Ghost Pruning for People Localization in Overlapping Multicamera Systems

Muhammad Owais Mehmood, Sebastien Ambellouis, Catherine Achard

Abstract

In this paper, we propose a novel ghost pruning technique for multicamera people localization in overlapping scenarios. First, synergy map is obtained from multiplanar projections across multiple overlapping cameras. Second, occupancy map is generated by back projection from the synergy map across various image layers. This back projected occupancy map is combined with constraints to remove ghosts. The novelty of this paper is the introduction of an intuitive ghost pruning technique, which does not require any temporal information. Experiments on a sequence of the PETS 2009 dataset show significant reduction in the number of ghosts. The purpose and novelty of this paper is focused to the ghost pruning module but detection metrics show results comparable to those of the complete, state-of-the-art multicamera object detection systems.

References

  1. Dollar, P., Wojek, C., Schiele, B., and Perona, P. (2012). Pedestrian detection: An evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell., 34(4):743-761.
  2. Eshel, R. and Moses, Y. (2010). Tracking in a dense crowd using multiple cameras. Int. J. Comput. Vision, 88(1):129-143.
  3. Evans, M., Li, L., and Ferryman, J. M. (2012). Suppression of detection ghosts in homography based pedestrian detection. In AVSS, pages 31-36. IEEE Computer Society.
  4. Khan, S. and Shah, M. (2009). Tracking multiple occluding people by localizing on multiple scene planes. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 31(3):505-519.
  5. PETS (2009). Pets dataset: Performance evaluation of tracking and surveillance. http://www.cvg.rdg.ac.uk/ PETS2009/a.html. [Online].
  6. Ren, J., Xu, M., and Smith, J. S. (2012). Pruning phantom detections from multiview foreground intersection. In ICIP, pages 1025-1028.
  7. . and Benedek, C. (2012). A bayesian approach on people localization in multi-camera systems. IEEE Transactions on Circuits and Systems for Video Technology.
  8. Yao, J. and Odobez, J. (2007). Multi-layer background subtraction based on color and texture. In IEEE Conference on Computer Vision and Pattern Recognition, 2007. CVPR'07, pages 1-8.
  9. Yilmaz, A., Javed, O., and Shah, M. (2006). Object tracking: A survey. ACM Comput. Surv., 38(4).
Download


Paper Citation


in Harvard Style

Mehmood M., Ambellouis S. and Achard C. (2014). Ghost Pruning for People Localization in Overlapping Multicamera Systems . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 632-639. DOI: 10.5220/0004741306320639


in Bibtex Style

@conference{visapp14,
author={Muhammad Owais Mehmood and Sebastien Ambellouis and Catherine Achard},
title={Ghost Pruning for People Localization in Overlapping Multicamera Systems},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={632-639},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004741306320639},
isbn={978-989-758-004-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Ghost Pruning for People Localization in Overlapping Multicamera Systems
SN - 978-989-758-004-8
AU - Mehmood M.
AU - Ambellouis S.
AU - Achard C.
PY - 2014
SP - 632
EP - 639
DO - 10.5220/0004741306320639