SCB-YOLO: a lightweight adaptive attention-enhanced network for student behavior detection in complex classroom settings

Student classroom behavior serves as a key indicator for evaluating teaching effectiveness and learning status, and its automated detection is crucial for the advancement of Smart Education. Addressing the limitations of existing classroom behavior detection methods—such as poor real-time performance, high computational complexity, insufficient accuracy in complex classroom settings, and weak differentiation of subtle behaviors—this paper proposes the SCB-YOLO algorithm specifically designed for student classroom behavior detection. Building upon the YOLOv11n framework, this algorithm first incorporates a lightweight Global Edge Information Transfer (GEIT) module to enhance the model’s ability to extract pose contour features such as hand-raising and writing. It then integrates a MANet_Star feature fusion module to improve multi-scale feature fusion efficiency. Experiments on the elementary school scene subset (SCB-Dataset3-S) of the public student classroom behavior dataset SCB-Dataset3 demonstrate that compared to the baseline YOLOv11n, the SCB-YOLO model achieves a 2.6% improvement in [email protected] while maintaining comparable detection speed. Compared to advanced lightweight models like YOLOv12n and YOLOv10n, SCB-YOLO also demonstrates higher detection accuracy and overall superiority in complex classroom scenarios. This indicates that the SCB-YOLO algorithm can effectively address challenges in real teaching environments and possesses strong application potential.