基于改进YOWO算法的学生课堂行为识别  

Classroom Behavior Recognition of Students Based on Improved YOWO Algorithm

作　　者：徐鑫磊 张景异 XU Xin-Lei;ZHANG Jing-Yi(School of Automation and Electrical Engineering,Shenyang Ligong University,Shenyang 110159,China)

机构地区：[1]沈阳理工大学自动化与电气工程学院,沈阳110159

出　　处：《计算机系统应用》2024年第4期113-122,共10页Computer Systems & Applications

摘　　要：当前,大部分的学生课堂行为识别工作主要基于单帧图像进行,忽略了行为的连贯性,因此不能充分利用视频信息来对学生的课堂行为进行准确刻画.所以,本文提出一种改进的YOWO算法模型,有效利用视频信息对学生课堂行为进行识别.首先,本文采集某高校真实课堂教学中的授课录像,制作出包含5类学生课堂行为的AVA格式视频数据集;其次,采用时移模块TSM(temporal shift module),用来增强模型获取时间上下文信息的能力;最后,采用非局部操作模块non-local来提高模型提取关键位置信息的能力.实验结果表明,通过对YOWO模型的优化,使得网络的识别性能更佳.在学生课堂行为数据集上,改进后的算法的mAP值为95.7%,相较于原YOWO算法在mAP值上提高了4.6%;模型参数量为81.97×10^(6),计算量为22.6 GFLOPs,参数量和计算量分别降低32.3%和9.6%;检测速度为24.03 f/s,提升了约3 f/s.At present,since the recognition of most students’classroom behavior is mainly based on a single frame image and ignores behavior coherence,video information cannot be made full use of to accurately depict students’classroom behavior.Therefore,this study proposes an improved YOWO algorithm model to effectively employ video information to identify students’classroom behavior.First,this paper collects teaching videos from real classroom teaching in a university and produces an AVA format video dataset containing five types of students’classroom behavior.Second,the temporal shift module(TSM)is adopted to enhance the ability of this model to obtain time context information.Finally,a non-local operation module is utilized to improve the ability of the model to extract key location information.The experimental results show that by optimizing the YOWO model,the recognition performance of the network is better.In the classroom behavior dataset,the mAP value of the improved algorithm is 95.7%,4.6%higher than that of the original YOWO algorithm.The parameter number in the model is reduced by 32.3%at 81.97×10^(6)and the calculation amount is decreased by 9.6%at 22.6 GFLOPs.The detection speed is 24.03 f/s,an increase of about 3 f/s.

关 键 词：YOWO算法 TSM NON-LOCAL 学生课堂行为 行为识别 注意力机制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] G434[自动化与计算机技术—计算机科学与技术]