Ahlam AL-DHAMARI, Rubita SUDIRMAN, Nasrul Humaimi MAHMOOD

Abnormal behavior detection using sparse representations through sequential generalization of k-means

The potential capability to automatically detect and classify human behavior as either normal or abnormal events is an important aspect in intelligent monitoring/surveillance systems. This study presents a new high-performance framework for detecting behavioral abnormalities in video streams by utilizing only the patterns for normal behaviors. In this paper, we used a hybrid descriptor, called a foreground optical flow energy (FGOFE), which makes use of two effective motion techniques in order to extract the most descriptive spatiotemporal features in video sequences. The FGOFE descriptor can effectively capture both weak and sudden incidents in a scene. The sequential generalization of k-means (SGK) algorithm was applied in this study to generate the dictionary set that can sparsely represent each signal; in addition, the orthogonal matching pursuit algorithm was utilized to recover high-dimensional sparse features when referring to a few numbers of noisy linear measurements. Using the SGK allows gaining a less complex and quicker implementation compared to other dictionary learning methods. We conducted comprehensive experiments to analyze and evaluate the ability of our framework in detecting abnormalities using several public benchmarks, which contain different abnormal samples and various contextual compositions. The experimental results show that the proposed framework achieved high detection accuracy (up to 95.33%) and low frame processing time (31 ms on average) compared to the relevant related work.

