| 142 | 0 | 46 |
| 下载次数 | 被引频次 | 阅读次数 |
针对教室环境中学生行为检测存在人员密集、遮挡、模糊以及前后排目标尺度变化显著等问题，提出名为DUHG-YOLO的先进目标检测模型。模型以YOLOv11框架为基础，首先设计C3k2＿Dual模块，既在主干网络的C3k2中引入双重卷积模块(DualConv),以增强模型特征提取能力，减少计算冗余并提高检测精度。其次提出一种多尺度特征融合与注意力增强的网络框架ZSH,通过引入混合注意力机制(HybridAttention)和双线性插值(Bilinear)增强特征融合效果，提升特征表示能力。最后使用广义交并比损失函数(GIoU)优化非重叠目标的梯度更新，提高模型的检测精度。实验结果表明，相较YOLOv11n, DUHG-YOLO在StuDataset数据集上精确率、召回率、平均精度均值分别提升1.7%、2.6%、2.1%,可以有效应用于教室学生行为检测任务。
Abstract：To address the challenges of dense crowds, occlusions, blurring, and significant scale variations of targets between front and back rows in student behavior detection within classroom environments, this paper proposes an advanced object detection model named DUHG-YOLO.Based on the YOLOv11 framework, the model first introduces the C3k2＿Dual module, which incorporates a dual convolution(DualConv) into the C3k2 block of the backbone network to enhance feature extraction capability, reduce computational redundancy, and improve detection accuracy.Then, a multi-scale feature fusion and attention-enhanced ZSH network framework is proposed, integrating a Hybrid Attention Mechanism(HybridAttention) and Bilinear Interpolation(Bilinear) to strengthen feature fusion and improve feature representation.Finally, the Generalized Intersection over Union(GIoU) loss function is employed to optimize gradient updates for non-overlapping targets, further enhancing detection accuracy.Experimental results demonstrate that, compared to YOLOv11n, DUHG-YOLO achieves improvements of 1.7% in precision, 2.6% in recall, and 2.1% in mean average precision(mAP) on the StuDataset, proving its effectiveness for classroom student behavior detection tasks.
[1] 王君，张德育，康鑫英.改进Faster-RCNN的低空小型无人机检测方法[J].沈阳理工大学学报，2021,40(4):23-28.WANG J,ZHANG D Y,KANG X Y.Improved detection method of low altitude small UAV by Faster R-CNN[J].Journal of Shenyang Ligong University,2021,40(4):23-28.(in Chinese)
[2] 张新航，张雅茹，麻振华，等.基于深度学习方法的YOLO目标检测综述[J].长江信息通信，2024,37(8):52-56.ZHANG X H,ZHANG Y R,MA Z H,et al.Overview of yolo object detection based on deep learning methods[J].Changjiang Information & Communications,2024,37(8):52-56.(in Chinese)
[3] 刘健，陈亮.基于YOLOv4的学生行为识别研究[J].沈阳理工大学学报，2023,42(3):16-21.LIU J,CHEN L.Research on student behavior recognition based on YOLOv4[J].Journal of Shenyang Ligong University,2023,42(3):16-21.(in Chinese)
[4] 刘宏，张释文，孙程，等.基于视频时空特征的学生课堂行为检测[J].软件导刊，2024,23(8):267-274.LIU H,ZHANG S W,SUN C,et al.Student classroom behavior detection based on video spatio-temporal features[J].Software Guide,2024,23(8):267-274.(in Chinese)
[5] 闫兴亚，匡娅茜，白光睿，等.基于深度学习的学生课堂行为识别方法[J].计算机工程，2023,49(7):251-258.YAN X Y,KUANG Y X,BAI G R,et al.Student classroom behavior recognition method based on deep learning[J].Computer Engineering,2023,49(7):251-258.(in Chinese)
[6] 胡敏，张伟，姜念祖，等.基于YOLOv8n的学生课堂行为检测算法[J].白城师范学院学报，2025,39(2):42-50,128.HU M,ZHANG W,JIANG N Z,et al.Student classroom behavior detection algorithm based on YOLOv8n[J].Journal of Baicheng Normal University,2025,39(2):42-50,128.(in Chinese)
[7] 曾钰琦，刘博，钟柏昌，等.智慧教育下基于改进YOLOv8的学生课堂行为检测算法[J].计算机工程，2024,50(9):344-355.ZENG Y Q,LIU B,ZHONG B C,et al.Student classroom behavior detection algorithm based on improved YOLOv8 in smart education[J].Computer Engineering,2024,50(9):344-355.(in Chinese)
[8] ZHANG H Y,LI Y.Student classroom teaching behavior recognition based on DSCNN model in intelligent campus education[J].Informatica,2024,48(9):19-35.
