Student Classroom Behavior Detection based on Improved YOLOv7

TL;DR

This paper introduces an improved YOLOv7-based method for detecting student classroom behaviors, achieving higher accuracy by incorporating attention modules and a new dataset, thereby aiding classroom analysis.

Contribution

The paper presents a novel dataset and enhances YOLOv7 with attention mechanisms and Wise-IoU for improved behavior detection in crowded classrooms.

Findings

Achieved 79% mAP@0.5, a 1.8% improvement over previous methods.

Created the SCB-Dataset with 18.4k labels and 4.2k images.

Enhanced detection accuracy in crowded scenes.

Abstract

Accurately detecting student behavior in classroom videos can aid in analyzing their classroom performance and improving teaching effectiveness. However, the current accuracy rate in behavior detection is low. To address this challenge, we propose the Student Classroom Behavior Detection method, based on improved YOLOv7. First, we created the Student Classroom Behavior dataset (SCB-Dataset), which includes 18.4k labels and 4.2k images, covering three behaviors: hand raising, reading, and writing. To improve detection accuracy in crowded scenes, we integrated the biformer attention module and Wise-IoU into the YOLOv7 network. Finally, experiments were conducted on the SCB-Dataset, and the model achieved an mAP@0.5 of 79%, resulting in a 1.8% improvement over previous results. The SCB-Dataset and code are available for download at: https://github.com/Whiffe/SCB-dataset.