Automated Alarm System for Student Anomalous Action Detection in Examination Based on Video Surveillance Using ML Techniques
Pushpa B. Patil, Suvarna Laxmikant Kattimani, Suman M. Hugar · 2022
Determining students' anomalous behavior in the examination room is an important issue to consider. Video surveillance is one of the foremost machinery for identifying the aberrant behavior of the students in test room. This method performs best when it is used with a compact camera and focuses on every student. Monitoring students during exams is a tedious task, with rapid development of technology there is a need for a system that effectively performs the function of the invigilator during the exams i.e., to monitor students for misconduct during exams. The system is designed to detect unique patterns for actions of concern in real-time, such as passing of notes, using cellphones & earphones etc., during exam hours. This detection is based on YOLOv3 object detection algorithm. The paper explores ways to discover the unusual behavior of the students in a test room that helps to avoid cheating in the test room and helps to reduce the duty of invigilator and provide evidence of cheat with an alarm sound.