Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지
DOI QR코드

DOI QR Code

Real-time Online Study and Exam Attitude Dataset Design and Implementation

실시간 온라인 수업 및 시험 태도 데이터 세트 설계 및 구현

  • Kim, Junsik (Department of Electronic Engineering, Kwangwoon University) ;
  • Lee, Chanhwi (Department of Electronic Engineering, Kwangwoon University) ;
  • Song, Hyok (Korea Electronics Technology Institute) ;
  • Kwon, Soonchul (Graduate School of Smart Convergence, Kwangwoon University)
  • 김준식 (광운대학교 전자공학과) ;
  • 이찬휘 (광운대학교 전자공학과) ;
  • 송혁 (한국전자기술연구원) ;
  • 권순철 (광운대학교 스마트융합대학원)
  • Received : 2021.11.08
  • Accepted : 2021.12.21
  • Published : 2022.01.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, due to COVID-19, online remote classes and non-face-to-face exams have made it difficult to manage class attitudes and exam cheating. Therefore, there is a need for a system that automatically recognizes and detects the behavior of students online. Action recognition, which recognizes human action, is one of the most studied technologies in computer vision. In order to develop such a technology, data including human arm movement information and information about surrounding objects, which can be key information in online classes and exams, are needed. It is difficult to apply the existing dataset to this system because it is classified into various fields or consists of daily life action. In this paper, we propose a dataset that can classify attitudes in real-time online tests and classes. In addition, it shows whether the proposed dataset is correctly constructed through comparison with the existing action recognition dataset.

최근 코로나바이러스감염증-19(COVID-19)로 인해 온라인 원격 수업과 비대면 시험으로 인해 수업 태도 및 시험 부정행위에 대한 관리가 어려움을 겪고 있다. 따라서 온라인으로 학생들의 행동을 자동으로 인식하고 검출하는 시스템이 필요하다. 사람의 행동을 인식하는 행동 인식의 경우 컴퓨터 비전에서 많이 연구되는 기술 중 하나이다. 이러한 시스템을 개발하기 위해서는 온라인 수업 및 시험에서 주요 정보가 될 수 있는 사람의 팔 움직임 정보와 주변 물체에 대한 정보를 포함하는 데이터가 필요하다. 기존 데이터 세트는 여러 분야에 대해 분류를 하거나 일상생활 행동으로 구성되어 있어 본 시스템에 적용시키기에 어려움이 있다. 본 논문에서는 실시간으로 진행되는 온라인 시험 및 수업에서 태도를 분류할 수 있는 데이터 세트를 제시한다. 또한, 기존의 행동 인식 데이터 세트와의 비교를 통해 제안된 데이터 세트가 올바르게 구성되었는지를 보여준다.

Keywords

Acknowledgement

This work was supported by institute of information & communications Technology Planning & Evaluation(IITP) Grant funded by the Korea Government(MSIT) (No. 2021-0-00804, Development of online exam fraud prevention and class concentration improvement technology).

References

  1. School Remote Class Operation Status due to COVID-19, https://kess.kedi.re.kr/post/6711307?itemCode=03&menuId=m_02_03_03 (accessed Oct. 20, 2020)
  2. Yan, S., Xiong, Y., Lin, D., "Spatial temporal graph convolutional networks for skeleton-based action recognition," American Association for Artificial Intelligence Conference, Artificial intelligence, New Orleans, USA, pp. 7444-7452, 2018
  3. Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W., "Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition," Proceedings of the IEEE/CVF International Conference, Computer Vision, Paris, France, pp. 13359-13368, 2021.
  4. Carreira, J., & Zisserman, A.. "Quo vadis, action recognition? a new model and the kinetics dataset," Proceeding of the IEEE Conference, Computer Vision and Pattern Recognition, Honolulu, USA, pp. 6299-6308, 2017. https://doi.org/10.1109/cvpr.2017.502
  5. Feichtenhofer, C., Pinz, A., & Zisserman, A., "Convolutional two-stream network fusion for video action recognition," Proceedings of the IEEE conference, Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 1933-1941, 2016. https://doi.org/10.1109/cvpr.2016.213
  6. Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M., "Learning spatiotemporal features with 3d convolutional networks," Proceedings of the IEEE international conference, Computer Vision, Santiago, Chile, pp. 4489-4497, 2015. https://doi.org/10.1109/iccv.2015.510
  7. Soomro, K., Zamir, A. R., & Shah, M., "UCF101: A dataset of 101 human actions classes from videos in the wild," arXiv preprint arXiv:1212.0402. 2012.
  8. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011, November). "HMDB: a large video database for human motion recognition," Proceeding of the IEEE International conference, Computer Vision, Barcelona, Spain, pp. 2556-2563, 2011. https://doi.org/10.1109/iccv.2011.6126543
  9. Varol, G., Laptev, Cordelia Schmid "Long-term temporal convolutions for action recognition," Proceeding of the IEEE transactions on pattern analysis and machine intelligence, pp. 1510-1517, 2017. https://doi.org/10.1109/tpami.2017.2712608
  10. Reddy, K. K., & Shah, M., "Recognizing 50 human action categories of web videos," Machine Vision and Applications, Vol.24, No.5, pp.971-981, July 2013. https://doi.org/10.1007/s00138-012-0450-4
  11. Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L., "Large-scale video classification with convolutional neural networks," Proceedings of the IEEE conference, Computer Vision and Pattern Recognition, Columbus, USA, pp. 1725-1732, 2014. https://doi.org/10.1109/cvpr.2014.223
  12. Bottou, L., Neural networks: Tricks of the trade, Springer, pp. 421-436, Berlin, Heidelberg. 2012.
  13. N. Srivastava, G. Hinton, A. Krizhevesky and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," J. of Machine Learning Research, Vol. 15, No. 1, pp. 1929-1958, June 2014.