Online Classroom Evaluation System Based on Multi-Reaction Estimation

TL;DR

This paper introduces an online classroom evaluation system that uses multi-reaction estimation from student camera feeds to assess participation and help teachers adjust lesson pacing in real-time.

Contribution

It presents a novel method combining head pose, hand pose, and facial expression recognition to evaluate student engagement during online classes.

Findings

System effectively classifies class quality into positive, neutral, and negative.

Enables teachers to adjust teaching content based on real-time student reactions.

Improves online teaching effectiveness through automated participation assessment.

Abstract

Compared with traditional face-to-face teaching, online learning is more convenient. However, during online classes, it is more difficult for teachers to observe all student reactions at the same time. Our system is designed to help teachers to adjust the speed of their lessons by detecting student reactions. In this study, we estimate student head pose, hand poses, and expressions through the camera, all these poses will be used as criteria for judging the student participation. After estimating, we proposed a method to evaluate classroom participation based on student head pose, hand poses, and facial expression recognition. The estimated result divides the class quality into positive, neutral, and negative, then, under the help of the system, teachers can rearrange the content of the class.