Towards Unsupervised Sudden Group Movement Discovery for Video Surveillance

Sofia Zaidenberg, Piotr Bilinski, François Brémond

2014

Abstract

This paper presents a novel and unsupervised approach for discovering “sudden” movements in video surveillance videos. The proposed approach automatically detects quick motions in a video, corresponding to any action. A set of possible actions is not required and the proposed method successfully detects potentially alarm-raising actions without training or camera calibration. Moreover, the system uses a group detection and event recognition framework to relate detected sudden movements and groups of people, and provide a semantical interpretation of the scene. We have tested our approach on a dataset of nearly 8 hours of videos recorded from two cameras in the Parisian subway for a European Project. For evaluation, we annotated 1 hour of sequences containing 50 sudden movements.

References

  1. Belshaw, M., Taati, B., Snoek, J., and Mihailidis, A. (2011). Towards a single sensor passive solution for automated fall detection. In IEEE Engineering in Medicine and Biology Society, pages 1773-1776.
  2. Blank, M., Gorelick, L., Shechtman, E., Irani, M., and Basri, R. (2005). Actions as space-time shapes. In ICCV, volume 2, pages 1395-1402.
  3. Brox, T. and Malik, J. (2011). Large displacement optical flow: Descriptor matching in variational motion estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3):500-513.
  4. Castrodad, A. and Sapiro, G. (2012). Sparse modeling of human actions from motion imagery. International Journal of Computer Vision, 100(1):1-15.
  5. Daniyal, F. and Cavallaro, A. (2011). Abnormal motion detection in crowded scenes using local spatio-temporal analysis. In Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pages 1944-1947.
  6. Efros, A., Berg, A., Mori, G., and Malik, J. (2003). Recognizing action at a distance. In ICCV, pages 726-733 vol.2.
  7. Emonet, R., Varadarajan, J., and Odobez, J.-M. (2011). Multi-camera open space human activity discovery for anomaly detection. In AVSS.
  8. Farnebäck, G. (2003). Two-frame motion estimation based on polynomial expansion. In Scandinavian Conference on Image Analysis, LNCS 2749, pages 363-370.
  9. Gaidon, A., Harchaoui, Z., and Schmid, C. (2011). A time series kernel for action recognition. In BMVC.
  10. Jouneau, E. and Carincotte, C. (2011). Particle-based tracking model for automatic anomaly detection. In ICIP, pages 513-516.
  11. Kellokumpu, V., Zhao, G., and Pietikinen, M. (2008). Human activity recognition using a dynamic texture based method. In BMVC.
  12. Mahadevan, V., Li, W., Bhalodia, V., and Vasconcelos, N. (2010). Anomaly detection in crowded scenes. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 1975-1981.
  13. Raptis, M. and Soatto, S. (2010). Tracklet descriptors for action modeling and video analysis. In ECCV.
  14. Wang, H., Kläser, A., Schmid, C., and Cheng-Lin, L. (2011). Action Recognition by Dense Trajectories. In CVPR, pages 3169-3176, Colorado Springs, United States.
  15. Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., and Bischof, H. (2009). Anisotropic Huber-L1 Optical Flow. BMVC, pages 108.1-108.11.
  16. Wu, S., Oreifej, O., and Shah, M. (2011). Action recognition in videos acquired by a moving camera using motion decomposition of lagrangian particle trajectories. In ICCV.
  17. Xiang, T. and Gong, S. (2005). Video behaviour profiling and abnormality detection without manual labelling. In Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on, volume 2, pages 1238- 1245 Vol. 2.
  18. Xiang, T. and Gong, S. (2008). Activity based surveillance video content modelling. Pattern Recognition, 41(7):2309 - 2326.
  19. Zaidenberg, S., Boulay, B., and Bremond, F. (2012). A generic framework for video understanding applied to group behavior recognition. In 9th IEEE International Conference on Advanced Video and SignalBased Surveillance (AVSS 2012), Advanced Video and Signal Based Surveillance, IEEE Conference on, pages 136 -142, Beijing, Chine. IEEE Computer Society, IEEE Computer Society.
Download


Paper Citation


in Harvard Style

Zaidenberg S., Bilinski P. and Brémond F. (2014). Towards Unsupervised Sudden Group Movement Discovery for Video Surveillance . 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 388-395. DOI: 10.5220/0004682403880395


in Bibtex Style

@conference{visapp14,
author={Sofia Zaidenberg and Piotr Bilinski and François Brémond},
title={Towards Unsupervised Sudden Group Movement Discovery for Video Surveillance},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={388-395},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004682403880395},
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 - Towards Unsupervised Sudden Group Movement Discovery for Video Surveillance
SN - 978-989-758-004-8
AU - Zaidenberg S.
AU - Bilinski P.
AU - Brémond F.
PY - 2014
SP - 388
EP - 395
DO - 10.5220/0004682403880395