Student Behavior Detection in the Classroom Based on Improved YOLOv8

The main goal of studying students' classroom behavior is to comprehensively collect data on students' behavior in the classroom as a way to provide solid technical support for education and teaching quality assessment. Aiming at the problems of complex types of classroom student behaviors and weak timeliness of student behavior detection, this paper proposes an improved YOLOv8 detection method. First, the Shuffle Attention mechanism is added to the original network to enhance the model's ability to capture information from different locations. At the same time, the C2f module in the original network is replaced by the CSPHet module, which reduces the number of parameters and complexity of the model while maintaining the accuracy of the model. The experimental results show that the improved algorithm mAP is improved by 3% and GFLOPs are reduced by 20%, and the improved algorithm model is more in line with the requirements for edge computing devices.