Advertisement

Surveillance Scene Segmentation Based on Trajectory Classification Using Supervised Learning

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 459)

Abstract

Scene understanding plays a vital role in the field of visual surveillance and security where we aim to classify surveillance scenes based on two important information, namely scene’s layout and activities or motions within the scene. In this paper, we propose a supervised learning-based novel algorithm to segment surveillance scenes with the help of high-level features extracted from object trajectories. High-level features are computed using a recently proposed nonoverlapping block-based representation of surveillance scene. We have trained Hidden Markov Model (HMM) to learn parameters describing the dynamics of a given surveillance scene. Experiments have been carried out using publicly available datasets and the outcomes suggest that, the proposed methodology can deliver encouraging results for correctly segmenting surveillance with the help of motion trajectories. We have compared the method with state-of-the-art techniques. It has been observed that, our proposed method outperforms baseline algorithms in various contexts such as localization of frequently accessed paths, marking abandoned or inaccessible locations, etc.

Keywords

Trajectory Surveillance HMM Supervised classification Scene segmentation RAG 

References

  1. 1.
    X. Wang, K. Tieu, and E. Grimson. Learning semantic scene models by trajectory analysis. In European Conference on Computer Vision, Proceedings of the, pages 110–123, 2006.Google Scholar
  2. 2.
    J. Melo, A. Naftel, A. Bernardino, and J. Santos-Victor. Detection and classification of highway lanes using vehicle motion trajectories. Intelligent Transportation Systems, IEEE Transactions on, 7(2):188–200, June 2006.CrossRefGoogle Scholar
  3. 3.
    C. Piciarelli and G. Foresti. On-line trajectory clustering for anomalous events detection. Pattern Recognition Letters, 27(15):1835–1842, 2006. Vision for Crime Detection and Prevention.Google Scholar
  4. 4.
    L. Brun, A. Saggese, and M. Vento. Dynamic scene understanding for behavior analysis based on string kernels. Circuits and Systems for Video Technology, IEEE Transactions on, 24(10):1669–1681, Oct 2014.CrossRefGoogle Scholar
  5. 5.
    G. Salvi. An automated nighttime vehicle counting and detection system for traffic surveillance. In International Conference on Computational Science and Computational Intelligence, Proceedings of the, 2014.Google Scholar
  6. 6.
    C. Piciarelli, C. Micheloni, and G. Foresti. Trajectory-based anomalous event detection. Circuits and Systems for Video Technology, IEEE Transactions on, 18(11):1544–1554, Nov 2008.CrossRefGoogle Scholar
  7. 7.
    N. Suzuki, K. Hirasawa, K. Tanaka, Y. Kobayashi, Y. Sato, and Y. Fujino. Learning motion patterns and anomaly detection by human trajectory analysis. In International Conference on Systems, Man and Cybernetics, Proceedings of the, pages 498–503, 2007.Google Scholar
  8. 8.
    D. Xu, X. Wu, D. Song, N. Li, and Y. Chen. Hierarchical activity discovery within spatio-temporal context for video anomaly detection. In International Conference on Image Processing, Proceedings of the, pages 3597–3601, 2013.Google Scholar
  9. 9.
    H. Fradi and J. Dugelay. Robust foreground segmentation using improved gaussian mixture model and optical flow. In International Conference on Informatics, Electronics and Vision, Proceedings of the, pages 248–253, 2012.Google Scholar
  10. 10.
    D. Dogra, R. Reddy, K. Subramanyam, A. Ahmed, and H. Bhaskar. Scene representation and anomalous activity detection using weighted region association graph. In 10th International Conference on Computer Vision Theory and Applications, Proceedings of the, pages 31–38, March 2015.Google Scholar
  11. 11.
    B. Morris and M. Trivedi. Learning and classification of trajectories in dynamic scenes: A general framework for live video analysis. In International Conference on Advanced Video and Signal Based Surveillance, Proceedings of the, pages 154–161, 2008.Google Scholar
  12. 12.
    D. Dogra, A. Ahmed, and H. Bhaskar. Interest area localization using trajectory analysis in surveillance scenes. In 10th International Conference on Computer Vision Theory and Applications, Proceedings of the, pages 31–38, March 2015.Google Scholar
  13. 13.
    D. Dogra, A. Ahmed, and H. Bhaskar. Smart video summarization using mealy machine-based trajectory modelling for surveillance applications. Multimedia Tools and Applications, pages 1–29, 2015.Google Scholar
  14. 14.
    Y. Sugaya and K. Kanatani. Outlier removal for motion tracking by subspace separation. IEICE Trans. Inf. and Syst, 86:1095–1102, 2003.Google Scholar
  15. 15.
    T. Dinh, N. Vo, and G. Medioni. Context tracker: Exploring supporters and distracters in unconstrained environments. In Computer Vision and Pattern Recognition, Proceedings of the IEEE Computer Society Conference on, pages 1177–1184, 2011.Google Scholar
  16. 16.
    W. Xiaogang, T. Keng, N. Gee-Wah, and W. Grimson. Trajectory analysis and semantic region modeling using a nonparametric bayesian model. In Computer Vision and Pattern Recognition, Proceedings of the IEEE Computer Society Conference on, pages 1–8, June 2008.Google Scholar
  17. 17.
    Visor dataset. http://www.openvisor.org
  18. 18.

Copyright information

© Springer Science+Business Media Singapore 2017

Authors and Affiliations

  1. 1.IIT RoorkeeRoorkeeIndia
  2. 2.Haldia Institute of TechnologyHaldiaIndia
  3. 3.IIT BhubaneswarBhubaneswarIndia

Personalised recommendations