A REVIEW ON DETECTION OF ABNORMAL EVENT FOR PEDESTRIAN VIDEO SURVEILLANCE
Abstract
An Anomaly can be defined as an observation that does follow the normal activities with respect to others. Anomaly is polysemy that varies in a different context. For video sequences, an anomaly can be defined in terms of motion or state of motion that obtrude concerning to state and time. This work is based on Pedestrian Video Surveillance, having a normal event as a pedestrian and abnormal event as cars, skaters, bikers, wheelchairs, etc.i.e., non-pedestrian.A comprehensive study has been carried out of many existing systems for the Anomaly detection system. Based on many existing techniques we select a method called optical flow for the feature presentation of the detection of motion and Histogram of optical flow (HOOF) for the action contour of optical flow for every time instant irrespective of scale and direction of motion. As HOOF represents the motion of an object in a region, so there may be cases that the information related to the motion is not well represented. We used these two techniques along with the labelling of the frame in order to overcome the problem of HOOF for the classifier. And gives the improved results. For training the model, the UCSD dataset is used which is very versatile having ample scenarios of normal and abnormal activities. For classification, three classifiers are used namely k Nearest Neighbors (k-NN), Logistic Regression (LR) and Support Vector Machine (SVM) which train the model to classify the event into a normal and abnormal event. The results of these classifiers are compared and give the best result out of it for all the video sequences.
Keyword : figure, project, table, layout
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1] "A. Basharat, A. Gritai, and M. Shah, “Learning object motion patterns for anomaly detection and improved object detection,” 26th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR, 2008, doi: 10.1109/CVPR.2008.4587510. [2] P. Gomathi, S. Baskar, P. M. Shakeel, and V. R. S. Dhulipala, “Identifying brain abnormalities from electroencephalogram using evolutionary gravitational neocognitron neural network,” Multimed. Tools Appl., vol. 79, no. 15–16, pp. 10609–10628, 2020, doi: 10.1007/s11042-019-7301-5. [3] S. Huang, D. Huang, and X. Zhou, “Learning Multimodal Deep Representations for Crowd Anomaly Event Detection,” Math. Probl. Eng., vol. 2018, 2018, doi: 10.1155/2018/6323942. [4] S. Wu, B. E. Moore, and M. Shah, “Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 2054–2060, 2010, doi: 10.1109/CVPR.2010.5539882." [5] "B. Zhao, L. Fei-Fei, and E. P. Xing, “Online detection of unusual events in videos via dynamic sparse coding,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 3313–3320, 2011, doi: 10.1109/CVPR.2011.5995524. [6] F. Jiang, J. Yuan, S. A. Tsaftaris, and A. K. Katsaggelos, “Anomalous video event detection using spatiotemporal context,” Comput. Vis. Image Underst., vol. 115, no. 3, pp. 323–333, 2011, doi: 10.1016/j.cviu.2010.10.008. [7] O. Boiman and M. Irani, “Detecting irregularities in images and in video,” Int. J. Comput. Vis., vol. 74, no. 1, pp. 17–31, 2007, doi: 10.1007/s11263-006-0009-9. [8] N. R. Prasad, S. Almanza-Garcia, and T. T. Lu, “Anomaly detection,” Comput. Mater. Contin., vol. 14, no. 1, pp. 1–22, 2009, doi: 10.1145/1541880.1541882." [9] S. Wang, E. Zhu, J. Yin, and F. Porikli, “Video anomaly detection and localization by local motion based joint video representation and OCELM,” Neurocomputing, vol. 277, pp. 161–175, 2018, doi: 10.1016/j.neucom.2016.08.156. [10] "T. Subetha and S. Chitrakala, “A survey on human activity recognition from videos,” 2016 Int. Conf. Inf. Commun. Embed. Syst. ICICES 2016, no. Icices, 2016, doi: 10.1109/ICICES.2016.7518920. [11] O. L. Mangasarian, “A Feature Selection Newton Method for Support,” pp. 185–202, 2004. [12] M. Mejdoub and C. Ben Amar, “Classification improvement of local feature vectors over the KNN algorithm,” Multimed. Tools Appl., vol. 64, no. 1, pp. 197–218, 2013, doi: 10.1007/s11042-011-0900-4. [13] O. P. Popoola and K. Wang, “Video-based abnormal human behavior recognitiona review,” IEEE Trans. Syst. Man Cybern. Part C Appl. Rev., vol. 42, no. 6, pp. 865–878, 