Skip to main content
SpringerLink
Log in

Multiple feature set with feature selection for anomaly search in videos using hybrid classification

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

An examination of abnormal activities in video scenes is a very difficult task in computer vision community. An efficient anomaly detection technique to detect anomalies in crowded scenes is presented in this paper. It uses Multiple Feature Set (MFS) to represent a piece of rectangular region of predefined size in a video frame called as patch with Hybrid Classification (HC) using Gaussian Mixture Model (GMM) and Support Vector Machine (SVM) classifiers for anomaly detection. The MFS contains a combination of the following types of features; gray intensity values, gradient edge features and texture energy map. The predominant features are selected from MFS by using a model of t-test feature selection method and are classified by HC model made up of GMM and SVM classifiers. The UCSD video clip database is used for performance analysis of MFS-HC system and compared with other approaches. Results show that MFS-HC provides better results than other approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Adam A, Rivlin E, Shimshoni I, Reinitz D (2008) Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans Pattern Anal Mach Intell 30(3):555–560

    Article  Google Scholar 

  2. Benabbas Y, Ihaddadene N, Djeraba C (2011) Motion pattern extraction and event detection for automatic visual surveillance. EURASIP Journal on Image and Video Processing 1:1–15

    Article  Google Scholar 

  3. Bishop CM (2006) Pattern recognition and machine learning, Springer, chapter 9, vol. 1, pp. 435

  4. Erasto P (2001) Support Vector Machines - Backgrounds and Practice, Academic Dissertation for the Degree of Licentiate of Philosophy, Rolf Nevanlinna Institute

  5. Javan Roshtkhari M, Levine MD (2013) Online dominant and anomalous behavior detection in videos, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2611–2618

  6. Kim J, Grauman K (2008) Observe locally, infer globally: a space-time MRF for detecting abnormal activities with incremental updates, IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2928

  7. Laws KI (1980) Rapid texture identification. International Society for Optics and Photonics In Image processing for missile guidance 238:376–382

    Article  Google Scholar 

  8. Leyva R, Sanchez V, Li CT (2014) Video anomaly detection based on wake motion descriptors and perspective grids, IEEE International Workshop on Information Forensics and Security, pp. 209–214

  9. Mahadevan V, Li W, Bhalodia V, Vasconcelos N (2009) Anomaly detection in crowded scenes, IEEE Conference on Computer Vision and Pattern Recognition, pp. 1975–1981

  10. Mahadevan V, Li W, Bhalodia V, Vasconcelos N (2010) Anomaly detection in crowded scenes, IEEE Conference on Computer Vision and Pattern Recognition, pp. 1975–1981

  11. Mehran R, Oyama A, Shah M (2009) Abnormal crowd behavior detection using social force model, IEEE Conference on Computer Vision and Pattern Recognition, pp. 935–942

  12. Mo X, Monga V, Baia R, Fan Z, Burry A (2014) Low rank sparsity prior for robust video anomaly detection, IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1285–1289

  13. Saligrama V, Chen Z (2012) Video anomaly detection based on local statistical aggregates, IEEE Conference on Computer Vision and Pattern Recognition, pp. 2112–2119

  14. Shreedarshan K, Selvi SS (2016) An Adaptive swarm optimization technique for anomaly detection in crowded scene, IEEE International Conference on Circuits, Controls, Communications and Computing, pp. 4–6

  15. Stauffer C, Grimson W (2000) Learning patterns of activity using real-time tracking. IEEE Trans Pattern Anal Mach Intell 22(8):747–758

    Article  Google Scholar 

  16. Thida M, Eng HL, Remagnino P (2013) Laplacian eigenmap with temporal constraints for local abnormality detection in crowded scenes. IEEE Transactions on Cybernetics 43(6):2147–2156

    Article  Google Scholar 

  17. UCSD database: http://www.svcl.ucsd.edu/projects/anomaly/

  18. Wei Z, Xuena W, Yeming M, Manlong R, James G, John SK (2003) Detection of cancer-specific markers amid massive mass spectral data. Proc Natl Acad Sci 100(25):4666–14671

    MathSciNet  MATH  Google Scholar 

  19. Xiao T, Zhang C, Zha H, Wei F. (2014) Anomaly detection via local coordinate factorization and spatio-temporal pyramid, In Asian Conference on Computer Vision, pp. 66–82, Springer, Cham

    Google Scholar 

  20. Yuan Y, Fang J, Wang Q (2015) Online anomaly detection in crowd scenes via structure analysis. IEEE transactions on cybernetics 45(3):548–561

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Misrimal Navajee Munoth Jain Engineering College, Anna University, Chennai, Tamilnadu, India

    A. Srinivasan & V. K. Gnanavel

Authors
  1. A. Srinivasan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. V. K. Gnanavel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to A. Srinivasan.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Srinivasan, A., Gnanavel, V.K. Multiple feature set with feature selection for anomaly search in videos using hybrid classification. Multimed Tools Appl 78, 7713–7725 (2019). https://doi.org/10.1007/s11042-018-6348-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6348-z

Keywords

Search

Navigation