Student classroom behavior identification method based on convolutional neural network
A convolutional neural network and recognition method technology, applied in the field of student classroom behavior recognition, can solve the problems of low manual labeling efficiency, easy misoperation, complex labeling operation logic, etc., and achieve the effect of great practical value and strong anti-interference ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0027] The present invention will be further described below in conjunction with the accompanying drawings.
[0028] like figure 1 As shown in the figure, it is a schematic flow chart of the student classroom behavior recognition method based on the convolutional neural network in the teaching field. Include the following steps:
[0029] Step (1), collect picture data and make your own database. The pictures are required to be class pictures in different classroom environments;
[0030] In step (2), the database collected in step (1) is sent to a behavior recognition network based on a convolutional neural network for a series of training to obtain a pre-trained model.
[0031] Step (3), use the obtained pre-training model to detect the student’s classroom video, detect which of the five behaviors of raising hands, listening to lectures, sleeping, answering, and writing, and generate corresponding borders (Box) and the corresponding behavior name.
[0032] like figure 2 ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