2012, doi: 10.1109/TSMCC.2011.2178594. [14] F. Jiang, Y. Wu, and A. K. Katsaggelos, “A dynamic hierarchical clustering method for trajectory-based unusual video event detection,” IEEE Trans. Image Process., vol. 18, no. 4, pp. 907–913, 2009, doi: 10.1109/TIP.2008.2012070. [15] T. Zhang, H. Lu, and S. Z. Li, “Learning semantic scene models by object classification and trajectory clustering,” 2009 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work. CVPR Work. 2009, vol. 2009 IEEE, pp. 1940–1947, 2009, doi: 10.1109/CVPRW.2009.5206809." [16] "A. Raghunandan, Mohana, P. Raghav, and H. V. R. Aradhya, “Object Detection Algorithms for Video Surveillance Applications,” Proc. 2018 IEEE Int. Conf. Commun. Signal Process. ICCSP 2018, no. February 2019, pp. 563–568, 2018, doi: 10.1109/ICCSP.2018.8524461. [17] D. Campo, M. Baydoun, L. Marcenaro, A. Cavallaro, and C. S. Regazzoni, “Unsupervised trajectory modeling based on discrete descriptors for classifying moving objects in video sequences,” Proc. - Int. Conf. Image Process. ICIP, pp. 833–837, 2018, doi: 10.1109/ICIP.2018.8451837. [18] P. Cui, L. F. Sun, Z. Q. Liu, and S. Q. Yang, “A sequential Monte Carlo approach to anomaly detection in tracking visual events,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., no. 7001794, 2007, doi: 10.1109/CVPR.2007.383515. [19] G. Luo and Y. Zhu, “Foreground Removal Approach for Hole Filling in 3D Video and FVV Synthesis,” IEEE Trans. Circuits Syst. Video Technol., vol. 27, no. 10, pp. 2118–2131, 2017, doi: 10.1109/TCSVT.2016.2583978." [20] "H. Zhong, J. Shi, and M. Visontai, “Detecting Unusual Events in Video,” IEEE Conf. Comput. Vis. Pattern Recognit., vol. 2, no. June, pp. II--819, 2004. [21] S. Bansod and A. Nandedkar, “Detection and Localization of Anomalies from Videos based on Optical flow Magnitude and Direction,” vol. 137, pp. 457–465, 2017, doi: 10.2991/iccasp-16.2017.68. [22] R. Parvathy, S. Thilakan, M. Joy, and K. M. Sameera, “Anomaly detection using motion patterns computed from optical flow,” Proc. - 2013 3rd Int. Conf. Adv. Comput. Commun. ICACC 2013, pp. 58–61, 2013, doi: 10.1109/ICACC.2013.18. [23] W. Hu, X. Xiao, Z. Fu, D. Xie, T. Tan, and S. Maybank, “A system for learning statistical motion patterns,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 9, pp. 1450–1464, 2006, doi: 10.1109/TPAMI.2006.176. [24] Y. Yuan, J. Fang, and Q. Wang, “Online anomaly detection in crowd scenes via structure analysis,” IEEE Trans. Cybern., vol. 45, no. 3, pp. 562–575, 2015, doi: 10.1109/TCYB.2014.2330853. [25] M. Granovetter, T. American, N. May, and M. Granovetter, “Threshold Models of Collective Behavior Threshold Models of Collective Behavior ’,” vol. 83, no. 6, pp. 1420–1443, 2007." [26] "S. Chowdhury, B. Verma, M. Tom, and M. Zhang, “Pixel characteristics based feature extraction approach for roadside object detection,” Proc. Int. Jt. Conf. Neural Networks, vol. 2015-Septe, 2015, doi: 10.1109/IJCNN.2015.7280599. [27] S. Yi, H. Li, and X. Wang, “Understanding pedestrian behaviors from stationary crowd groups,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 07-12-June, pp. 3488–3496, 2015, doi: 10.1109/CVPR.2015.7298971. [28] S. Cosar, G. Donatiello, V. Bogorny, C. Garate, L. O. Alvares, and F. Bremond, “Toward Abnormal Trajectory and Event Detection in Video Surveillance,” IEEE Trans. Circuits Syst. Video Technol., vol. 27, no. 3, pp. 683–695, 2017, doi: 10.1109/TCSVT.2016.2589859. [29] R. Emonet, J. Varadarajan, and J. M. Odobez, “Temporal analysis of motif mixtures using dirichlet processes,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 36, no. 1, pp. 140–156, 2014, doi: 10.1109/TPAMI.2013.100. [30] B. Zhou, X. Tang, and X. Wang, “Measuring crowd collectiveness,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 3049–3056, 2013, doi: 10.1109/CVPR.2013.392." [31] B. K. Horn and B. G. Schunck, “Determining Optical Flow” Tech. Appl. Image Underst., vol. 0281, pp. 319–331, 1981, doi: 10.1117/12.965761. [32] "B. D. Lucas, “An Iterative Image Registration Technique with an Application to Stereo Vision 2 . The registration problem 3 . Existing techniques,” Robotics, no. x, pp. 674–679, 1981. [33] A. Ranjan and M. J. Black, “Optical flow estimation using a spatial pyramid network,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 2720–2729, 2017, doi: 10.1109/CVPR.2017.291. [34] L. Li and Y. Yang, “Optical flow estimation for a periodic image sequence,” IEEE Trans. Image Process., vol. 19, no. 1, pp. 1–10, 2010, doi: 10.1109/TIP.2009.2032341. [35] D. List, Advances in Nematology Advances in Nematology, no. December. 