Student Engagement Assessment in Classrooms Using a Novel 3D Eye-Gaze Estimation and Evaluation Algorithm
Matthew Korban, Jonathan McGee, Peter A. Youngs, Scott T. Acton · 2024
Student attentiveness within the classroom can be assessed by observing student attention toward the teacher or whiteboard, which may be inferred through eye-gaze direction. This paper introduces a novel technique for evaluating student attentiveness by analyzing the direction of their eye gaze derived from their 3D skeletal pose in a reconstructed 3D environment. As for the contributions, the paper suggests a novel 3D head pose estimation algorithm that, unlike other works, does not need frontal face information. As a result, the method is highly effective in uncontrolled environments such as classrooms, where frontal face data is often unavailable. Moreover, a new algorithm was developed to evaluate student attentiveness based on 3D eye gaze information interpreted from the 3D head pose. The proposed method has been validated using a set of instructional videos collected at the University of Virginia.