International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Recognizing Anomalies in Real Time Using CCTV and Neural Networks

Author : K V Sandeep ¹ Manoj D ² P Dhanusha ³ Deepthi S Shetty R ⁴

Date of Publication :19th October 2021

Abstract: There has been an upsurge in the amount of unsettling and annoying events occurring recently. As a result, safety has been prioritized. To assure the security of the public, public spaces such as stores, highways, and banks are increasingly outfitted with CCTV. Following that, these interruptions need a precise installation of the application on a computer. As human monitoring of these surveillance cameras is impractical. It needs personnel and continuous monitoring to determine if tasks chosen are unpopular or questionable. As a result of this degradation, the necessity to improve the precision of this procedure becomes apparent. Additionally, it is necessary to identify which frames and sections of the video include odd work, which aids in rapidly determining whether an uncommon conduct is unusual or suspicious. As a result, we use the Automating Threat Detection System's in-depth learning capabilities to minimize time and effort waste. Its aim is to automatically identify and filter out indications of violence and aggression in real time. We want to discover and distinguish high flow rates in the framework by using a number of in-depth assessments (CNN and RNN). From there, we may notify you of the identification of a potentially dangerous scenario, which signals suspicious behaviour on occasion.

Reference :

1. Jie Xu, “A deep learning approach to building an intelligent video surveillance system” 2020.
2. Virender Singh, et.al. , “Real-Time Anomaly Recognition Through CCTV Using Neural Networks” 2020.
3. Raksha S, et.al. , “Anomalous Human Activity Recognition in Surveillance Videos” 2019.
4. Yang Liu and Mirella Lapata, “Text Summarization with Pretrained Encoders”
5. Waqas Sultani, et.al. , “Real-world Anomaly Detection in Surveillance Videos”
6. Parth Mehta, et.al. , “Fire and Gun Violence based Anomaly Detection System Using Deep Neural Networks” 2020.
7. Rashmika Nawaratne, et.al. , “Spatiotemporal Anomaly Detection using Deep Learning for Realtime Video Surveillance” 2019.
8. O.S Amosov, et.al. , “Using the Ensemble of Deep Neural Networks for Normal and Abnormal Situations Detection and Recognition in the Continuous Video Stream of the Security System” 2019.
9. Charuni Rajapakshe, et.al, “Using CNNs RNNs and Machine Learning Algorithms for Real-time Crime Prediction” 2019. [10] Komal V Shivthare, et.al. , “Suspicious Activity Detection Network For Video Surveillance Using Machine Learning”, 2021.
10. D Zh Satybaldina, et.al. ,” Development of an algorithm for abnormal human behavior detection in intelligent video surveillance system”, 2020.
11. Sultani W, Chen C, Shah M. Real-world Anomaly Detection in Surveillance Videos. Arxiv 2018; [Online document]; URL: https://arxiv.org/abs/1801.04264 (accessed: 15.03.2018).
12. Yuan Gao, Hong Liu, Xiaohu Sun, Can Wang. Violence detection using Oriented VIolent Flows. In ResearchGate, 2016.
13. R. Kanehisa and A. Neto, “Firearm Detection using Convolutional Neural Networks,” Proceedings of the 11th International Conference on Agents and Artificial Intelligence, vol.2, pp. 707–714, 2019.
14. M. Sabokrou, M. Fathy, M. Hoseini, and R. Klette, “Real-time anomaly detection and localization in crowded scenes,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2015.
15. J. R. Medel and A. Savakis, “Anomaly detection in video using predictive convolutional long short-term memory networks,” arXiv preprint arXiv:1612.00390, 2016.
16. Qiu, Z.; Yao, T.; Ngo, C.W.; Tian, X.; Mei, T. Learning spatio-temporal representation with local and global diffusion. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 15–21 June 2019; pp. 12056–12065.
17. Sreenu, G.; Durai, M.A.S. Intelligent video surveillance: A review through deep learning techniques for crowd analysis. J. Big Data 2019, 6, 48
18. Satybaldina D., Kalymova G. and Glazyrina N. 2020 Application Development for Hand Gestures Recognition with Using the Depth Camera Communications in Computer and Information Science (Springer, Cham) V.1243 pp. 55-67
19. Rabiee H et al. 2018 Detection and localization of crowd behavior using a novel tracklet-based model International Journal of Machine Learning and Cybernetics (Springer Nature)V. 9, â„–. 12 pp.1999- 2010
20. Zhao L, He Z, Cao W and Zhao D 2018 Real-time moving object segmentation and classification from HEVC compressed surveillance video IEEE Trans. Circuits Syst. Video Technol. (IEEE) vol. 28, no. 6 pp. 1346–1357.