Detection and localization of anomalies in video surveillance using novel optimization based deep convolutional neural network
Tóm tắt
Nowadays, the demand for the surveillance applications is increased in order to guarantee the safety and security of the people/society. Due to the rapid growth in surveillance, human intervention is required to process the human behaviors in monitoring the anomaly attempts. Hence, this research proposes an automatic anomaly detection model for monitoring the anomalies from the surveillance videos. Accordingly, hierarchical-based social hunting optimization tuned Deep-convolutional neural network (HiS- Deep CNN) is proposed for video anomaly detection for which the object detection and tracking are the done initially. The detection improvement of the classifier is based on the training algorithm, hierarchical social hunting optimization (HiS) algorithm, which is designed based on the hybrid characteristics inherited from timber wolf and Ateles geoffrogis search agents. Moreover, the hierarchical social hunting strategy tracking of the video object is done using the features of Minimum output sum of squared error tracking algorithm (MOSSE) and Simple moving average based algorithm (SMA). The effectiveness of the hierarchical-based social hunting tuned Deep-convolutional neural network anomaly detection model is analyzed concerning the indices, such as sensitivity, accuracy, specificity, and Multiple Object Tracking Precision, which is 96.62%, 96.56%, 96.14%, and 0.994, respectively.
Tài liệu tham khảo
Aberkane S, Elarbi-Boudihir M (2022) Deep reinforcement learning-based anomaly detection for video surveillance. Informatica 46(2)
Avenue Dataset, http://www.cse.cuhk.edu.hk/leojia/projects/detectabnormal/dataset.html. Accessed April 2021
Basharat A, Gritai A, Shah M (2008) Learning object motion patterns for anomaly detection and improved object detection. Proc Cvpr IEEE, pp 1–8. https://doi.org/10.1109/CVPR.2008.4587510
Bolme DS, Beveridge J R, Draper BA, Lui Y M (2010) Visual object tracking using adaptive correlation filters. In: Proc Twenty-Third IEEE conf on computer vision and pattern recog CVPR 2010, San Francisco
Cewu L, Shi J, Jia J (2013) Abnormal event detection at 150 fps in matlab. In :Proc IEEE inter conf on computer vision, Sydney, pp2720–2727
Deepak K, Chandrakala S, Mohan CK (2020) Residual spatiotemporal autoencoder for unsupervised video anomaly detection. Signal Image Video P 15(4):1–8
Deshpande K, Punn NS, Sonbhadra SK, Agarwal S (2022) Anomaly detection in surveillance videos using transformer based attention model. arXiv preprint arXiv:2206.01524
Dongyue C, Wang P, YueL Zhang Y, Jia T (2020) Anomaly detection in surveillance video based on bidirectional prediction. Image Vis Comput 98:103915
Duman E, Erdem A (2019) Anomaly Detection in videos using optical flow and convolutional autoencoder. IEEE Access 7(99):183914–183923
ELHarrouss O, Moujahid D, Elkaitouni SE, Tairi H (2015) Moving objects detection based on thresholding operations for video surveillance systems. IEEE/ACS 12th inter conf compu syst appli (AICCSA) IEEE 1-5
Fuqiang Z, Wang L, Li Z, Zuo W, Tan H (2020) Unsupervised learning approach for abnormal event detection in surveillance video by hybrid autoencoder. Neural Process Lett 52(2):961–975
Guha P, Biswas A, Mukerjee A, Sateesh P, Venkatesh KS (2006) Surveillance video mining. Proc visual inform Eng IEEE. https://doi.org/10.1049/CP:20060572
Hao Y, Li J, Wang N, Wang X, Gao X (2022) Spatiotemporal consistency-enhanced network for video anomaly detection. Pattern Recognit 121
