Browse > Article
http://dx.doi.org/10.3837/tiis.2015.01.010

Anomalous Event Detection in Traffic Video Based on Sequential Temporal Patterns of Spatial Interval Events  

Ashok Kumar, P.M. (Department of Electronics Engineering & AU-KBC Research Centre, MIT Campus. Anna University)
Vaidehi, V. (Department of Electronics Engineering & AU-KBC Research Centre, MIT Campus. Anna University)
Publication Information
KSII Transactions on Internet and Information Systems (TIIS) / v.9, no.1, 2015 , pp. 169-189 More about this Journal
Abstract
Detection of anomalous events from video streams is a challenging problem in many video surveillance applications. One such application that has received significant attention from the computer vision community is traffic video surveillance. In this paper, a Lossy Count based Sequential Temporal Pattern mining approach (LC-STP) is proposed for detecting spatio-temporal abnormal events (such as a traffic violation at junction) from sequences of video streams. The proposed approach relies mainly on spatial abstractions of each object, mining frequent temporal patterns in a sequence of video frames to form a regular temporal pattern. In order to detect each object in every frame, the input video is first pre-processed by applying Gaussian Mixture Models. After the detection of foreground objects, the tracking is carried out using block motion estimation by the three-step search method. The primitive events of the object are represented by assigning spatial and temporal symbols corresponding to their location and time information. These primitive events are analyzed to form a temporal pattern in a sequence of video frames, representing temporal relation between various object's primitive events. This is repeated for each window of sequences, and the support for temporal sequence is obtained based on LC-STP to discover regular patterns of normal events. Events deviating from these patterns are identified as anomalies. Unlike the traditional frequent item set mining methods, the proposed method generates maximal frequent patterns without candidate generation. Furthermore, experimental results show that the proposed method performs well and can detect video anomalies in real traffic video data.
Keywords
Gaussian Mixture Models; Block Motion Estimation; Primitive Events; Lossy Count based Approach; Sequential Temporal Patterns;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Benezeth.Y, Jodoin P.M., Saligrama V, "Abnormal events detection based on spatio-temporal co-occurrences," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2458-2465, 2009.
2 Chen L, Yuan Cao and Ronghua Ji, "Automatic Incident Detection Algorithm Based on Support Vector Machine," in Proc. of Sixth IEEE International Conference on Natural Computation, vol. 2, pp. 864-866, 2010.
3 Dong N, Zhen Jia, Jie Shao, "Traffic Abnormality Detection through Directional MotionBehaviour Map," in Proc. of Seventh IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 80-84, 2010.
4 Galata A, Johnson N., Hogg D.C., "Learning variable-length Markov Models of behaviour," Computer Vision and Image Understanding 81 (3), 398-413 , 2001.   DOI
5 Harwood D, Haritaoglu I and Larry S. Davis, "W4: Real-time surveillance of people and their activities," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.22, pp. 809-830, 2000.   DOI
6 Hoppner, F., "Knowledge discovery from sequential data," Ph.D. thesis, Technical University Braunschweig, Germany, 2003.
7 Hsu W L, Chang-Lung Tsai and Po-Lun Chang, "Automatic Traffic Monitoring Method Based on Cellular Model," in Proc. of Fifth IEEE International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 640-643, 2009.
8 Hu W, Wang L and Tan T., "Recent developments in human motion analysis and Pattern Recognition," in Elsevier Journal, vol. 36, pp. 585-601,2003.   DOI
9 C.R. Jung, L. Hennemann, S.R. Musse, "Event detection using trajectory clustering and 4-d histograms," IEEE Transactions on Circuits and Systems for Video Technology, 18 (11), 1565-1575, 2008.   DOI
10 Kamijo S, Harada M, Sakauchi M, "Incident Detection based on Semantic Hierarchy composed of the Spatio-Temporal MRF model and Statistical Reasoning," IEEE International Conference on Man and Cybernetics, vol.1 ,415-421, 2004.
11 Ki Y, Lee D, "A traffic accident recording and reporting model at Intersections," IEEE Transactions on Intelligent TransportationSystem, vol.8, issue. 2, pp.188-196, 2007.   DOI
12 Kim. J, Grauman K., "Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates," in Proc. of Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921-2928, 2009.
13 Kuettel.D, Breitenstein, M.D.,VanGool, L., "What's going on? Discovering spatio-temporal dependencies in dynamic scenes," in Proc. of Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2010.
14 Leibe. B,Schindler, K.,Cornelis, N., "Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30, No. 10, pp. 1683-1698 , 2008.   DOI
15 Lin, C., Tai, J. and Song, K, "Traffic monitoring based on real-time image tracking," in Proceedings of the IEEE International Conference on Robotics & Automation, vol.2, pp. 2091-2096, 2003.
