Open Access
Subscription Access
Student Surveillance System: An AI-Powered Approach for Campus Monitoring
Abstract
Educational institutions should implement a strong monitoring mechanism to ensure that their dress code and campus movement orders are adhered to. Modern influence technologies such as the RetinaFace algorithm for face detec- tion, face recognition through Dlib, ID card detection through YOLOv5, and shirt tuck analysis using a ResNet-based model play a critical role in system consideration. Alongside this, student tracking would be done using the SORT algorithm; abandonment comes from real-time object detection data to map student movement paths. It will continuously monitor and help identify violations of policies such as improper dress codes (ID cards missing, untucked shirts).In the event of a policy violation, the student receives an automated notification along with the faculty concerned. In addition, analysis of movement activity can trace the path taken by students for better supervision and safety on campus. The proposed approach would appear much more competent than the others, owing to a minimum of manual intervention. The experimental conclusions showed great strength in student recognition and detection of policy violations, making this approach flexible and viable for schools and education sites. This is achieved through supplementary automation of supervision, and hence its solution with logic drawn through artificial intelligence.
References
Ahmed Rimaz Faizabadi et al. “Efficient Region of Interest Based Metric Learning for Effective Open World Deep Face Recognition Applications”. In: IEEE Access 10 (2022), pp. 76168–76184. doi: 10.1109/ACCESS.2022.3192520.
Hyun-Bin Kim et al. “Surveillance System for Real-Time High-Precision Recognition of Criminal Faces From Wild Videos”. In: IEEE Access 11 (2023), pp. 56066–56082. doi: 10.1109/ACCESS.2023.3282451.
Tuan T. Nguyen et al. “Multi-Vehicle Multi-Camera Tracking With Graph-Based Tracklet Features”. In: IEEE Transactions on Multimedia 26 (2024), pp. 972–983. doi: 10.1109/TMM.2023.3274369.
Gyana Ranjana Panigrahi et al. “Enhancing Security in Real-Time Video Surveillance: A Deep Learning-Based Remedial Approach for Adversar- ial Attack Mitigation”. In: IEEE Access 12 (2024), pp. 88913–88926. doi: 10.1109/ACCESS.2024.3418614.
Muhammad Sohail et al. “Deep Learning Based Multi Pose Human Face Matching System”. In: IEEE Access 12 (2024), pp. 26046–26061. doi: 10.1109/ACCESS.2024.3366451.
W. E. Villegas, S. Sa´nchez-Viteri and S. Luja´n-Mora, ”Real-Time Recognition and Tracking in Urban Spaces Through Deep Learning: A Case Study,” in IEEE Access, vol. 12, pp. 95599-95612, 2024, doi: 10.1109/ACCESS.2024.3426295.
D. A. H. Ollachica, B. K. A. Asante and H. Imamura, ”Autonomous UAV Implementation for Facial Recognition and Tracking in GPS- Denied Environments,” in IEEE Access, vol. 12, pp. 119464-119487, 2024, doi: 10.1109/ACCESS.2024.3447899.
G. Y. Shien, K. Shanmugam and M. E. Rana, ”Automated Face Mask Detection using Artificial Intelligence and Video Surveillance Management,” 2023 15th International Conference on Developments in eSystems Engineering (DeSE), Baghdad & Anbar, Iraq, 2023, pp. 233- 236, doi: 10.1109/DeSE58274.2023.10099878.
A. S. Renugadevi, R. Jayavadivel, B. Ananthi, M. Ramesh, P. Palanisamy and M. V. Praveen, ”Real Time Dress Code Surveillance of College Students Using Deep Learning Techniques,” 2024 15th International Conference on Computing Communication and Networking Technolo- gies (ICCCNT), Kamand, India, 2024, pp. 1-6, doi: 10.1109/ICC- CNT61001.2024.10723331.
H. -T. Ngo, M. -K. Phan, N. -L. Le and T. -K. Cao, ”YOLOv3
Tiny-Based Human Detection and Tracking using Vitis AI and VVAS on FPGA,” 2024 5th International Conference on Communications, Information, Electronic and Energy Systems (CIEES), Veliko Tarnovo, Bulgaria, 2024, pp. 1-6, doi: 10.1109/CIEES62939.2024.10811271.
Refbacks
- There are currently no refbacks.