PDF

___

1] Al-Dhamari A, Sudirman R, Mahmood NH. Abnormal behavior detection in automated surveillance videos: a review. Journal of Theoretical & Applied Information Technology 2017; 95(19): 5245-5263.
[2] Sahu AK, Sahu M. Digital image steganography techniques in spatial domain: a study. International Journal of Pharmacy & Technology 2016; 8(4): 5205-5217.
[3] Mu C, Xie J, Yan W, Liu T, Li P. A fast recognition algorithm for suspicious behavior in high definition videos. Multimedia Systems 2016; 22(3): 275-285.
[4] Al-Dhamari A, Sudirman R, Mahmood NH, Khamis NH, Yahya A. Online video-based abnormal detection using highly motion techniques and statistical measures. Telkomnika 2019; 17(4): 2039-2047.
[5] Gnouma M, Ejbali R, Zaied M. Abnormal events detection in crowded scenes. Multimedia Tools and Applications 2018; 1: 1-22.
[6] Sadeghi M, Babaie-Zadeh M, Jutten C. Learning overcomplete dictionaries based on atom-by-atom updating. IEEE Transactions on Signal Processing 2014; 62(4): 883-891.
[7] Yu B, Liu Y, Sun Q. A content-adaptively sparse reconstruction method for abnormal events detection with low-rank property. IEEE Transactions on Systems, Man, and Cybernetics: Systems 2017; 47(4): 704-716.
[8] Stauffer C, Grimson WEL. Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 2000; 22(8): 747-757.
[9] Bruni V, Vitulano D. An improvement of kernel-based object tracking based on human perception. IEEE Transac- tions on Systems, Man, and Cybernetics: Systems 2014; 44(11): 1474-1485.
[10] Wu Q, Wang Z, Deng F, Chi Z, Feng DD. Realistic human action recognition with multimodal feature selection and fusion. IEEE Transactions on Systems, Man, and Cybernetics: Systems 2013; 43(4): 875-885.
[11] Fu W, Wang J, Lu H, Ma S. Dynamic scene understanding by improved sparse topical coding. Pattern Recognition 2013; 46(7): 1841-1850.
[12] Felori F, Margez F. Motif mining by combined hidden markov model and clustering method. Journal of Bioinfor- matics and Intelligent Control 2015; 4(1): 35-43.
[13] Porikli F, Haga T. Event detection by eigenvector decomposition using object and frame features. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop; Washington, DC, USA; 2004. pp. 114-114.
[14] Varadarajan J, Odobez JM. Topic models for scene analysis and abnormality detection. In: 12th IEEE International Conference on Computer Vision Workshops (ICCV); Kyoto, Japan; 2009. pp. 1338-1345.
[15] Basharat A, Gritai A, Shah M. Learning object motion patterns for anomaly detection and improved object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Anchorage, AK, USA; 2008. pp. 1-8.
16] Cui X, Liu Q, Gao M, Metaxas DN. Abnormal detection using interaction energy potentials. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Colorado Springs, CO, USA; 2011. pp. 3161-3167.
[17] Feng J, Zhang C, Hao P. Online learning with self-organizing maps for anomaly detection in crowd scenes. In: 20th International Conference on Pattern Recognition (ICPR); Istanbul, Turkey; 2010. pp. 3599-3602.
[18] Shao J, Loy CC, Kang K, Wang X. Crowded scene understanding by deeply learned volumetric slices. IEEE Transactions on Circuits and Systems for Video Technology 2017; 27(3): 613-623.
[19] Cong Y, Yuan J, Liu J. Sparse reconstruction cost for abnormal event detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Colorado Springs, CO, USA; 2011. pp. 3449-3456.
[20] Li C, Han Z, Ye Q, Jiao J. Abnormal behavior detection via sparse reconstruction analysis of trajectory. In: Sixth International Conference on Image and Graphics (ICIG); Hefei, Anhui, China; 2011. pp. 807-810.
[21] Lu C, Shi J, Jia J. Abnormal event detection at 150 fps in matlab. In: Proceedings of the IEEE International Conference on Computer Vision; Sydney, NSW, Australia; 2013. pp. 2720-2727.
[22] Qasim T, Bhatti N. A low dimensional descriptor for detection of anomalies in crowd videos. Mathematics and Computers in Simulation 2019; 166: 245-252.
[23] Srinivasan A, Gnanavel VK. Multiple feature set with feature selection for anomaly search in videos using hybrid classification. Multimedia Tools and Applications 2019; 78(6): 7713-7725.
[24] Leyva R, Sanchez V, Li CT. Video anomaly detection with compact feature sets for online performance. IEEE Transactions on Image Processing 2017; 26(7): 3463-3478.
[25] KaewTraKulPong P, Bowden R. An improved adaptive background mixture model for real-time tracking with shadow detection. In: Remagnino P, Jones GA, Paragios N, Regazzoni CS (editors). Video-Based Surveillance Systems. Boston, MA: Springer, 2002, pp. 135-144.
[26] Elgammal A, Duraiswami R, Harwood D, Davis LS. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE 2002; 90(7): 1151-1163.
[27] Abdallah ACB, Gouiffès M, Lacassagne L. A modular system for global and local abnormal event detection and categorization in videos. Machine Vision and Applications 2016; 27(4): 463-481.
[28] Tharwat A. Principal component analysis-a tutorial. International Journal of Applied Pattern Recognition 2016; 3(3): 197-240.
[29] Kutbay U, Ural AB, Hardalaç F. Underground electrical profile clustering using K-MEANS algorithm. In: 23nd Signal Processing and Communications Applications Conference (SIU); Malatya, Turkey; 2015. pp. 561-564.
[30] Hardalaç F, Kutbay U, Şahin İsa, Akyel A. A novel method for robust object tracking with k-means clustering using histogram back-projection technique. Multimedia Tools and Applications 2018; 77(18): 24059-24072.
[31] Zhou T, Liu F, Bhaskar H, Yang J, Zhang H et al. Online discriminative dictionary learning for robust object tracking. Neurocomputing 2018; 275: 1801-1812.
[32] Sahoo SK, Makur A. Sparse sequential generalization of k-means for dictionary training on noisy signals. Signal Processing 2016; 129: 62-66.
[33] Sahoo SK, Makur A. Image denoising via sparse representations over sequential generalization of k-means (SGK). In: 9th International Conference on Information, Communications and Signal Processing (ICICS); Tainan, Taiwan; 2013. pp. 1-5.
[34] Lu G, Zhang K, Huang S, Zhang Y, Feng Z. Modulation recognition for incomplete signals through dictionary learning. In: IEEE Wireless Communications and Networking Conference (WCNC); San Francisco, CA, USA; 2017. pp. 1-6.
[35] Ren H, Pan H, Olsen SI, Moeslund TB. A comprehensive study of sparse codes on abnormality detection. arXiv preprint arXiv:1603.04026 2016
[36] Mahadevan V, Li W, Bhalodia V, Vasconcelos N. Anomaly detection in crowded scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); San Francisco, CA, USA; 2010. pp. 1975-1981.
[37] Mehran R, Oyama A, Shah M. Abnormal crowd behavior detection using social force model. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Miami, FL, USA; 2009. pp. 935-942.
[38] Tharwat A. Classification assessment methods. Applied Computing and Informatics 2018.
[39] Hu Y, Zhang Y, Davis L. Unsupervised abnormal crowd activity detection using semiparametric scan statistic. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops; Portland, OR, USA; 2013. pp. 767-774.
[40] Li W, Mahadevan V, Vasconcelos N. Anomaly detection and localization in crowded scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence 2014; 36(1): 18-32.
[41] Zhu X, Liu J, Wang J, Li C, Lu H. Sparse representation for robust abnormality detection in crowded scenes. Pattern Recognition 2014; 47(5): 1791-1799.
[42] Biswas S, Babu RV. Real time anomaly detection in H. 264 compressed videos. In: Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG); Jodhpur, India; 2013. pp. 1-4.
[43] Adam A, Rivlin E, Shimshoni I, Reinitz D. Robust real-time unusual event detection using multiple xed-location monitors. IEEE Transactions on Pattern Analysis and Machine Intelligence 2008; 30(3): 555-560.
[44] Kim J, Grauman K. Observe locally, infer globally: a space-time MRF for detecting abnormal activities with incremental updates. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Miami, USA; 2009. pp. 2921-2928.