A Video-based Detector for Suspicious Activity in Examination with OpenPose
This addresses the need for scalable cheating prevention in academic institutions, though it is incremental as it applies existing methods to a specific domain.
The paper tackles the problem of cheating in exams by developing a video-based detector using OpenPose and CNN to identify students exchanging objects, achieving efficient and effective automated monitoring to replace impractical manual invigilation.
Examinations are a crucial part of the learning process, and academic institutions invest significant resources into maintaining their integrity by preventing cheating from students or facilitators. However, cheating has become rampant in examination setups, compromising their integrity. The traditional method of relying on invigilators to monitor every student is impractical and ineffective. To address this issue, there is a need to continuously record exam sessions to monitor students for suspicious activities. However, these recordings are often too lengthy for invigilators to analyze effectively, and fatigue may cause them to miss significant details. To widen the coverage, invigilators could use fixed overhead or wearable cameras. This paper introduces a framework that uses automation to analyze videos and detect suspicious activities during examinations efficiently and effectively. We utilized the OpenPose framework and Convolutional Neural Network (CNN) to identify students exchanging objects during exams. This detection system is vital in preventing cheating and promoting academic integrity, fairness, and quality education for institutions.