Research on Intelligent Teaching Mode Based on Classroom Behavior Monitoring of Body Motion

Abstract

Objective: Classroom behavior detection is of great significance in the field of education, as it can assess students’ participation and focus. Methods: This paper introduces a novel classroom behavior detection method based on PP-YOLOv2. Leveraging computer vision and deep learning, the proposed approach involves the collection and annotation of student sample datasets, accompanied by thorough data preprocessing. The utilization of the Mish Activation function enhances the model’s learning ability and improves the accuracy of behavior detection. Results: This study is of great significance for real-time monitoring, enabling the evaluation of student behavior to improve teaching effectiveness and promote personalized learning. The experimental results show that this method exhibits good performance in classroom environments, providing educators with an efficient and accurate tool for behavior detection. Conclusion: Further research endeavors can expand the application scope and optimize algorithms to enhance performance. In summary, the proposed method shows promise in revolutionizing classroom behavior detection, offering a more efficient and accurate means of assessing and improving students’ educational experiences.