SCIENCE CHINA Information Sciences, Volume 63 , Issue 5 : 154101(2020) https://doi.org/10.1007/s11432-018-9792-8

Anomaly detection by exploiting the tracking trajectory in surveillance videos

More info
  • ReceivedSep 18, 2018
  • AcceptedFeb 15, 2019
  • PublishedFeb 25, 2020


There is no abstract available for this article.


This work was supported by National Natural Science Foundation of China (Grant Nos. 61872024, 61472020).


Videos and other supplemental documents.


[1] Zhou S, Shen W, Zeng D. Spatial-temporal convolutional neural networks for anomaly detection and localization in crowded scenes. Signal Process Image Commun, 2016, 47: 358-368 CrossRef Google Scholar

[2] Kaltsa V, Briassouli A, Kompatsiaris I. Swarm Intelligence for Detecting Interesting Events in Crowded Environments. IEEE Trans Image Process, 2015, 24: 2153-2166 CrossRef PubMed ADS Google Scholar

[3] Mehran R, Oyama A, et al. Abnormal crowd behavior detection using social force model. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, 2009. 935--942. Google Scholar

[4] Adler A, Elad M, Hel-Or Y. Sparse Coding with Anomaly Detection. J Sign Process Syst, 2015, 79: 179-188 CrossRef Google Scholar

[5] Bae S, Yoon K. Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Boston, 2014. 1218--1225. Google Scholar

[6] Multiple object tracking benchmark. https://motchallenge.net/results/2D_MOT_2015/. Google Scholar

  • Figure 1

    (Color online) (a) Results of the application of proposed method to the UCSD Ped1, UMN, and PKU-SVD-B datasets; (b) anomaly detection using the PKU-SVD-B dataset; (c) comparative results of the tracking trajectory with respect to the 2D MOT 2015 benchmark; (d) the process of double fusion method. A and B represent different video sequences.