Real-time classroom student behavior detection based on improved YOLOv8s

Abstract The learning capacity of students is significantly influenced by the quality of instruction they receive in the classroom. With the rapid advancement of behavior detection technology, identifying classroom behaviors of students is becoming increasingly common in educational settings. Howeve...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaojing Sheng, Suqiang Li, Sixian Chan
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-99243-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850172988096249856
author Xiaojing Sheng
Suqiang Li
Sixian Chan
author_facet Xiaojing Sheng
Suqiang Li
Sixian Chan
author_sort Xiaojing Sheng
collection DOAJ
description Abstract The learning capacity of students is significantly influenced by the quality of instruction they receive in the classroom. With the rapid advancement of behavior detection technology, identifying classroom behaviors of students is becoming increasingly common in educational settings. However, the field still faces specific challenges, primarily concerning the accuracy of identifying student behaviors within complex and variable classroom environments, as well as the real-time capabilities of detection algorithms. To address these challenges, we propose an efficient and straightforward algorithm based on the YOLO architecture. A Multi-scale Large Kernel Convolution Module (MLKCM) has been designed to capture feature information across various dimensions through multi-axis pooling, achieving adaptive receptive fields and effectively capturing multi-scale features. This design enhances the network’s sensitivity to feature information by incorporating convolution kernels of varying sizes. Subsequently, we introduce a Progressive Feature Optimization Module (PFOM) to segment the channel dimension of the input feature map. This module integrates feature refinement blocks progressively, which not only preserve the refined features but also efficiently aggregate both local and global information. Finally, we conducted comprehensive experiments using the SCB-Dataset3-S and SCB-Dataset3-U datasets. The results demonstrated mean Average Precision (mAP) values of 76.5% and 95.0%, respectively, surpassing other commonly used detection techniques. Additionally, the effectiveness of our approach was validated through ablation studies and visualization of the detection outcomes.
format Article
id doaj-art-7cdaa10e8cc345d08f440d9771d85013
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7cdaa10e8cc345d08f440d9771d850132025-08-20T02:19:57ZengNature PortfolioScientific Reports2045-23222025-04-0115111110.1038/s41598-025-99243-xReal-time classroom student behavior detection based on improved YOLOv8sXiaojing Sheng0Suqiang Li1Sixian Chan2College of Teacher Education, Quzhou UniversitySchool of Electronic and Information Engineering, Anhui Jianzhu UniversityCollege of Computer Science and Technology, Zhejiang University of TechnologyAbstract The learning capacity of students is significantly influenced by the quality of instruction they receive in the classroom. With the rapid advancement of behavior detection technology, identifying classroom behaviors of students is becoming increasingly common in educational settings. However, the field still faces specific challenges, primarily concerning the accuracy of identifying student behaviors within complex and variable classroom environments, as well as the real-time capabilities of detection algorithms. To address these challenges, we propose an efficient and straightforward algorithm based on the YOLO architecture. A Multi-scale Large Kernel Convolution Module (MLKCM) has been designed to capture feature information across various dimensions through multi-axis pooling, achieving adaptive receptive fields and effectively capturing multi-scale features. This design enhances the network’s sensitivity to feature information by incorporating convolution kernels of varying sizes. Subsequently, we introduce a Progressive Feature Optimization Module (PFOM) to segment the channel dimension of the input feature map. This module integrates feature refinement blocks progressively, which not only preserve the refined features but also efficiently aggregate both local and global information. Finally, we conducted comprehensive experiments using the SCB-Dataset3-S and SCB-Dataset3-U datasets. The results demonstrated mean Average Precision (mAP) values of 76.5% and 95.0%, respectively, surpassing other commonly used detection techniques. Additionally, the effectiveness of our approach was validated through ablation studies and visualization of the detection outcomes.https://doi.org/10.1038/s41598-025-99243-x
spellingShingle Xiaojing Sheng
Suqiang Li
Sixian Chan
Real-time classroom student behavior detection based on improved YOLOv8s
Scientific Reports
title Real-time classroom student behavior detection based on improved YOLOv8s
title_full Real-time classroom student behavior detection based on improved YOLOv8s
title_fullStr Real-time classroom student behavior detection based on improved YOLOv8s
title_full_unstemmed Real-time classroom student behavior detection based on improved YOLOv8s
title_short Real-time classroom student behavior detection based on improved YOLOv8s
title_sort real time classroom student behavior detection based on improved yolov8s
url https://doi.org/10.1038/s41598-025-99243-x
work_keys_str_mv AT xiaojingsheng realtimeclassroomstudentbehaviordetectionbasedonimprovedyolov8s
AT suqiangli realtimeclassroomstudentbehaviordetectionbasedonimprovedyolov8s
AT sixianchan realtimeclassroomstudentbehaviordetectionbasedonimprovedyolov8s