2013. [36] A. L. Hou, J. L. Guo, C. J. Wang, L. Wu, and F. Li, “Abnormal behavior recognition based on trajectory feature and regional optical flow,” Proc. - 2013 7th Int. Conf. Image Graph. ICIG 2013, pp. 643–649, 2013, doi: 10.1109/ICIG.2013.134. [37] R. Mondal and B. Chanda, “Anomaly Detection using Context Dependent Optical Flow,” pp. 1–8, 2018, doi: 10.1145/3293353.3293375." [38] "E. Ilg, N. Mayer, T. Saikia, M. Keuper, A. Dosovitskiy, and T. Brox, “FlowNet 2.0: Evolution of optical flow estimation with deep networks,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 1647–1655, 2017, doi: 10.1109/CVPR.2017.179. [39] H. Nallaivarothayan, C. Fookes, S. Denman, and S. Sridharan, “An MRF based abnormal event detection approach using motion and appearance features,” 11th IEEE Int. Conf. Adv. Video Signal-Based Surveillance, AVSS 2014, pp. 343–348, 2014, doi: 10.1109/AVSS.2014.6918692. [40] N. Nayan, S. S. Sahu, and S. Kumar, “Detecting anomalous crowd behavior using correlation analysis of optical flow,” Signal, Image Video Process., no. 0123456789, 2019, doi: 10.1007/s11760-019-01474-9. [41] R. Chaudhry, A. Ravichandran, G. Hager, and R. Vidal, “Histograms of oriented optical flow and Binet-Cauchy kernels on nonlinear dynamical systems for the recognition of human actions,” 2009 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work. CVPR Work. 2009, vol. 2009 IEEE, pp. 1932–1939, 2009, doi: 10.1109/CVPRW.2009.5206821. [42] S. V. N. Vishwanathan, A. J. Smola, and R. Vidal, “Binet-Cauchy kernels on dynamical systems and its application to the" analysis of dynamic scenes,” Int. J. Comput. Vis., vol. 73, no. 1, pp. 95–119, 2007, doi: 10.1007/s11263-006-9352-0. [43] "L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri, “Actions as space-time shapes,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 12, pp. 2247–2253, 2007, doi: 10.1109/TPAMI.2007.70711. [44] T. Wang and H. Snoussi, “Detection of abnormal visual events via global optical flow orientation histogram,” IEEE Trans. Inf. Forensics Secur., vol. 9, no. 6, pp. 988–998, 2014, doi: 10.1109/TIFS.2014.2315971. [45] K. Lertniphonphan, S. Aramvith, and T. H. Chalidabhongse, “Human action recognition using direction histograms of optical flow,” 11th Int. Symp. Commun. Inf. Technol. Isc. 2011, vol. c, no. Iscit, pp. 574–579, 2011, doi: 10.1109/ISCIT.2011.6089701. [46] T. Wang and H. Snoussi, “Histograms of optical flow orientation for abnormal events detection,” IEEE Int. Work. Perform. Eval. Track. Surveillance, PETS, pp. 45–52, 2013, doi: 10.1109/PETS.2013.6523794. [47] Y. Benabbas, N. Ihaddadene, and C. Djeraba, “Motion pattern extraction and event detection for automatic visual surveillance,” Eurasip J. Image Video Process., vol. 2011, 2011, doi: 10.1155/2011/163682." [48] C. L. Algorithms, “Chapter 5.” [49] L. J. Cao and F. E. H. Tay, “Support "vector machine with adaptive parameters in financial time series forecasting,” IEEE Trans. Neural Networks, vol. 14, no. 6, pp. 1506–1518, 2003, doi: 10.1109/TNN.2003.820556. [50] Y. Miao, “Abnormal Event Detection Based on SVM in Video Surveillance,” 2014 IEEE Work. Adv. Res. Technol. Ind. Appl., pp. 1379–1383, 2014, doi: 10.1109/WARTIA.2014.6976540. [51] P. Batapati, D. Tran, W. Sheng, M. Liu, and R. Zeng, “Video analysis for traffic anomaly detection using support vector machines,” Proc. World Congr. Intell. Control Autom., vol. 2015-March, no. March, pp. 5500–5505, 2015, doi: 10.1109/WCICA.2014.7053655. [52] C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, “finder : Real-Time Tracking” Analysis, vol. 19, no. 7, pp. 780–785, 1997. [53] N. Community, “NumPy User Guide 1.11,” p. 109, 2013. [54] I. P. Alonso et al., “Combination of feature extraction methods for SVM pedestrian detection,” IEEE Trans. Intell. Transp. Syst., vol. 8, no. 2, pp. 292–307, 2007, doi: 10.1109/TITS.2007.894194. [55]" http://www.svcl.ucsd.edu/projects/anomaly/dataset.html