A Survey on Deep Learning Approach For Suspicious Activity Detection from Surveillance Video in Examination Hall

Computer Engineering

Surveillance-based monitoring of examination halls is crucial for maintaining academic integrity. Traditional invigilation methods face challenges in scalability, real-time detection, and automation. Recent advancements in deep learning and computer vision have led to the development of intelligent systems for detecting suspicious activities in examination environments. This survey paper provides a comprehensive review of existing research on automated examination monitoring systems, focusing on deep learning-based approaches. It explores various methodologies, datasets, architectures, and evaluation metrics used for suspicious activity detection. Additionally, the paper discusses the challenges, limitations, and future research directions in this domain. By analyzing state-of-the-art techniques, this survey aims to guide researchers in developing more efficient and accurate systems for ensuring fair examinations through automated surveillance.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.