ABSTRACT
Real-time student classroom action recognition allows the creation of a closed-loop teaching system and efficient teaching methods. To address the issue of a lack of open dataset in the SCAR re- search field, we proposed a challenging dataset SCAR-dataset with a total of 7194 samples, which was collected in college classrooms and after exploratory experiments. The dataset were defined into six categories: focused, head_drop, bored_distraction, looking_around, sleeping, and stand_up. We benchmarked the SCAR dataset for real-time deployment using YOLOv5, YOLOv7, and YOLOv8 algorithms, which served as the foundation for subsequent classroom concentration analysis research. By combining depth-separable convolution, a lightweight asymmetric detector head LADH was proposed. Experiments show that improving the Yolov8n model increases the map value by 2.5 points while don't in- creasing the number of parameters and Gflops.
- W. Fan, 2021. A realtime action detection frame work based on pytorchvideo.Google Scholar
- R. Fu, T. Wu, Z. Luo, F. Duan, X. Qiao, and P. Guo. 2021. Learning behavior analysis in classroom based on deep learning in 2019 Tenth International Conference on Intelligent Control and Information Processing (ICICIP). IEEE, pp. 206– 212.Google Scholar
- D. Maji, S. Nagori, M. Mathew, and D. Poddar, 2022. Yolo-pose: Enhancing yolo for multi person pose estimation using object keypoint similarity loss. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2637–2646.Google Scholar
- E. Murphy-Chutorian and M. M. Trivedi. 2008. Head pose estimation in computer vision: A survey. IEEE transactions on pattern analysis and machine intelligence, vol. 31, no. 4, pp. 607–626.Google Scholar
- W. Chen, H. Huang, S. Peng, C. Zhou, and C. Zhang. 2021.Yolo-face: a real-time face detector, The Visual Computer, vol. 37, pp. 805–813,Google ScholarDigital Library
- S. Li and W. Deng. 2020. Deep facial expression recognition: A survey. IEEE transactions on affective computing, vol. 13, no. 3, pp. 1195–1215Google Scholar
- C. Li, R. Wang, J. Li, and L. Fei. 2020. Face detection based on yolov3 in Recent Trends in Intelligent Computing, Communication and Devices: Proceedings of ICCD 2018. Springer, pp. 277–284.Google Scholar
- W. Xu, B. Li, Y. Du, and S. Dong. 2023. Study on facial recognition method based on yolov5 in Journal of Physics: Conference Series, vol. 2560, no. 1. IOP Publishing, p. 012020Google Scholar
- K. Li, Y. Wang, and Z. Hu. 2023. Improved yolov7 for small object detection algorithm based on attention and dynamic convolution. Applied Sciences, vol. 13, no. 16, p. 9316Google ScholarCross Ref
- F. Yang and T. Wang, 2023, Scb-dataset3: A benchmark for detecting student classroom behavior. arXiv preprint arXiv:2310.02522Google Scholar
- J. Zhang, Z. Chen, G. Yan, Y. Wang, and B. Hu. 2023. Faster and lightweight: An im- proved yolov5 object detector for remote sensing images. Remote Sensing, vol. 15, no. 20, p. 4974Google ScholarCross Ref
- R. Li and Y. Wu. 2022. Improved yolo v5 wheat ear detection algorithm based on attention mechanism. Electronics, vol. 11, no. 11, p. 1673Google ScholarCross Ref
Recommendations
Flipping a college mathematics classroom: An action research project
AbstractIn this action research study, a flipped and non-flipped college-level mathematics classroom were compared. Participants in the flipped classroom watched video lessons outside of class and engaged in classwork problems during class. The non-...
Promoting Student Engagement Using Flipped Classroom in Large Introductory Financial Accounting Class
ICEEL '19: Proceedings of the 2019 3rd International Conference on Education and E-LearningFlipped classroom has become an instructional trend used by many universities especially in Science courses. The use of flipped instructional classroom encourages student to be actively engaged in their learning. However, the implementation of flipped ...
Lessons learned when gathering real-time formative assessment in the university classroom using tablet PCs
FIE'09: Proceedings of the 39th IEEE international conference on Frontiers in education conferenceWorldwide, higher education instructors are exploring ways of enhancing classroom learning experiences with their Tablet PC-equipped students. To collect real-time formative assessment, instructors pose an open-format question to the class and the ...
Comments