Advertisement

A Discriminative Framework for Anomaly Detection in Large Videos

  • Allison Del GiornoEmail author
  • J. Andrew Bagnell
  • Martial Hebert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9909)

Abstract

We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach of learning high-dimensional models and finding low-probability events. These algorithms are sensitive to the order in which anomalies appear and require either training data or early context assumptions that do not hold for longer, more complex videos. By defining anomalies as examples that can be distinguished from other examples in the same video, our definition inspires a shift in approaches from classical density estimation to simple discriminative learning. Our contributions include a novel framework for anomaly detection that is (1) independent of temporal ordering of anomalies, and (2) unsupervised, requiring no separate training sequences. We show that our algorithm can achieve state-of-the-art results even when we adjust the setting by removing training sequences from standard datasets.

Keywords

Anomaly detection Discriminative Unsupervised Context Surveillance Temporal invariance 

Notes

Acknowledgements

This research was supported through the DoD National Defense Science & Engineering Graduate Fellowship (NDSEG) Program and NSF grant IIS1227495.

Supplementary material

419978_1_En_21_MOESM1_ESM.avi (66.5 mb)
Supplementary material 1 (avi 68145 KB)
419978_1_En_21_MOESM2_ESM.avi (51.9 mb)
Supplementary material 2 (avi 53179 KB)
419978_1_En_21_MOESM3_ESM.avi (60.4 mb)
Supplementary material 3 (avi 61843 KB)
419978_1_En_21_MOESM4_ESM.pdf (12 kb)
Supplementary material 4 (pdf 11 KB)
419978_1_En_21_MOESM5_ESM.pdf (8 kb)
Supplementary material 5 (pdf 8 KB)
419978_1_En_21_MOESM6_ESM.png (6 kb)
Supplementary material 6 (png 6 KB)
419978_1_En_21_MOESM7_ESM.pdf (570 kb)
Supplementary material 7 (pdf 569 KB)

References

  1. 1.
    Zhao, B., Fei-Fei, L., Xing, E.: Online detection of unusual events in videos via dynamic sparse coding. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3313–3320, June 2011Google Scholar
  2. 2.
    Lu, C., Shi, J., Jia, J.: Abnormal event detection at 150 fps in matlab. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 2720–2727. IEEE (2013)Google Scholar
  3. 3.
    Mahadevan, V., Li, W., Bhalodia, V., Vasconcelos, N.: Anomaly detection in crowded scenes. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1975–1981. IEEE (2010)Google Scholar
  4. 4.
    Kim, J., Grauman, K.: Observe locally, infer globally: a space-time MRF for detecting abnormal activities with incremental updates. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009, CVPR 2009, pp. 2921–2928. IEEE (2009)Google Scholar
  5. 5.
    Li, W., Mahadevan, V., Vasconcelos, N.: Anomaly detection and localization in crowded scenes. IEEE Trans. Pattern Anal. Mach. Intell. 36(1), 18–32 (2014)CrossRefGoogle Scholar
  6. 6.
    Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009, CVPR 2009, pp. 935–942. IEEE (2009)Google Scholar
  7. 7.
    Antić, B., Ommer, B.: Video parsing for abnormality detection. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2415–2422. IEEE (2011)Google Scholar
  8. 8.
    Roshtkhari, M., Levine, M.: Online dominant and anomalous behavior detection in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2611–2618 (2013)Google Scholar
  9. 9.
    Calderara, S., Heinemann, U., Prati, A., Cucchiara, R., Tishby, N.: Detecting anomalies in peoples trajectories using spectral graph analysis. Comput. Vis. Image Underst. 115(8), 1099–1111 (2011)CrossRefGoogle Scholar
  10. 10.
    Liu, S., Yamada, M., Collier, N., Sugiyama, M.: Change-point detection in time-series data by relative density-ratio estimation. Neural Netw. 43, 72–83 (2013)CrossRefzbMATHGoogle Scholar
  11. 11.
    Ito, Y., Kitani, K.M., Bagnell, J.A., Hebert, M.: Detecting interesting events using unsupervised density ratio estimation. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7585, pp. 151–161. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-33885-4_16 Google Scholar
  12. 12.
    Kawahara, Y., Sugiyama, M.: Change-point detection in time-series data by direct density-ratio estimation. In: SDM, vol. 9, pp. 389–400. SIAM (2009)Google Scholar
  13. 13.
    Sugiyama, M., Suzuki, T., Kanamori, T.: Density ratio estimation: a comprehensive review. RIMS Kokyuroku, pp. 10–31 (2010)Google Scholar
  14. 14.
    Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Action recognition by dense trajectories. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3169–3176. IEEE (2011)Google Scholar
  15. 15.
    Motwani, R., Raghavan, P.: Randomized algorithms. Chapman & Hall/CRC (2010)Google Scholar
  16. 16.
    Kakade, S.: Hoeffding, Chernoff, Bennet, and Bernstein Bounds. http://stat.wharton.upenn.edu/ skakade/courses/stat928/lectures/lecture06.pdf
  17. 17.
    Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1–2), 151–175 (2010)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Bartlett, P.L., Mendelson, S.: Rademacher and gaussian complexities: risk bounds and structural results. J. Mach. Learn. Res. 3, 463–482 (2003)MathSciNetzbMATHGoogle Scholar
  19. 19.
    Balcan, M.F.: Rademacher complexity. http://www.cs.cmu.edu/ ninamf/ML11/lect1117.pdf
  20. 20.
    Borenstein, M., Hedges, L.V., Higgins, J., Rothstein, H.R.: A basic introduction to fixed-effect and random-effects models for meta-analysis. Res. Synth. Methods 1(2), 97–111 (2010)CrossRefGoogle Scholar
  21. 21.
    Adam, A., Rivlin, E., Shimshoni, I., Reinitz, D.: Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans. Pattern Anal. Mach. Intell. 30(3), 555–560 (2008)CrossRefGoogle Scholar
  22. 22.
    Minnesota, U.: Crowd activity dataset. http://mha.cs.umn.edu/proj_events.shtml
  23. 23.
    Andrei Zaharescu, R.P.W.: Anomalous behavior data set. http://vision.eecs.yorku.ca/research/anomalous-behaviour-data/. Accessed 01 March 2016

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Allison Del Giorno
    • 1
    Email author
  • J. Andrew Bagnell
    • 1
  • Martial Hebert
    • 1
  1. 1.Carnegie Mellon UniversityPittsburghUSA

Personalised recommendations