REVIEW OF TECHNOLOGIES AND USES OF VIDEO SURVEILLANCE
Keywords:
IVA (Intelligent Video Analytics), OD (Object Detection), OT (Object Tracking), MD (Motion Detection), DL (Deep Learning), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), YOLO (You Only Look Once), VMS (Video Management System), FR (Facial Recognition), AR (Activity Recognition), AD (Anomaly Detection), SF (Sensor Fusion), CC (Cloud Computing), EC (Edge Computing), SC (Smart Cities), RT (Real-Time), SP (Security and Privacy).Abstract
Modern security and monitoring systems now mostly depend on video surveillance. It covers a broad spectrum of technologies and uses, therefore greatly improving operational effectiveness and safety in many different fields. Thanks to developments in computer vision, artificial intelligence, and networking, video surveillance has advanced impressively from its early use in sensitive surroundings to its general presence in public spaces (Ardabili et al., 2022; Rezaei et al., 2021). Beyond only capturing visual data, video surveillance's main goal is intelligent analysis of image sequences to identify and track things, so helping to comprehend and interpret their activity (Ko, 2011). Advanced algorithms built into modern systems enable them to quickly identify and respond to any hazards or odd events by automatically detecting, classifying items, and spotting anomalies (Alhaidari et al., 2019; Civelek & Yaz, 2016). Security, traffic monitoring, retail analysis, and industrial automation (Patrikar & Parate, 2022) are just a few of the several domains these systems find use in. Furthermore, by providing a multimodal monitoring and anomaly detection (Mãâ¼Ller et al., 2021) integration of video surveillance with other sensor technologies such as sound sensors improves capabilities. Furthermore made possible by the development of cloud-based video surveillance systems is remote access and management of video data, which facilitates real-time and historical analysis from anywhere with an internet connection.
Modern security and monitoring systems now revolve around video surveillance as absolutely essential component. Driven by developments in computer vision, artificial intelligence (AI), and networking, modern surveillance technologies go from simple video recording tools to advanced intelligent systems. This study investigates the technical development, present capabilities, and several uses of video surveillance systems, so underlining their increasing importance in improving operational efficiency and safety in several fields. It also looks at the development of cloud-based solutions as major field innovations and the integration of multimodal sensors.
Downloads
References
Alhaidari, F., Alshaibani, M., & Altowaijri, S. (2019). Object detection and tracking using computer vision for video surveillance. Procedia Computer Science, 163, 252–259.
Ardabili, S. F., Mosavi, A., & Várkonyi-Kóczy, A. R. (2022). Smart surveillance: AI-based anomaly detection and situation awareness. Sensors, 22(3), 1120.
Civelek, T., & Yazıcı, C. (2016). Video analytics in intelligent video surveillance systems. Journal of Applied Research and Technology, 14(2), 100–109.
Ko, T. (2011). A survey on behavior analysis in video surveillance for homeland security applications. Proceedings of the 2011 International Conference on Systems, Man, and Cybernetics, 1817–1822.
Müller, M., Göpfert, T., & Gritzner, S. (2021). Fusion of acoustic and visual data in multimodal surveillance systems. IEEE Transactions on Multimedia, 23, 273–283.
Patrikar, R. M., & Parate, D. M. (2022). Applications of AI-enabled video surveillance in industrial environments. International Journal of Industrial Engineering and Management, 13(1), 44–53.
Rezaei, M., & Azarmi, M. (2021). Deep learning for intelligent video surveillance: A review. Artificial Intelligence Review, 54, 363–394.
Paper: Ren, Y., Chua, C.-S., & Ho, Y.-K. (2003). Motion detection with nonstationary background. Machine Vision and Applications, 13(6), 332–343. LinkSpringerLink+1ACM Digital Library+1
Paper: Horn, B. K. P., & Schunck, B. G. (1981). Determining optical flow. Artificial Intelligence, 17(1–3), 185–203. Link
Paper: Pratama, D. I., Sari, I. P., & Sari, L. O. (2017). Comparison of background subtraction, sobel, adaptive motion detection, frame differences, and accumulative differences images on motion detection
Paper: Yu, R., Wang, H., & Davis, L. S. (2018). ReMotENet: Efficient relevant motion event detection for large-scale home surveillance videos. arXiv preprint arXiv:1801.02031. Linkarxiv.org
Paper: O'Carroll, D. C., & Brinkworth, R. S. (2009). Secret math of fly eyes could overhaul robot vision. Wired. Linkwired.com
Paper: Qi, Q., Yu, X., Lei, P., et al. (2023). Background subtraction via regional multi-feature-frequency model in complex scenes. Soft Computing, 27, 15305–15318. LinkSpringerLink
Paper: Lu, Y., Wang, Q., Ma, S., et al. (2023). TransFlow: Transformer as Flow Learner. LinkarXiv
Paper: Wang, P., Zeng, F., & Qian, Y. (2023). A Survey on Deep Learning-based Spatio-temporal Action Detection. LinkarXiv
Paper: Colonnier, F., Seeralan, A., & Zhu, L. (2023). Event-Based Visual Sensing for Human Motion Detection and Classification at Various Distances. In: Wang, H., et al. (Eds.), Image and Video Technology. Springer, Cham.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 https://creativecommons.org/licenses/by-nc-nd/4.0/
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
