for human detection. In CVPR.
  6. Dalal, N., Triggs, B., and Schmid, C. (2006). Human detection using oriented histograms of flow and appearance. In ECCV.
  7. Ess, A., Leibe, B., Schindler, K., and van Gool, L. (2008). A mobile vision system for robust multi-person tracking. In CVPR.
  8. Felzenszwalb, P. F., McAllester, D., and Ramanan, D. (2008). A discriminatively trained, mulitscale, deformable part model. In CVPR.
  9. Fitzgibbon, A. W. and Zisserman, A. (2000). Multibody structure and motion: 3-d reconstruction of indepenently moving objects. In ECCV.
  10. Holzer, P. and Pinz, A. (2010). Mobile surveillance by 3doutlier analysis. In ACCV Visual Surveillance Workshop.
  11. Hu, W., Tan, T., Wang, L., and Maybank, S. (2004). A survey on visual surveillance of object motion and behaviors. Trans. on Systems, Man, and Cybernetics, 34:334-352.
  12. Leibe, B., Schindler, K., Cornelis, N., and Gool, L. V. (2008). Coupled object detection and tracking from static cameras and moving vehicles. PAMI, 30:1683- 1698.
  13. Li, T., Kallem, V., Singaraju, D., and Vidal, R. (2007). Projective factorization of multiple rigid-body motions. In CVPR.
  14. Lin, Z. and Davis, L. S. (2010). Shape-based human detection and segmentation via hierarchical part-template matching. In PAMI.
  15. Lopez, D. M., Sappa, A. D., and Graf, T. (2010). Survey of pedestrian detection for advanced driver assistance systems. PAMI, 32:1239-1258.
  16. Ozden, K., Schindler, K., and Gool, L. V. (2010). Multibody structure-from-motion in practice. PAMI, 32:1134- 1141.
  17. Schindler, K., Suter, D., and Wang, H. (2008). A model-selection framework for multibody structureand-motion of image sequences. IJCV, 79:159-177.
  18. Song, Y., Feng, X., and Perona, P. (2000). Towards detection of human motion. In CVPR.
  19. Yan, J. and Pollefeys, M. (2006). A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate. In ECCV, pages 94-106.
  20. Yan, J. and Pollefeys, M. (2008). A factorization based approach for articulated nonrigid shape, motion, and kinematic chain recovery from video. PAMI, 30:865- 887.
Download


Paper Citation


in Harvard Style

Holzer P., Li C. and Pinz A. (2011). DETECTING AND TRACKING PEOPLE IN MOTION - A Hybrid Approach Combining 3D Reconstruction and 2D Description . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011) ISBN 978-989-8425-47-8, pages 561-568. DOI: 10.5220/0003317005610568


in Bibtex Style

@conference{visapp11,
author={Peter Holzer and Chunming Li and Axel Pinz},
title={DETECTING AND TRACKING PEOPLE IN MOTION - A Hybrid Approach Combining 3D Reconstruction and 2D Description},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)},
year={2011},
pages={561-568},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003317005610568},
isbn={978-989-8425-47-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)
TI - DETECTING AND TRACKING PEOPLE IN MOTION - A Hybrid Approach Combining 3D Reconstruction and 2D Description
SN - 978-989-8425-47-8
AU - Holzer P.
AU - Li C.
AU - Pinz A.
PY - 2011
SP - 561
EP - 568
DO - 10.5220/0003317005610568