Abnormal global and local event detection in compressive sensing domain
Source abstract
Abstract
Abnormal event detection, also known as anomaly detection, is one challenging task in security video surveillance. It is important to develop effective and robust movement representation models for global and local abnormal event detection to fight against factors such as occlusion and illumination change. In this paper, a new algorithm is proposed. It can locate the abnormal events on one frame, and detect the global abnormal frame. The proposed algorithm employs a sparse measurement matrix designed to represent the movement feature based on optical flow efficiently. Then, the abnormal detection mission is constructed as a one-class classification task via merely learning from the training normal samples. Experiments demonstrate that our algorithm performs well on the benchmark abnormal detection datasets against state-of-the-art methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Network Security and Intrusion Detection · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automation Science and Electrical Engineering, Beihang University 1 , Beijing 100191, China
Centre of Intelligent Acoustics and Immersive Communications at School of Marine Science and Technology, Northwestern Polytechnical University 2 , Xi’an 710072, China
School of Computer Science, Shenyang Aerospace University 3 , Shenyang 110136, China
Institute Charles Delaunay-LM2S-UMR STMR 6279 CNRS, University of Technology of Troyes 4 , Troyes 10010, France
Funding
National Key R&D Program of China · National Natural Science Foundation of China · Aeronautical Science Foundation of China
References (34)
Show source-provided references
1. Anomaly detection and activity perception using covariance descriptor for trajectories
2. Action recognition with improved trajectories
3. Realtime anomaly detection using trajectory-level crowd behavior learning
4. Video covariance matrix logarithm for human action recognition in videos
5. A fast and robust convolutional neural network-based defect detection model in product quality control
6. Real-time compressive tracking
7. Abnormality detection using low-level co-occurring events10.1016/j.patrec.2010.10.008 ↗
8. Robust visual behavior recognition10.1109/msp.2010.937392 ↗
9. Anomaly detection and localization in crowded scenes10.1109/tpami.2013.111 ↗
10. Swarm intelligence for detecting interesting events in crowded environments10.1109/tip.2015.2409559 ↗
11. Internal transfer learning for improving performance in human action recognition for small datasets10.1109/access.2017.2746095 ↗
12. Robust real-time unusual event detection using multiple fixed-location monitors10.1109/tpami.2007.70825 ↗
13. Detection of unusual optical flow patterns by multilevel hidden Markov models10.1117/1.3280284 ↗
14. Sparse reconstruction cost for abnormal event detection
15. Abnormal event detection in crowded scenes using sparse representation10.1016/j.patcog.2012.11.021 ↗
16. Chaotic invariants of Lagrangian particle trajectories for anomaly detection in crowded scenes
17. Detection of abnormal visual events via global optical flow orientation histogram10.1109/tifs.2014.2315971 ↗
18. Online least squares one-class support vector machines-based abnormal visual event detection10.3390/s131217130 ↗
19. Determining optical flow10.1016/0004-3702(81)90024-2 ↗
20. Secrets of optical flow estimation and their principles
21. A simple proof of the restricted isometry property for random matrices10.1007/s00365-007-9003-x ↗
22. Database-friendly random projections: Johnson-Lindenstrauss with binary coins10.1016/s0022-0000(03)00025-4 ↗
23. Abnormal event detection via covariance matrix for optical flow based feature
24. Estimating the support of a high-dimensional distribution10.1162/089976601750264965 ↗
25. 2005
26. Abnormal crowd behavior detection using social force model
27. Real-time abnormal event detection in complicated scenes
28. Crowd behavior analysis using local mid-level visual descriptors10.1109/tcsvt.2016.2615443 ↗
29. Crowd behavior recognition using dense trajectories
30. Anomaly detection in crowded scenes
31. Detecting humans in dense crowds using locally-consistent scale prior and global occlusion reasoning10.1109/tpami.2015.2396051 ↗
32. Mask r-cnn
33. Video anomaly search in crowded scenes via spatio-temporal motion context10.1109/tifs.2013.2272243 ↗
34. Social network model for crowd anomaly detection and localization10.1016/j.patcog.2016.06.016 ↗