AI-Based Suspicious Activity Detection Using Camera with Clip Extraction and Transmission

The project on Suspicious Activity Detection using Camera with Clip Extraction and Transmission successfully demonstrates an intelligent surveillance system capable of identifying abnormal human activities such as fights or thefts in real time. Using computer vision and machine learning techniques, the system detects suspicious motion patterns from live camera footages and immediately extracts the corresponding video clip for evidence storage or further analysis. The extracted clips are automatically transmitted to a remote server or cloud platform for monitoring and alert generation. The experimental results show that the model effectively distinguishes between normal and suspicious activities with reliable accuracy and consistent processing performance.

[1] Ajeet Sunil, Manav Hiren Sheth, Shreyas E, Mohana, “Usual and Unusual Human Activity Recognition in Video using Deep Learning and Artificial Intelligence for Security Applications”, 2021 Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT) | 978-1-6654-1480-7/21/$31.00 ©2021 IEEE | DOI: 10.1109/ICECCT52121.2021.9616791.   [2] Bathula Prasanna Kumar, Satra Sala Jyotsnika, Vuyyuru Lakshmi Sruthi, Regalla Sumana, Shaik Hussanibi, “AI-driven security: real time women’s protection via IOT-based guardian device”, International Journal of Engineering Science and Advanced Technology (IJESAT) Vol 25 Issue 03, MAR, 2025.   [3] Dr. Nookala Venu, Dr. A. Arun Kumar, “Suspicious Activity Tracking Artificial Intelligence Camera”, Volume 29, Issue 10, 2023.   [4] I. Subha, P. Narmadha, S. Nivedha, T. Sethukarasi, “Real-Time Suspicious Human Action Recognition from Surveillance Videos for Resource-Constrained Devices”, 2020 Journal Computational and Theoretical Nanoscience Vol. 17, 3790–3797.   [5] Ogochukwu Susan Ndibe, “AI-Driven Forensic Systems for Real-Time Anomaly Detection and Threat Mitigation in Cybersecurity Infrastructures”, International Journal of Advance Research Publication and Reviews, Vol 2, no 5, pp 389-411, May 2025.   [6] Akshay Vaja, Dr. Dhaval Raghav Bhai Kathiriya, “Suspicious Activity Detection using AI under Surveillance Video”, Advanced International Journal of Multidisciplinary Research E-ISSN: XXXX-XXXX [email protected] Volume 1, Issue 1, July – August 2023.   [7] J. Arunnehru, Divya Midhunchakkaravarthy, S. Hemalatha, “Intelligent Video Surveillance Systems for Real-Time Suspicious Activity Detection Using AI and Computer Vision: A Study”, SGS Engineering & Sciences, VOL. 1 NO .1 (2025): LGPR.   [8] AasmaAas , Hamza Naveed , Sarah Khaleel, Junaid Asghar, Talia Noureen  , Zubda Khanum , “Efficient and Sustainable Video Surveillance Using CNN-LSTM Model for Suspicious Activity Detection”, VFAST Transactions on Software Engineering VFAST Transactions on Software Engineering Volume 13, Issue 1, 2025 https://vfast.org/journals/index.php/VTSE@ 2025, ISSN(e): 2309-3978, ISSN(p): 2411-6246 Volume 13, Number 1, January-March 2025.   [9] Monji Mohamed Zaidi Ahmadalmadhor, Gabriel Avelino Sampedro, Shtwai Alsubai, Abdullah Al Hejaili, Michal Gregus, Sidra Abbas, “Suspicious Human Activity Recognition From Surveillance Videos Using Deep Learning”.   [10] Vedant Saikhede, Kiran Shende, Yuvraj Darekar, Hemant Thorat Prof. Snehal. S. Shinde, “Deep Learning Approach for Suspicious Activity Detection from Surveillance Video”, International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 10 Issue: 12 | Dec 2023.