改进YOLOv8的学生课堂行为识别算法:DMS-YOLOv8  

Improved YOLOv8-BasedAlgorithm for Classroom Behavior Recognition of Students:DMS-YOLOv8

作　　者：陈晨 保文星[1] 陈旭 景永俊[1] 李卫军 CHEN Chen;BAO Wenxing;CHEN Xu;JING Yongjun;LI Weijun(School of Computer Science and Engineering,Northern University for Nationalities,Yinchuan 750021,China)

机构地区：[1]北方民族大学计算机科学与工程学院,银川750021

出　　处：《计算机工程与应用》2024年第24期222-234,共13页Computer Engineering and Applications

基　　金：宁夏科技研发重点项目(2021BEG03030);国家民委图像图形与智能信息处理创新团队。

摘　　要：针对智慧教室中存在前后排学生图像尺寸差异较大、后排小目标检测困难的问题,提出了一种改进YOLOv8的学生课堂行为识别方法:DMS-YOLOv8。结合CA注意力机制与深度卷积,提出了动态通道注意力卷积(DCAConv),能够动态调整通道权重,更灵敏地捕获关键特征;引入多尺度卷积注意力(MSCA),通过元素乘法最大化挖掘多尺度卷积特征,增强对空间细节的关注;同时,构建了多尺度上下文融合(LCD)模块,通过卷积和自注意力机制,增强多尺度特征融合。增加小目标检测层,通过较大尺寸特征图的局部特征提取,显著提高模型对后排学生行为的识别能力。与基线模型YOLOv8n相比,该方法在自制学生行为数据集上的mAP50值提高了4.6个百分点,在VOC数据集上提高了18.7个百分点。该方法在学生课堂行为识别方面表现突出,可显著提高智慧教室学生课堂行为识别的准确率。To address significant image size differences and small target detection challenges in smart classrooms,an improved YOLOv8 method for recognizing student behavior,DMS-YOLOv8,is proposed.Firstly,dynamic channel atten-tion convolution(DCAConv)combines CA attention with deep convolution to dynamically adjust channel weights and capture key features.Secondly,multi-scale convolutional attention(MSCA)utilizes element-wise multiplication to enhance spatial details by maximizing multi-scale features.Additionally,a multi-scale context fusion(LCD)module is constructed to improve feature fusion using convolution and self-attention mechanisms.Finally,a small target detection layer is added to enhance the model’s ability to recognize back-row student behavior by extracting local features from larger-sized fea-ture maps.Compared to the baseline YOLOv8n model,this method improves the mAP50 value by 4.6 percengtage points on a custom student behavior dataset and by 18.7 percengtage points on the VOC dataset,significantly increasing the accu-racy of student classroom behavior recognition in smart classrooms.

关 键 词：学生行为识别 YOLOv8 目标检测 动态通道注意力卷积 多尺度上下文融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]