Exécution de notre outil de synthèse sur un nouvel article

Vérifiez l’article ci-dessous, puis lancez sa synthèse.


Student Classroom Behavior Recognition Based on Improved YOLOv7

Chunling Li (Xinjiang Normal University), Cheng Peng (Xinjiang Normal University)

International Conference on Informatics Education and Computer Technology Applications (IECA)
DOI: 10.1145/3732801.3732815 (Computer Science)
Licence : CC BY

Résumé : The recognition of students' classroom behavior by artificial intelligence and deep learning can be used as an auxiliary means to improve teaching quality. In the real classroom scene, due to the background clutter, crowded scene and object occlusion and other problems, There are many challenges in behavior recognition. To solve these problems, This paper proposes an improved model based on YOLOv7. It is used to identify students' classroom behavior in real classroom scenes. The improved model incorporates three CBAM attention modules into the original structure of YOLOv7. To obtain additional local information about the image during training and ensure the recognition accuracy. In order to accurately locate the detection target, Focal-EIoU Loss was introduced to replace CIoU to improve and optimize the comprehensive performance of students' classroom behavior detection. Finally, experiments are conducted on real student classroom data sets.the experiment result shows that the accuracy of the improved YOLOv7+CBAM+Focal-EIoU Loss model was improved by 3.81%, the recall rate rose 0.44%.At the same time, the mAP value of 91.77% is obtained, which is 1.34% higher than the original YOLOv7 model. The improved model can be applied to identify students' classroom behavior, monitor and analyze students' behavior in real time, and provide teachers with immediate feedback, thus improving teaching quality and classroom interaction effect.

Publié le 17 Jan. 2025