Research on Monitoring Teaching Activities Based on Image Recognition in Educational Management Informatization Construction of Colleges and Universities

Abstract

Teaching activity monitoring is an important part of the development of educational management informationization in colleges and universities. In this paper, we initially integrate the FDRL model with the self-attention mechanism to create the IMEDRL model, a tool for identifying the micro-expression categories of students during teaching activities. Then, the YOLOv5 model is added with the CA attention mechanism, and the loss function is replaced from CIOU to SIOU to get the IM-YOLOv5 model, which is used to detect the behavioral categories of students in teaching activities. Finally, a teaching activity monitoring system was designed based on these two models and used in actual teaching activity monitoring to explore the application effect of the models in the system. The IMEDRL model achieved an average recognition rate of 95.2% and 91.4% on the two public datasets, CK+ and Oulu-CASIA, respectively. The training and testing convergence on the teaching activity video dataset was superior, and the recognition accuracy rate reached 87.48%, demonstrating the model’s strong practical value. IM-YOLOv5 compared to YOLOv5, the FPS is basically the same, the number of parameters only increases by 8.72%, and the mAP0.5 and mAP0.5:0.95 improve by 0.99% and 1.65%, respectively. Among the 16 indicators of the 8 behaviors, 14 of the 8 behaviors of IM-YOLOv5 are higher than those of YOLOv5, confirming the feasibility of this study to improve YOLOv5. The monitoring system of teaching activities designed in this paper has a strong practicality, which is conducive to promoting informationization in education management in colleges and universities.