[9] WANG Z F,WANG M H,ZENG C Y,et al.SBD-net:incorporating multi-level features for an efficient detection network of student behavior in smart classrooms[J].Applied Sciences,2024,14(18):8357.
[10] 王鑫钰，高东怀，宁玉文，等.基于改进YOLO算法的学生行为检测方法研究[J/OL].计算机科学，2025:1-15.[2025-03-18].https://kns.cnki.net/kcms/detail/50.1075.tp.20250317.1846.032.html.WANG X Y,GAO D H,NING Y W,et al.Research on student behavior detection method based on improved YOLO algorithm[J/OL].Computer Science,2025:1-15.[2025-03-18].https://kns.cnki.net/kcms/detail/50.1075.tp.20250317.1846.032.html.(in Chinese)
[11] KANG M,TING C M,TING F F,et al.ASF-YOLO:a novel YOLO model with attentional scale sequence fusion for cell instance segmentation[J].Image and Vision Computing,2024,147:105057.
[12] 董铠，马勇年.基于改进YOLOv8算法的学生课堂行为检测优化方法研究[J].兰州职业技术学院学报，2025,41(2):61-65.DONG K,MA Y N.Optimization of student classroom behavior detection based on improved YOLOv8 algorithm[J].Journal of Lanzhou Vocational Technical College,2025,41(2):61-65.(in Chinese)
[13] 王嘉瑞.基于多尺度局部特征融合与Distance-IoU的学生课堂行为检测算法[J].信息系统工程，2025(3):173-176.WANG J R.Detection algorithm of students' classroom behavior based on multi-scale local feature fusion and Distance-IoU[J].China CIO News,2025(3):173-176.(in Chinese)
[14] 张小妮，杨萌萌，张军锋，等.基于改进YOLOv7算法的学生课堂行为识别研究[J].现代信息科技，2025,9(4):69-73.ZHANG X N,YANG M M,ZHANG J F,et al.Research on student classroom behavior recognition based on the improved YOLOv7 algorithm[J].Modern Information Technology,2025,9(4):69-73.(in Chinese)
[15] 牛泽刚，赵玉兰.基于RI-YOLO的学生行为检测算法[J].无线互联科技，2024,21(24):86-90.NIU Z G,ZHAO Y L.Student behavior detection algorithm based on RI-YOLO[J].Wireless Internet Science and Technology,2024,21(24):86-90.(in Chinese)
[16] 张杰，魏艳龙，薛红新.基于CBW-YOLOv5s轻量化模型的学生课堂行为快速检测[J].现代计算机，2024,30(21):1-7.ZHANG J,WEI Y L,XUE H X.Fast detection of student classroom behavior based on CBW-YOLOv5s lightweight model[J].Modern Computer,2024,30(21):1-7.(in Chinese)
[17] ZHONG J C,CHEN J Y,MIAN A.DualConv:dual convolutional kernels for lightweight deep neural networks[J].IEEE Transactions on Neural Networks and Learning Systems,2023,34(11):9528-9535.
[18] ZHAO J H,ZHU H Y.CBPH-net:a small object detector for behavior recognition in classroom scenarios[J].IEEE Transactions on Instrumentation and Measurement,2023,72:2521112.
[19] WOO S,PARK J,LEE J Y,et al.CBAM:convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision-(ECCV).Munich,Germany:Springer,2018:3-19.
[20] HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA:IEEE,2018:7132-7141.
基本信息:
中图分类号:TP391.41;TP18
引用信息:
[1]魏英姿,于聚壮,张航.基于DUHG-YOLO的教室学生行为检测[J].沈阳理工大学学报,2026,45(02):39-46.
基金信息:
辽宁省自然科学基金计划机器人学国家重点实验室联合开放基金(2022-KF-12-08)
2026-02-24
2026-02-24