Improved Classroom Behavior Detection Algorithm for YOLOv8

doi:10.3969/j.issn.1006-2475.2025.08.011

Abstract

Abstract:
Abstract: Aiming at the problems of low detection accuracy of student classroom behavior under monitoring and difficulty in deploying models， an improved YOLOv8 algorithm is proposed for detecting student behavior. Firstly， the YOLOv8 backbone network is improved by introducing the Swin Transformer network as the backbone feature extraction network to reduce information loss and improve the effectiveness of feature extraction. Secondly， to enhance the model’s attention to the features of distant targets， a flexible dual channel attention mechanism EMA is introduced， which makes the model focus more on targets with fewer pixels at long distances and improves detection accuracy. Finally， in the Neck section， the Slim Neck design paradigm containing GSConv is used to make lightweight improvements to the model. The experimental results on the SCB-Dataset3 dataset show that the improved model has a parameter count of 3.3 M and a computational load of 11.1 GFLOPs， respectively， with a detection accuracy of 88.75%. Compared with the original model， the parameter count is reduced by 40.7%， the computational load is reduced by 15.9%， and the detection accuracy is improved by 7.7 percentage points. This achieves good detection accuracy while achieving model lightweighting.

Key words: Key words: classroom behavior detection, YOLOv8, Swin Transformer, attention mechanism, Slim-Neck
Backbone

CLC Number:

中图分类号：TP391.4

SU Yansen, MOU Li. Improved Classroom Behavior Detection Algorithm for YOLOv8[J]. Computer and Modernization, 2025, 0(08): 76-81.

References

［1］魏艳涛，秦道影，胡佳敏，等. 基于深度学习的学生课堂行为检测［J］. 现代教育技术， 2019，29（7）:87-91.
［2］ HARIHARAN B， PADMINI S， GOPALAKRISHNAN U. Gesture recognition using Kinect in a virtual classroom environment［C］// 2014 4th International Conference on Digital Information and Communication Technology and its Applications （DICTAP）. IEEE， 2014:118-124.
［3］ SIMONYAN K， ZISSERMAN A. Two-stream convolutional networks for action recognition in videos［C］// Proceedings of the 28th International Conference on Neural Information Processing Systems. ACM， 2014，1:568-576.
［4］ FEICHTENHOFER C， FAN H Q， MALIK J， et al. Slowfast networks for video recognition［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. IEEE， 2019:6201-6210.
［5］ ARNAB A， DEHGHANI M， HEIGOLD G， et al. ViViT: A video vision Transformer［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. IEEE， 2021:6816-6826.
［6］ VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］// Proceedings of the 31st International Conference on Advances in Neural Information Processing Systems. ACM， 2017:6000-6010.
［7］林灿然. 基于深度学习的课堂学生行为识别技术研究与分析系统设计［D］. 广州:广东工业大学， 2020.
［8］ FANG H S， LI J F， TANG H Y， et al. AlphaPose: Whole-body regional multi-person pose estimation and tracking in real-time［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2023，45（6）:7157-7173.
［9］ YU X， WANG S H. Abnormality diagnosis in mammograms by transfer learning based on ResNet18［J］. Fundamenta Informaticae， 2019，168（2-4）:219-230.
［10］刘秋会. 基于视频分析的课堂学生学习状态研究与分析［D］. 贵阳:贵州民族大学， 2021.
［11］ GHIASI G， LIN T Y， LE Q V. Dropblock: A regularization method for convolutional networks［C］// Proceedings of the 32nd International Conference on Neural Information Processing Systems. ACM， 2018:10750-10760.
［12］黄勇康，梁美玉，王笑笑，等. 基于深度时空残差卷积神经网络的课堂教学视频中多人课堂行为检测［J］. 计算机应用， 2022，42（3）:736-742.
［13］ JAISWAL S K， AGRAWAL R. A comprehensive review of YOLOv5: Advances in real-time object detection［J］. International Journal of Innovative Research in Computer Science & Technology， 2024，12（3）:75-80.
［14］ WOJKE N， BEWLEY A， PAULUS D. Simple online and realtime tracking with a deep association metric［C］// 2017 IEEE International Conference on Image Processing （ICIP）. IEEE， 2017:3645-3649.
［15］何秀玲，杨凡，陈增照，等. 基于人体骨架和深度学习的学生课堂行为检测［J］. 现代教育技术， 2020，30（11）:105-112.
［16］ QIAO S， WANG Y L， LI J. Real-time human gesture grading based on OpenPose［C］// 2017 10th International Congress onImage and Signal Processing， BioMedical Engineering and Informatics （CISP-BMEI）. IEEE， 2017. DOI: 10.1109/CISP-BMEI.2017.8301910.
［17］苏超，王国中. 基于改进OpenPose的学生行为检测研究［J］. 计算机应用研究， 2021，38（10）:3183-3188.
［18］闫兴亚，匡娅茜，白光睿，等. 基于深度学习的学生课堂行为检测方法［J］. 计算机工程， 2023，49（7）:251-258.
［19］ KOONCE B. MobileNetV3［M］// Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization. Apress， 2021:125-144.
［20］ JOCHER G， CHAURASIA A， QIU J. YOLO by Ultralytics［CP/OL］. （2023-02-28）［2024-06-29］. https://github.com/ultralytics/ultralytics.
［21］ LIU Z， LIN Y T， CAO Y， et al. Swin Transformer: Hierarchical vision Transformer using shifted windows［J］. arXiv preprint arXiv:2103.14030， 2021
［22］ OUYANG D L， HE S， ZHANG G Z， et al. Efficient multi-scale attention module with cross-spatial learning［C］// ICASSP 2023-2023 IEEE International Conference on Acoustics， Speech and Signal Processing （ICASSP）. IEEE， 2023. DOI: 10.1109/ICASSP49357.2023.10096516.
［23］ LI H L， LI J， WEI H B， et al. Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles［J］. arXiv preprint arXiv:2206.02424， 2022.
［24］ HOU Q B， ZHOU D Q， FENG J S. Coordinate attention for efficient mobile network design［C］// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2021:13708-13717.
［25］ YANG F， WANG T. SCB-Dataset3: A benchmark for detecting student classroom behavior［J］. arXiv preprint arXiv:2310.02522， 2023
［26］ WANG C Y， BOCHKOVSKIY A， LIAO H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for realtime object detectors［C］// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE， 2023:7464-7475.
［27］ GE Z， LIU S， WANG F， et al. YOLOX: Exceeding YOLO series in 2021［J］. arxiv preprint arxiv:2107.08430， 2021.
［28］ WANG C Y， YEH I H， LIAO H Y M. YOLOv9: Learning what you want to learn using programmable gradient information［J］. arXiv preprint arXiv:2402.13616， 2024.

