Abstract
Abnormal event detection is a challenging issue in video surveillance, and it is quite necessary for detecting suspicious behaviour in the normal video data. Detecting abnormalities in video is very crucial and the application ranges from automatic control of quality to visual surveillance data. This paper presented efficient abnormal event detection in video utilizing deep attention based bidirectional LSTM (Long Short Term Memory) with a Mayfly optimization. Initially, the key frames of input video are selected utilizing threshold based discrete wavelet transform. In the second stage, Kernel Entropy Component Analysis (KECA) is used for decreasing the dimensionality. In the third stage, optimal weighted bilateral filtering is utilized for removing the unnecessary noises. In the next stage, a hybrid dual tree Gabor transform is utilized for the effective feature extraction. Afterwards, the Farne back optical methodology is incorporated to estimate the motion in the video sequence. In the final stage, deep attention based bidirectional LSTM with a mayfly optimized model effectively detects the abnormal events. This presented methodology effectively detects normal and abnormal events and it is implemented in PYTHON platform. The performance of the proposed approach is tested on QMUL and UCF datasets. The experimental outcomes of the presented methodology proved that the presented work is significantly better in terms of various effective performance measures like accuracy, AUC (Area Under Curve), execution time and ROC (Receiver Operating Characteristics) measures. The proposed approach achieved the improved outcomes in terms of accuracy as (94.19%) for QMUL dataset, and (93.60%) for UCF dataset.
Similar content being viewed by others
References
Athanesious JJ, Chakkaravarthy SS, Vasuhi S, Vaidehi V (2019) Trajectory based abnormal event detection in video traffic surveillance using general potential data field with spectral clustering. Multimed Tools Appl 78(14):19877–19903
Balasundaram A, Chellappan C (2020) An intelligent video analytics model for abnormal event detection in online surveillance video. J Real-Time Image Proc 17(4):915–930
Bhargavi MS, Benifa JVB, Jaiswal R (2020) Abnormal Event Detection in Public Places by Deep Learning Methods. In Congress on Intelligent Systems, pp. 701–711. Springer, Singapore
Bouindour S, Hittawe MM, Mahfouz S, Snoussi H (2017) "Abnormal event detection using convolutional neural networks and 1-class SVM classifier." : 1–6
Bouindour S, Snoussi H, Hittawe MM, Tazi N, Wang T (2019) An On-Line and Adaptive Method for Detecting Abnormal Events in Videos Using Spatio-Temporal ConvNet. Appl Sci 9(4):757
Chen H, Gai J, Zhang S, Wang C, Guo C, Ye X, Yu L (2018) Abnormal event detection based on cosparse reconstruction. The Journal of Engineering 2018(5):254–256
Chu W, Xue H, Yao C, Deng C (2018) Sparse coding guided spatiotemporal feature learning for abnormal event detection in large videos. IEEE Transactions on Multimedia 21(1):246–255
Fanello SR, Gori I, Metta G, Odone F (2013) One-shot learning for real-time action recognition. In Iberian Conference on Pattern Recognition and Image Analysis, pp. 31–40. Springer, Berlin, Heidelberg
Geng Y, Du J, Liang M (2019) Abnormal event detection in tourism video based on salient spatio-temporal features and sparse combination learning. World Wide Web 22(2):689–715
Jiang F, Wu Y, Katsaggelos AK (2007) .Abnormal event detection from surveillance video by dynamic hierarchical clustering. In 2007 IEEE international conference on image processing, vol. 5, pp. V-145. IEEE
Jiang F, Wu Y, Katsaggelos AK (2009) A dynamic hierarchical clustering method for trajectory-based unusual video event detection. IEEE Trans Image Process 18(4):907–913
Li A, Miao Z, Cen Y, Zhang X-P, Zhang L, Chen S (2020) Abnormal event detection in surveillance videos based on low-rank and compact coefficient dictionary learning. Pattern Recogn 108:107355
Lu C, Shi J, Wang W, Jia J (2019) Fast abnormal event detection. Int J Comput Vis 127(8):993–1011
QMUL dataset (n.d.) http://personal.ie.cuhk.edu.hk/~ccloy/downloads_qmul_junction.html. Accessed 15 Aug 2021
Sekh AA, Dogra DP, Kar S, Roy PP (2020) Video trajectory analysis using unsupervised clustering and multi-criteria ranking. Soft Computing, vol 24, pp-16643–16654.
Sun J, Shao J, He C (2019) Abnormal event detection for video surveillance using deep one-class learning. Multimed Tools Appl 78(3):3633–3647
UCF dataset (n.d.) https://www.crcv.ucf.edu/data/crowd.php. Accessed 15 Aug 2021
Wan S, Xu X, Wang T, Zonghua G (2020) An intelligent video analysis method for abnormal event detection in intelligent transportation systems. IEEE Trans Intell Transp Syst 22:4487–4495
Wang T, Chen J, Snoussi H (2013) Online detection of abnormal events in video streams. Journal of Electrical and Computer Engineering 2013:1–12
Wang T, Qiao M, Deng Y, Zhou Y, Wang H, Lyu Q, Snoussi H (2018) Abnormal event detection based on analysis of movement information of video sequence. Optik 152:50–60
Wang Z, Hou C, Li B, Chen T, Yao L, Song M (2018) "Global abnormal event detection in video via motion information entropy." In 2018 2nd URSI Atlantic Radio Science Meeting (AT-RASC), pp. 1–4. IEEE
Wang J, Xia L, Hu X, Xiao Y (2019) Abnormal event detection with semi-supervised sparse topic model. Neural Comput & Applic 31(5):1607–1617
Wang T, Qiao M, Zhu A, Shan G, Snoussi H (2020) Abnormal event detection via the analysis of multi-frame optical flow information. Frontiers of Computer Science 14(2):304–313
Xu D, Ricci E, Yan Y, Song J, Sebe N (2015) "Learning deep representations of appearance and motion for anomalous event detection." arXiv preprint arXiv:1510.01553
Ye R, Li X (2017) Collective representation for abnormal event detection. J Comput Sci Technol 32(3):470–479
Ye O, Deng J, Yu Z, Liu T, Dong L (2020) Abnormal event detection via feature expectation subgraph calibrating classification in video surveillance scenes. IEEE Access 8:97564–97575
Yu M, Bambacus M, Cervone G, Clarke K, Duffy D, Huang Q, Li J et al (2020) Spatiotemporal event detection: a review. Int J Digit Earth 13(12):1339–1365
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Matlani, P., Shrivastava, M. Efficient abnormal event detection in video using deep attention based bidirectional lstm with a mayfly optimization. Multimed Tools Appl 81, 42371–42392 (2022). https://doi.org/10.1007/s11042-022-13494-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13494-8