International Journal of Innovative Research in Computer and Communication Engineering

ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines

| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |


TITLE Automated Invigilation System for Physical Classrooms using CCTV Surveillance and Computer Vision
ABSTRACT The integrity of examinations in physical classrooms is paramount to the educational system. Traditional invigilation methods, relying solely on human supervision, are often prone to error due to fatigue and limited field of view. This paper proposes a robust ”Automated Invigilation System” that utilizes YOLOv8 architecture for multi-person detection and object recognition. Furthermore, it integrates a Head Pose Estimation algorithm to identify suspicious behaviors such as peeping. Experimental evaluation on a custom dataset demonstrates a mean Average Precision (mAP) of 94% with a real-time processing speed of 35 FPS, offering a scalable solution for academic institutions.
AUTHOR ISHANT BAGUL, PUSHKAR AHER, SANCHITA BARVE, YASH KSHIRSAGAR, RUSHIKESH PAWAR Student, Department of Computer Technology, SNJB’s S.H.H.J.B Polytechnic, Chandwad, India Lecturer, Department of Computer Technology, SNJB’s S.H.H.J.B Polytechnic, Chandwad, India
VOLUME 180
DOI DOI: 10.15680/IJIRCCE.2026.1401059
PDF pdf/59_Automated Invigilation System for Physical Classrooms using CCTV Surveillance and Computer Vision.pdf
KEYWORDS
References 1. Ishant B. Bagul et al., ”Automated Invigilation System,” 2026.
2. J. Redmon, ”You Only Look Once,” CVPR 2016.
3. G. Jocher, ”YOLO by Ultralytics,” 2023.
image
Copyright © IJIRCCE 2020.All right reserved