%0 Journal Article
%T 一种基于深度学习的课堂学生学习状态研究<br>A Study on the Learning State of Classroom Students Based on Deep Learning
%A 刘秋会
%A 梁明秀
%A 王林
%J Computer Science and Application
%P 2339-2345
%@ 2161-881X
%D 2020
%I Hans Publishing
%R 10.12677/CSA.2020.1012247
%X <div style=\"text-align:justify;\">
	<span style=\"font-size:14px;\">为了对学生课堂学习情况及教师授课情况进行客观评价，需要掌握学生在课堂上的学习状态，随着计算机视觉技术的发展，对学生课堂学生状态的分析成为可能。本文采用深度学习网络yolov3与dropblock结合对教室监控视频进行分析，检测学生在老师上课时的听课状态，实现对学生在课堂上是否专心听讲的学习状态检测。实验结果表明，通过建议方法得到的学生学习状态与实际人工观察具有很好的吻合度。<br />
In order to objectively evaluate students’ classroom learning and teachers’ teaching, it is necessary to master students’ learning status in class. With the development of computer vision technology, it is possible to analyze students’ classroom learning status. In this paper, the deep learning network yolov3 is combined with dropblock to analyze classroom surveillance video, detect the state of students listening to teachers in class, and realize the learning state detection of whether students are paying attention in class. The experimental results show that the students’ learning status obtained by the proposed method is in good agreement with the actual artificial observation.</span> 
</div>
%K 深度学习，课堂学习状态检测，Yolov3，Dropblock<br>Deep Learning
%K Classroom Learning Status Detection
%K Yolov3
%K Dropblock
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=39404