[1]	JING Qingwu, CHEN Hongjun, GAO Di, ZHOU Meimei. Goal Driven Recommendation-oriented Dialog Generation Method [J]. Computer and Modernization, 2025, 0(08): 16-23.
[2]	GAO Lisha1, PENG Guozheng2, WANG Chong1, HAN Shuo1, XIANG Nan1, ZHANG Qizhe2, ZHU Yuefei3, CHENG Xu3. Dual-backbone Network Insulator Defect Detection Algorithm Based on YOLOv5 [J]. Computer and Modernization, 2025, 0(08): 82-88.
[3]	CAI Bohan, LIU Jun. Long-and Short-Term Air Pollutant Concentration Forecasting Based on Optimized Transformer [J]. Computer and Modernization, 2025, 0(07): 55-62.
[4]	LI Zihe, WANG Yiding. 3D Human Motion Similarity Estimation from Different Perspectives [J]. Computer and Modernization, 2025, 0(07): 63-68.
[5]	JIAO Leyan, ZHU Xinjuan. Speech Cloning Method Based on Self-attention Mechanism Speaker Encoder And SA-Decoder [J]. Computer and Modernization, 2025, 0(07): 69-76.
[6]	RAO Hongyu1, CHEN Xin2, CHEN Sheng3, XIA Tian3, SHEN Li4, LUY Guangqiang5. Power Load Forecasting of Bi-LSTM Based on Improving Whale Algorithm [J]. Computer and Modernization, 2025, 0(07): 77-82.
[7]	WEI Qingsong1, WANG Xiaojun2, WEI Yuan1, ZENG Shangqi1, FANG Yuan1. HGAT: Multivariate Time Series Anomaly Detection Based on Hybrid Graph Attention Network [J]. Computer and Modernization, 2025, 0(07): 97-105.
[8]	XIE Peidong, CHENG Yuanzhi, XU Haotian. Hierarchical Classification Algorithm for Marine Organisms [J]. Computer and Modernization, 2025, 0(06): 21-27.
[9]	HAO Rongrong1, MA Qiaomei1, TAN Yajun1, SHI Huanyin2. Complex Fire Detection Based on Deformable Convolutions and Attention Mechanisms [J]. Computer and Modernization, 2025, 0(06): 79-85.
[10]	QIN Hongzheng1, 2, WANG Tonghan1, 2, JIA Huizhen1, 2. Image Quality Assessment with Multi-scale Interaction and Cross-channel Attention [J]. Computer and Modernization, 2025, 0(06): 86-91.
[11]	WANG Chengxian1, ZHAO Qing2. Yi Language Named Entity Recognition Method Based on CR-BACC Model [J]. Computer and Modernization, 2025, 0(05): 28-35.
[12]	CHI Biwei1, SUN Rui2. DDoS Attack Detection Method Based on Transformer Architecture [J]. Computer and Modernization, 2025, 0(05): 36-40.
[13]	JI Zhengjie, WEI Linjing. ICS-ResNet： A Lightweight Network for Maize Leaf Disease Classification [J]. Computer and Modernization, 2025, 0(04): 19-28.
[14]	WANG Jiale, SONG Wenai, FU Lizhen. Occupational Pneumoconiosis Screening Based on HA-Net Model [J]. Computer and Modernization, 2025, 0(04): 103-110.
[15]	TANG Rui1, WU Jianchao1, CHEN Jianbo1, CHAI Jiang1, WANG Qian1, HE Yuchen2. Improved YOLOv8s Algorithm Based on GiraffeDet for Transmission Line Icing Detection [J]. Computer and Modernization, 2025, 0(03): 6-11.