Student behavior detection method based on target detection

Abstract

The invention relates to a student behavior detection method based on target detection, and the method comprises the following steps: S1, building a data set comprising student behavior information which comprises hand raising, standing and sleeping; S2, establishing a student behavior detection model, wherein the model is an improved Faster R-CNN model based on a residual network ResNet-101; S3,training the student behavior detection model based on an online hard sample mining method; S4, detecting a to-be-detected video by using the trained student behavior detection model to obtain a student behavior result, and visualizing the student behavior result; wherein the residual network ResNet-101 adopts a multi-layer feature fusion strategy and the fifth convolution stage of the residual network ResNet-101 includes multiple branches with different receptive field sizes.. Compared with the prior art, the method has the advantages of high precision and the like.

Description

technical field [0001] The invention relates to the field of behavior detection, in particular to a method for detecting student behavior based on target detection. Background technique [0002] Behavior detection is an important research topic in the field of artificial intelligence, and it is widely used in public security, human-computer interaction and other fields. Student behavior detection in classrooms and other scenarios is an important part of subsequent teaching analysis, which can effectively help schools improve teaching quality. Therefore, automatic detection of student behavior can greatly reduce the burden on teachers and provide continuous quality assessment for the teaching process. However, in the real classroom scene, there are problems such as low resolution, diverse behaviors of students, and severe occlusion. At the same time, there are big differences in camera shooting angles, shooting distances, and lighting conditions in different classrooms. Tr...

AI Technical Summary

Problems solved by technology

However, the above technologies all need to be calculated on high-resolution feature maps or pictures, which leads to the slow inference speed of such methods and it is difficult to achieve real-time detection; and simply fusing multi-scale features will affect the strong semantic information in the deep layer of the network. Damage the detection effect of large targets, the multi-scale training method requires longer training time, and the convergence speed is slower

Images