一种基于深度学习的课堂学生学习状态研究
A Study on the Learning State of Classroom Students Based on Deep Learning
DOI: 10.12677/CSA.2020.1012247, PDF,  被引量   
作者: 刘秋会, 梁明秀, 王 林：贵州民族大学数据科学与信息工程学院，贵州 贵阳
关键词: 深度学习；课堂学习状态检测；Yolov3；Dropblock；Deep Learning； Classroom Learning Status Detection； Yolov3； Dropblock
摘要: 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。
Abstract: 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.
文章引用：刘秋会, 梁明秀, 王林. 一种基于深度学习的课堂学生学习状态研究[J]. 计算机科学与应用, 2020, 10(12): 2339-2345. https://doi.org/10.12677/CSA.2020.1012247

参考文献

[1] 唐康, 先强, 李明勇. 基于人脸检测的大学课堂关注度研究[J]. 重庆师范大学学报(自然科学版), 2019, 36(5): 123.
[2] 郭秀兰, 赵佳敏. 本科课堂教学“出勤率、抬头率、满意率”的调查报告[J]. 改革与开放, 2016(19): 108-110.
[3] 左国才, 吴小平, 苏秀芝, 等. 基于CNN人脸识别模型的大学生课堂行为分析研究[J]. 智能计算机与应用, 2019, 9(6): 107-110.
[4] 屈梁浩. 基于深度学习的学生课堂疲劳状态的分析与研究[D]: [硕士学位论文]. 重庆: 重庆师范大学, 2019.
[5] Krizhevsky, A., Sutskever, I. and Hinton, G. (2012) ImageNet Classification with Deep Convolutional Neural Networks. 2012 NIPS, Lake Tahoe, NV, December 2012, 1097-1105.
[6] Szegedy, C., Liu, W., Jia, Y., et al. (2014) Going Deeper with Convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 1-9. [Google Scholar] [CrossRef] 
[7] He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. IEEE Conference on Computer Vision & Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[8] Girshick, R. (2015) Fast R-CNN. IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[9] Xie, S., Girshick, R., Dollár, P., et al. (2017) Aggregated Residual Transformations for Deep Neural Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 5987-5995. [Google Scholar] [CrossRef] 
[10] Liu, W., Anguelov, D., Erhan, D., et al. (2016) SSD: Single Shot MultiBox Detector. European Conference on Computer Vision, Amsterdam, 8-16 October 2016, 21-37. [Google Scholar] [CrossRef] 
[11] Redmon, J., Divvala, S., Girshick, R., et al. (2016) You Only Look Once: Unified, Real-Time Object Detection. IEEE Conference on Computer Vision & Pattern Recognition, Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[12] Redmon, J. and Farhadi, A. (2017) YOLO9000: Better, Faster, Stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 6517-6525. [Google Scholar] [CrossRef] 
[13] Redmon, J. and Farhadi, A. (2018) YOLOv3: An In-cremental Improvement.
[14] Yang, Z., Xu, W., Wang, Z., et al. (2019) Combining Yolov3-Tiny Model with Dropblock for Tiny-Face Detection. 2019 IEEE 19th International Conference on Communication Technology (ICCT) IEEE, Xi’an, 16-19 October 2019, 1673-1677. [Google Scholar] [CrossRef] 
[15] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R. (2014) Dropout: A Simple Way to Prevent Neural Networks from Overfitting. The Journal of Machine Learning Research, 15, 1929-1958.
[16] Ghiasi, G., Lin, T.-Y. and Le, Q.V. (2018) DropBlock: A Regularization Method for Convolutional Networks.