CoChat

Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks

Luo, Weixin, Liu, Wen, Lian, Dongze, Tang, Jinhui, Duan, Lixin, Peng, Xi, Gao, Shenghua · 2021 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Cited by 243

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Abstract

This paper presents an anomaly detection method that is based on a sparse coding inspired Deep Neural Networks (DNN). Specifically, in light of the success of sparse coding based anomaly detection, we propose a Temporally-coherent Sparse Coding (TSC), where a temporally-coherent term is used to preserve the similarity between two similar frames. The optimization of sparse coefficients in TSC with the Sequential Iterative Soft-Thresholding Algorithm (SIATA) is equivalent to a special stacked Recurrent Neural Networks (sRNN) architecture. Further, to reduce the computational cost in alternatively updating the dictionary and sparse coefficients in TSC optimization and to alleviate hyperparameters selection in TSC, we stack one more layer on top of the TSC-inspired sRNN to reconstruct the inputs, and arrive at an sRNN-AE. We further improve sRNN-AE in the following aspects: i) rather than using a predefined similarity measurement between two frames, we propose to learn a data-dependent similarity measurement between neighboring frames in sRNN-AE to make it more suitable for anomaly detection; ii) to reduce computational costs in the inference stage, we reduce the depth of the sRNN in sRNN-AE and, consequently, our framework achieves real-time anomaly detection; iii) to improve computational efficiency, we conduct temporal pooling over the appearance features of several consecutive frames for summarizing information temporally, then we feed appearance features and temporally summarized features into a separate sRNN-AE for more robust anomaly detection. To facilitate anomaly detection evaluation, we also build a large-scale anomaly detection dataset which is even larger than the summation of all existing datasets for anomaly detection in terms of both the volume of data and the diversity of scenes. Extensive experiments on both a toy dataset under controlled settings and real datasets demonstrate that our method significantly outperforms existing methods, which validates the effectiveness of our sRNN-AE method for anomaly detection. Codes and data have been released at https://github.com/StevenLiuWen/sRNN_TSC_Anomaly_Detection.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2019.2944377

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 13 references

Research works printed but not linked: 37

  1. tieleman, 2012, Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude, COURSERA Neural Netw Mach Learn, 26
  2. tudor ionescu, 2017, Unmasking the abnormal events in video, Proc IEEE Int Conf Comput Vis, 2914
  3. giorno, 2016, A discriminative framework for anomaly detection in large videos, Proc Eur Conf Comput Vis, 334
  4. goodfellow, 2014, Generative adversarial nets, Proc Neural Inf Process Syst, 2672
  5. lee, 2007, Efficient sparse coding algorithms, Proc 19th Int Conf Neural Inf Process Syst, 19
  6. 10.1109/TSP.2006.881199 · DOI · Paper page
  7. 10.1109/CVPR.2010.5539872 · DOI · Paper page
  8. sabokrou, 2016, Fully convolutional neural network for fast anomaly detection in crowded scenes. arxiv preprint, arXiv 1609 00866
  9. 10.1109/ICCV.2017.391 · DOI · Paper page
  10. 10.1109/CVPR.2018.00678 · DOI · Paper page
  11. 10.1109/ICME.2017.8019325 · DOI · Paper page
  12. 10.1109/CVPR.2016.86 · DOI · Paper page
  13. simonyan, 2014, Very deep convolutional networks for large-scale image recognition, arXiv 1409 1556
  14. xu, 2015, Learning deep representations of appearance and motion for anomalous event detection, arXiv 1510 01553
  15. chong, 2017, Abnormal event detection in videos using spatiotemporal autoencoder, Proc Int Symp Neural Netw, 189
  16. 10.1109/IWBF.2017.7935096 · DOI
  17. 10.1016/j.imavis.2010.11.003 · DOI · Paper page
  18. 10.1109/CVPR.2016.213 · DOI · Paper page
  19. dalal, 2006, Human detection using oriented histograms of flow and appearance, Proc Eur Conf Comput Vis, 428
  20. 10.1109/CVPR.2005.316 · DOI · Paper page
  21. 10.1109/TPAMI.2007.70825 · DOI · Paper page
  22. 10.1109/CVPR.2009.5206569 · DOI · Paper page
  23. 10.1109/TIP.2017.2695105 · DOI · Paper page
  24. 10.1109/CVPR.2011.5995434 · DOI · Paper page
  25. ren, 2016, A comprehensive study of sparse codes on abnormality detection, Proc IEEE Int Conf Adv Video Signal Based Surveillance, 66
  26. 10.1109/CVPR.2011.5995524 · DOI · Paper page
  27. 10.1109/ICCV.2013.338 · DOI · Paper page
  28. scholkopf, 2001, Learning With Kernels Support Vector Machines Regularization Optimization and Beyond, 10.7551/mitpress/4175.001.0001 · DOI · Paper page
  29. 10.1109/ICASSP.2017.7952977 · DOI
  30. simonyan, 2014, Two-stream convolutional networks for action recognition in videos, Proc 27th Int Conf Neural Inf Process Syst, 568
  31. 10.1016/j.cviu.2013.06.007 · DOI · Paper page
  32. 10.1109/ICCV.2017.45 · DOI · Paper page
  33. wang, 2013, Histograms of optical flow orientation for abnormal events detection, Proc IEEE Int Workshop Perform Eval Tracking Surveillance, 45
  34. abadi, 2016, Tensorflow: A system for large-scale machine learning, Proc 12th USENIX Conf Operating Syst Des Implementation, 16, 265
  35. 10.1109/CVPRW.2011.5981799 · DOI · Paper page
  36. 10.1109/NCVPRIPG.2013.6776164 · doi:10.1109/ncvpripg.2013.6776164
  37. 10.1109/CVPR.2017.787 · DOI · Paper page

Cited by

Metadata

Authors
Luo, W., Liu, W., Lian, D., Tang, J., Duan, L., Peng, X., & Gao, S.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2021-03-01
Volume
43
Issue
3
Pages
1070-1084
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W2976482555
Cited by
243
References
13
FWCI
9.90
Type
journal article
Language
en
Open access
closed
Funders
  • National Key Research and Development Program of China (2016YFB1001001)
  • National Natural Science Foundation of China (61502304)
  • Fundamental Research Funds for the Central Universities (YJ201949, 2018SCUH0070)
  • Northwest Fisheries Science Center (61806135)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.