Automatic detection of teacher behavior in classroom videos using AlphaPose and Faster R-CNN algorithms
This study proposes an automated classification framework for evaluating teacher behavior in classroom settings by integrating AlphaPose and Faster region-based convolutional neural networks (R-CNN) algorithms. The method begins by applying AlphaPose to classroom video footage to extract detailed sk...
| الحاوية / القاعدة: | PeerJ Computer Science |
|---|---|
| المؤلفون الرئيسيون: | , , , , |
| التنسيق: | مقال |
| اللغة: | الإنجليزية |
| منشور في: |
PeerJ Inc.
2025-05-01
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://peerj.com/articles/cs-2933.pdf |
| _version_ | 1849460851856113664 |
|---|---|
| author | Jing Huang Harwati Hashim Helmi Norman Mohammad Hafiz Zaini Xiaojun Zhang |
| author_facet | Jing Huang Harwati Hashim Helmi Norman Mohammad Hafiz Zaini Xiaojun Zhang |
| author_sort | Jing Huang |
| collection | DOAJ |
| container_title | PeerJ Computer Science |
| description | This study proposes an automated classification framework for evaluating teacher behavior in classroom settings by integrating AlphaPose and Faster region-based convolutional neural networks (R-CNN) algorithms. The method begins by applying AlphaPose to classroom video footage to extract detailed skeletal pose information of both teachers and students across individual frames. These pose-based features are subsequently processed by a Faster R-CNN model, which classifies teacher behavior into appropriate or inappropriate categories. The approach is validated on the Classroom Behavior (PCB) dataset, comprising 74 video clips and 51,800 annotated frames. Experimental results indicate that the proposed system achieves an accuracy of 74.89% in identifying inappropriate behaviors while also reducing manual behavior logging time by 47% and contributing to a 63% decrease in such behaviors. The findings highlight the potential of computer vision techniques for scalable, objective, and real-time classroom behavior analysis, offering a viable tool for enhancing educational quality and teacher performance monitoring. |
| format | Article |
| id | doaj-art-e5f4a86dcd9c4093bba52bc514167c94 |
| institution | Directory of Open Access Journals |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| spelling | doaj-art-e5f4a86dcd9c4093bba52bc514167c942025-08-20T03:22:30ZengPeerJ Inc.PeerJ Computer Science2376-59922025-05-0111e293310.7717/peerj-cs.2933Automatic detection of teacher behavior in classroom videos using AlphaPose and Faster R-CNN algorithmsJing Huang0Harwati Hashim1Helmi Norman2Mohammad Hafiz Zaini3Xiaojun Zhang4Faculty of Education, Universiti Kebangsaan Malaysia, Selangor, MalaysiaFaculty of Education, Universiti Kebangsaan Malaysia, Selangor, MalaysiaFaculty of Education, Universiti Kebangsaan Malaysia, Selangor, MalaysiaFaculty of Education, Universiti Kebangsaan Malaysia, Selangor, MalaysiaFaculty of Economics and Business Foreign Languages, Wuhan Technology and Business University, Wuhan, Hubei, ChinaThis study proposes an automated classification framework for evaluating teacher behavior in classroom settings by integrating AlphaPose and Faster region-based convolutional neural networks (R-CNN) algorithms. The method begins by applying AlphaPose to classroom video footage to extract detailed skeletal pose information of both teachers and students across individual frames. These pose-based features are subsequently processed by a Faster R-CNN model, which classifies teacher behavior into appropriate or inappropriate categories. The approach is validated on the Classroom Behavior (PCB) dataset, comprising 74 video clips and 51,800 annotated frames. Experimental results indicate that the proposed system achieves an accuracy of 74.89% in identifying inappropriate behaviors while also reducing manual behavior logging time by 47% and contributing to a 63% decrease in such behaviors. The findings highlight the potential of computer vision techniques for scalable, objective, and real-time classroom behavior analysis, offering a viable tool for enhancing educational quality and teacher performance monitoring.https://peerj.com/articles/cs-2933.pdfAutomatic detectionFaster R-CNNAlphaPoseTeacher behavior recognition |
| spellingShingle | Jing Huang Harwati Hashim Helmi Norman Mohammad Hafiz Zaini Xiaojun Zhang Automatic detection of teacher behavior in classroom videos using AlphaPose and Faster R-CNN algorithms Automatic detection Faster R-CNN AlphaPose Teacher behavior recognition |
| title | Automatic detection of teacher behavior in classroom videos using AlphaPose and Faster R-CNN algorithms |
| title_full | Automatic detection of teacher behavior in classroom videos using AlphaPose and Faster R-CNN algorithms |
| title_fullStr | Automatic detection of teacher behavior in classroom videos using AlphaPose and Faster R-CNN algorithms |
| title_full_unstemmed | Automatic detection of teacher behavior in classroom videos using AlphaPose and Faster R-CNN algorithms |
| title_short | Automatic detection of teacher behavior in classroom videos using AlphaPose and Faster R-CNN algorithms |
| title_sort | automatic detection of teacher behavior in classroom videos using alphapose and faster r cnn algorithms |
| topic | Automatic detection Faster R-CNN AlphaPose Teacher behavior recognition |
| url | https://peerj.com/articles/cs-2933.pdf |
| work_keys_str_mv | AT jinghuang automaticdetectionofteacherbehaviorinclassroomvideosusingalphaposeandfasterrcnnalgorithms AT harwatihashim automaticdetectionofteacherbehaviorinclassroomvideosusingalphaposeandfasterrcnnalgorithms AT helminorman automaticdetectionofteacherbehaviorinclassroomvideosusingalphaposeandfasterrcnnalgorithms AT mohammadhafizzaini automaticdetectionofteacherbehaviorinclassroomvideosusingalphaposeandfasterrcnnalgorithms AT xiaojunzhang automaticdetectionofteacherbehaviorinclassroomvideosusingalphaposeandfasterrcnnalgorithms |