Ankush Balaram Pawar, Gayatri Shitole, Sonali Naik, Rohan Patil, Yash Thakur | International Journal of Software Computing and Testing | Vol 10, Issue 01 | pp. 9-20 | ISSN: 2456-2351
Abstract
Intelligent video surveillance powered by deep learning represents a transformative paradigm in security and surveillance. This new approach uses the power of complex neural networks to revolutionize the analysis and management of video data. Through the seamless incorporation of deep learning technologies like convolutional neural networks (CNN) and recurrent neural networks (RNN) into observation systems, automated identification, tracking, and classification of objects can be accomplished, alleviating storage constraints on the inspection notebook. Technology is good at detecting anomalies, identifying unusual behavior or events, and even identifying people based on facial recognition. The result is a good method for security because it can alert authorities or security personnel to threats or crimes. Additionally, optimization provides rich data-driven insights that aid decision-making beyond security, such as improving customer sales or improving business processes. Currently, big data holds much of its importance and place in business and science. Video analysis is important for smoothing large data files. The main purpose of this article is to provide a brief overview of technology analysis activities. Our main goal is to use deep learning techniques to recognize regular activities in large groups of people, participants, and all kinds of needs. This video analysis can help us ensure security. Security, theft detection, brute force detection, etc. It can mean many things like. Human activity research is simply the process of investigating unusual (unusual) human activities. To do this, we must convert the video into frames; Making these frames helps us identify people and their activities. The system comprises two modules: one for product search and another for operation search. The object detection module detects whether an object is present or not. Once an object is detected, the next module checks if the activity is unexpected.
Keywords:Intelligent video surveillance, deep learning, convolutional neural networks (CNN), recurrent neural networks (RNN), automatic identification, tracking, classification of objects, anomalies detection, video analysis, regular activities recognition, theft detection
Keywords
recurrent neural networks (RNN), anomalies detection, classification of objects, convolutional neural networks (CNN), automatic identification, regular activities recognition, video analysis, tracking, theft detection, deep learning, Intelligent video surveillance
🔒 This is a subscription article
Full text is available to subscribers and institutional members. Please choose an option below to access it.
SubscribePurchase this articleInstitutional / Login accessReferences
- Sreenu GS, Durai S. Intelligent video surveillance: A review through deep learning techniques for crowd analysis. J Big Data. 2019 Dec;6(1):1–27.
- Shidik GF, Noersasongko E, Nugraha A, Andono PN, Jumanto J, Kusuma EJ. A systematic review of intelligence video surveillance: Trends, techniques, frameworks, and datasets. IEEE Access. 2019 Nov 25;7:170457–73. DOI: 10.1109/ACCESS.2019.2955387.
- Kardile N, Deshmukh R, Kalhapure V, Jaybhay D. Intelligent video surveillance system using deep learning. Int J Innov Technol Explor Eng. 2019;8(9):1719–22.
- Zahrawi M, Shaalan K. Improving video surveillance systems in banks using deep learning techniques. Sci Rep. 2023 May 16;13(1):7911. DOI: 10.1038/s41598-023-35190-9. PubMed: 37193787.
- Sarathy S, Manikandan J. Design and evaluation of a real-time character recognition system. 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Bangalore, India, 2018, pp. 519-525. DOI: 10.1109/ICACCI.2018.8554539.
- Pawar K, Attar V. Deep learning based detection and localization of road accidents from traffic surveillance videos. ICT Express. 2022 Sep;8(3):379–87. DOI: 10.1016/j.icte.2021.11.004.
- Huang C, Wu Z, Wen J, Xu Y, Jiang Q, Wang Y. Abnormal event detection using deep contrastive learning for intelligent video surveillance system. IEEE Trans Ind Inform. 2021 Oct 27;18(8):5171–9. DOI: 10.1109/TII.2021.3122801.
- Amrutha CV, Jyotsna C, Amudha J. Deep learning approach for suspicious activity detection from surveillance video. 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Bangalore, India, 2020, pp. 335-339. DOI: 10.1109/ICIMIA48430.2020.
- Antoniou A, Angelov P. A general purpose intelligent surveillance system for mobile devices using deep learning. 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada, 2016, pp. 2879-2886. DOI: 10.1109/IJCNN.2016.7727563.
- Gautam A, Singh S. Deep learning based object detection combined with internet of things for remote surveillance. Wirel Pers Commun. 2021 Jun;118(4):2121–40. DOI: 10.1007/s11277-021-08071-5.
- Team D. Deep surveillance with deep learning – Intelligent video surveillance project – DataFlair [online]. 2020. Available from: https://data-flair.training/blogs/deep-surveillance-with-deep-learning-intelligent-video-surveillance-project/.
- Avenue dataset for abnormal event detection [online]. 2024. Available from: https://www.cse.cuhk.hk/leojia/projects/detectabnormal/dataset.html.
How to cite this article
@article{PawarAB2024,
author = {Ankush Balaram Pawar and Gayatri Shitole and Sonali Naik and Rohan Patil and Yash Thakur},
title = {Intelligence Video Surveillance Using Deep Learning},
journal = {International Journal of Software Computing and Testing},
year = {2024},
volume = {10},
number = {01},
pages = {9--20},
issn = {2456-2351},
url = {https://journalspub.com/publication/uncategorized/article=6707}
}