Hui X-f, Wu Y-j (2012) Research on simple moving average trading system based on SVM. Proc 2012 Inter Conf Man Sci & Eng 19th Annual Conf Proc 1393–1397
Kai-Wen C, Chen Y-T, Fang W-H (2016) An efficient subsequence search for video anomaly detection and localization. Multimed Tools Appl 75(22):15101–15122
Ke X, Jiang X, Sun T (2018) An intra-frame classification network for video Anomaly Detection and localization. Proc of 11th inter congress on image and signal process, BioMedical Eng and inform (CISP-BMEI) 1-6
Khan M, Hussain T, Tanveer M, Sannino G, de Albuquerque VHC (2019) Cost-effective video summarization using deep CNN with hierarchical weighted fusion for IoT surveillance networks. IEEE Internet Things 7(5):4455-4463
Kratz L, Nishino K (2009) Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. Proc Cvpr IEEE 1446-1453
Liu S, Liu D, Srivastava G, Połap D, Woźniak M (2020) Overview of correlation filter based algorithms in object tracking. Complex Intell Syst 7(3)
Mahadevan V, Li W, Bhalodia V, Vasconcelos N (2010) Anomaly detection in crowded scenes. In: Proceedings of IEEE Comput Soc Conf 1975-1981
Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61
Murugesan M, Thilagamani S (2020) Efficient anomaly detection in surveillance videos based on multi layer perception recurrent neural network. Microprocess Microsyst 79:103303
Pawar K, Attar V (2022) Deep learning model based on cascaded autoencoders and one-class learning for detection and localization of anomalies from surveillance videos. IET Biometrics
Peter T, Sebastian T, Doretto G, Krahnstoever N, Rittscher J, Yu T (2008) Unified crowd segmentation. European conf comput vision 691–704
Qi X, Ji G, Hu Z (n.d.) Retraining Generative Adversarial Auto-encoder for Video Anomaly Detection, Available at SSRN 4273563
Sameema T, Farooq H, Jaleel A, Wasif SM (2021) Anomaly detection with particle filtering for online video surveillance. IEEE Access 9:19457–19468
Shandong W, Moore BE, Shah M (2010) Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes. 2010 IEEE computer society conf computer vision pattern recog conf 2054–2060
ShanghaiTech Campus dataset, https://svip-lab.github.io/dataset/campus_dataset.html. Accessed Sept 2021
Sharma H, Hazrati G, Bansal JC (2018) Spider monkey optimization algorithm. Evol Swarm Intel Algorithms 779:43–59
Tan X, Zhang C, Zha H (2015) Learning to detect anomalies in surveillance video. IEEE Signal Process Lett 22(9):1477–1481
UCSD Anomaly Detection Dataset, http://www.svcl.ucsd.edu/projects/anomaly/dataset.html#:~:text=UCSD%20Anomaly%20Detection%20Dataset&text=The%20UCSD%20Anomaly%20Detection%20Dataset,the%20video%20contains%20only%20pedestrians. Accessed April 2021
Waseem U, Ullah A, Haq IU, Muhammad K, Sajjad M, Baik SW (2020) CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks. Multimed Tools Appl 80(11):1–17
Xinfeng Z, Yang S, Zhang J, Zhang W (2020) Video anomaly detection and localization using motion-field shape description and homogeneity testing. Pattern Recog 105:107394
Yu B, Liu Y, Sun Q (2017) A content-adaptively sparse reconstruction method for abnormal events Detection with low-rank property. IEEE Trans Syst Man Cybern Syst 47(4):704–716
Yunzuo Z, Zhang S, Guo Y (2019) Research on the key-frame extraction of surveillance video based on motion velocity. Pro IEEE inter conf signal, inform data process (ICSIDP) IEEE 1-3
Zhao Y, Deng B, Shen C, Liu Y, Lu H, Hua X-S (2017) Spatio-temporal autoencoder for video anomaly detection. Pro 25th ACM int conf Mult 1933-1941
Zhiguo W, Yang Z, Zhang Y-J (2020) A promotion method for generation error-based video anomaly detection. Pattern Recogn Lett 140:88–94