16 Loy.C.C,Tao Xiang, Shaogang Gong, "Stream-based active unusual event detection," in Proc. of proceedings of Springer on Computer Vision-ACCV 2010, pp. 161-175, 2011.
17 Loy. C.C, Xiang T., and Gong S., "From Local Temporal Correlation to Global Anomaly Detection," in Proc. of ECCV, International Workshop on Machine Learning for Vision-based Motion Analysis, 2008.
18 Manku G.S. and Rajeev Motwani, "Approximate Frequency Counts over Data Streams," in Proc. of the 28th VLDB Conference, Hong Kong, China, 2002.
19 Moskovitch, R. Shahar, Y., "Medical temporal-knowledge discovery via temporal abstraction," in Proc. of the American Medical Informatics Association (AMIA), 2009.
20 Moerchen, F., "Algorithms for time series knowledge mining," in Proc. of the international conference on Knowledge Discovery and Data mining (SIGKDD), 668-673, 2006.
21 Oliver.N.M, Rosario B., Pentland A.P., "A Bayesian computer vision system for modeling human interactions," IEEE Transactions on Pattern Analysis and Machine Intelligence 22, pp no. 831-843, 2000.   DOI
22 Papapetrou P., Kollios, G., Sclaroff S., "Discovering frequent arrangements of temporal intervals," in Proc. of the International Conference on Data Mining (ICDM), 2005.
23 Piciarelli C., Micheloni C. and Foresti G.L, "Trajectory-Based Anomalous Event Detection," IEEE Transactions on Circuits and Systems for Video Technology, vol. 18, issue 11, pp. 1544-1554, 2008.   DOI
24 SacchiL, Cristiana Larizza, Carlo Combi, "Data mining with Temporal Abstractions: learning rules from time series," Data Mining and Knowledge Discovery, 2007.
25 Schindler. K., Schindler, K., Cornelis, N., "Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30, No. 10, pp. 1683-1698, 2008.   DOI
26 Shan kam P, Chee fu A. W., "Discovering temporal patterns for interval-based events," in Proc. of the International Conference on Data Warehousing and Knowledge Discovery (DaWaK),2000.
27 Stauffer. C and Grimson W., "Adaptive background mixture models for real-time tracking," in Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 246-252, 1999.
28 Villafane R, Kien A. Hua, Duc Tran, "Knowledge discovery from series of interval events," Journal of Intelligent Information Systems 15, pp 71-89, 2000.   DOI
29 Swears, E., Hoogs A., and Perera, A.G.A, "Learning motion patterns in surveillance video using HMM clustering," in Proc. of IEEE Visual Motion Computing (Motion) Workshop, Copper Mountain/Colarado, pp.1-8, 2008.
30 Veeraraghavan, H., Schrater. P. and Papanikolopoulos N, "Switching Kalman Filter-Based Approach for Tracking and Event Detection at Traffic Intersections," in Proc. of IEEE Conference on Control and Automation, 1167-1172, 2005.
31 Wang. X, Ma Xa, Grimson W.E.L., "Unsupervised activity perception in crowded and complicated scenes using hierarchical Bayesian models," IEEE Transactions on Pattern Analysis and Machine Intelligence, 31 (3), 539-555, 2009.   DOI
32 Winarko E, Roddick J. F. "Armada - an algorithm for discovering richer relative temporal association rules from interval-based data," Data and Knowledge Engineering 63, pp 76-90, 2007.   DOI
33 Wu S.Y., Chen Y.L. "Mining non-ambiguous temporal patterns for interval-based events," IEEE Transactions on Knowledge and Data Engineering 19, pp 742-758, 2007.   DOI
34 Yao B, Wang L, Zhu S., "Learning a scene contextual model for tracking and abnormality detection," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1-8 , 2008.
35 Zou Y,Guangyi Shi, Hang Shi, "Image sequences based traffic incident detection for signalled intersections using HMM," in Proc. of international Conference on Hybrid Intelligent Systems, 2009.
36 Xiaokun Li, Porikli, F.M. "A hidden Markov model framework for traffic event detection using video features," in Proc. of IEEE Conference on Image Processing, pp 1902-1907, 2004.
37 Gilbert. A, Illingworth. J. and Bowden, R, "Action Recognition Using Mined Hierarchical Compound Features," in IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, Issue: 5, pp.883 -897, 2011.   DOI
38 Lili C, Kehuang Li, Jiapin Chen, "Abnormal Event Detection in Traffic Video Surveillance Based on Local Features," IEEE Transactions on Image and Signal Processing, vol.1, pp. 362-366, 2011.
39 Renxiang Li, Bing Zeng, and Ming L. Liou, "A new Three- step Search Algorithm for Block Motion Estimation," IEEE Trans, Circuits and Systems For Video Technology, Vol 4., no 4, , pp 438-442 , 1994.   DOI