Abstract
A novel dataset on teacher-student classroom behavior has been designed and implemented in this paper. The dataset, named Posture-based Teacher-Student Behavioral Engagement Pattern Dataset (PTPD), is realized using AIoT technology and consists of over 13,500 videos from more than 1,000 scenarios, providing convenience for spatio-temporal analysis. PTPD also fills the gap of high-quality datasets for classroom behavior analysis of teachers and students. Then, Alpha Pose, Open Pose, and ST-GCN algorithms are employed to evaluate the accuracy of the dataset. Experimental results demonstrate that the pose-based algorithms achieve an average estimation accuracy of 91.14%, while the ST-GCN algorithm achieves a teacher-student behavior recognition rate of 92.15%, confirming the effectiveness and high quality of this dataset.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
