KIPS Transactions on Computer and Communication Systems (정보처리학회논문지:컴퓨터 및 통신 시스템)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Implementation of a Transition Rule Model for Automation of Tracking Exercise Progression

운동 과정 추적의 자동화를 위한 전이 규칙 모델의 구현

  • 정다니엘 (숭실대학교 정보통신소재융합학과) ;
  • 고일주 (숭실대학교 글로벌미디어학부)
  • Received : 2021.10.20
  • Accepted : 2021.12.14
  • Published : 2022.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Exercise is necessary for a healthy life, but it is recommended that it be conducted in a non-face-to-face environment in the context of an epidemic such as COVID-19. However, in the existing non-face-to-face exercise content, it is possible to recognize exercise movements, but the process of interpreting and providing feedback information is not automated. Therefore, in this paper, to solve this problem, we propose a method of creating a formalized rule to track the contents of exercise and the motions that constitute it. To make such a rule, first make a rule for the overall exercise content, and then create a tracking rule for the motions that make up the exercise. A motion tracking rule can be created by dividing the motion into steps and defining a key frame pose that divides the steps, and creating a transition rule between states and states represented by the key frame poses. The rules created in this way are premised on the use of posture and motion recognition technology using motion capture equipment, and are used for logical development for automation of application of these technologies. By using the rules proposed in this paper, not only recognizing the motions appearing in the exercise process, but also automating the interpretation of the entire motion process, making it possible to produce more advanced contents such as an artificial intelligence training system. Accordingly, the quality of feedback on the exercise process can be improved.

운동은 건강한 삶의 영위에 필요하지만 코로나19와 같은 전염병 유행 상황에서 비대면 환경에서 진행되는 것이 권장된다. 그러나 기존의 비대면 방식의 운동 콘텐츠에서는 운동 동작의 인식은 가능하지만 이를 해석해서 피드백 정보를 제공해주는 과정이 자동화되지 않았기 때문에 피드백이 트레이너의 눈대중으로 이루어지는 한계가 있다. 따라서 본 논문에서는 이러한 문제를 해결하기 위해서 운동 내용 및 이를 구성하는 동작을 추적하기 위해 공식화된 규칙을 만드는 방법을 제안한다. 이러한 규칙을 만들기 위해서는 전체적인 운동 내용의 진행 규칙을 먼저 만들고, 운동을 구성하는 동작의 추적 규칙을 만든다. 동작의 추적 규칙은 동작을 여러 단계로 나누고 단계를 나누는 키 프레임 자세를 정의하는 것에서 출발하여 키 프레임 자세로 대표되는 상태와 상태 간의 전이 규칙을 만듦으로써 생성될 수 있다. 이렇게 생성한 규칙은 모션 캡쳐 장비를 이용한 자세 및 동작 인식기술의 사용을 전제로 하며 이러한 기술 적용의 자동화를 위한 논리적인 전개에 사용된다. 본 논문에서 제안한 규칙을 사용하면 운동 과정에서 나타나는 동작을 인식하는 것뿐만 아니라 동작의 전 과정에 대한 해석의 자동화가 가능하여 인공지능 트레이닝 시스템 등 보다 진보된 콘텐츠 제작이 가능해진다. 이에 따라 운동 과정에 대한 피드백의 질을 높일 수 있다.

Keywords

References

  1. Quarantine System of Government of Republic of Korea [Internet], http://ncov.mohw.go.kr/baroView2.do?brdId=4&brdGubun=42.
  2. 'Sports Tok-Tok', Non Face-to-Face Sports Care Service, Gibbun Woori Sports Center [Internet], http://www.gibbunsports.or.kr/weel_bbs/board.php?bo_table=bbs_notice&wr_id=820&page=2.
  3. H. G. Lee, "A study on the gesture matching method for the development of gesture contents," Journal of Korea Game Society, Vol.13, No.6, pp.75-84, 2013. https://doi.org/10.7583/JKGS.2013.13.6.75
  4. S. H. Kim, Y. K. Lim, Y. H. Kim, and Y. H. Chai, "Partial movement authoring for a reconfigurable motion capture," Journal of Korean Institute of Information Scientists and Engineers (KIISE), Vol.46, No.10, pp.989-1000, 2019.
  5. J. A. Albert, V. Owolabi, A. Gebel, C. M. Brahms, U. Granacher, and B. Arnrich, "Evaluation of the pose tracking performance of the azure kinect and kinect v2 for gait analysis in comparison with a gold standard: A pilot study," Sensors, Vol.20, No.5104, pp.1-22, 2020. https://doi.org/10.1109/JSEN.2019.2959158
  6. F. Han, B. Reily, W. Hoff, and H. Zhang, "Space-time representation of people based on 3D skeletal data: A review," Computer Vision and Image Understanding, Vol.158, pp.85-105, 2017 https://doi.org/10.1016/j.cviu.2017.01.011
  7. S. Y. Kim, J. C. Park, K. S. Byun, and H. Y. Baek, "Biomechanical analysis of throw movement to second base in high school elite baseball catchers," Korean Journal of Sport Biomechanics, Vol.30, No.2, pp.165-172, 2020. https://doi.org/10.5103/KJSB.2020.30.2.165
  8. J. K. Lee, B. S. Heo, Y. J. Kim, and H. T. Lee, "Sports biomechanical analysis before and after applying weight belt during squat exercise," Journal of Fishries and Marines Sciences Education, Vol.28, No.4, pp.893-902, 2016. https://doi.org/10.13000/JFMSE.2016.28.4.893
  9. E. S. Shin, "Kinetics analysis of goal ball turning throw motion," Korean Journal of Sports Science, Vol.29, No.5, pp.1151-1160, 2020. https://doi.org/10.35159/kjss.2020.10.29.5.1151
  10. Carl Paoli and Anthony Sherbondy, "free+style, maximize sport and life performance with four basic movements," Victory Belt Publishing, pp.23-45, 2014.
  11. Daniel Chung, "Movement tracking and analysis for contactless exercise contents," Ph.D. Thesis, Soongsil University, 2021.
  12. M. O. Yoo and K. J. Park, "Comparison of the character movements from key-frame and motion capture animation," The Journal of the Korea Contents Association, Vol.8, No.9, pp.74-83, 2008. https://doi.org/10.5392/JKCA.2008.8.9.074
  13. S. M. Shin and J. L. Kim, "Reading body and movement: Theory and practice of the laban movement analysis," Ewha Womens University Press, 2010.
  14. A. Richard, H. Kuehne, and J. Gall, "Action sets: Weakly supervised action segmentation without ordering constraints," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.5987-5996, 2018.
  15. S. Dixon, R. Hansen, and W. Deneke, "Probabilistic grammar induction for long term human activity parsing," 2019 International Conference on Computational Science and Computational Intelligence (CSCI), pp.306-311, 2019.
  16. Formal Language, Wikipedia [Internet], https://ko.wikipedia.org/wiki/%ED%98%95%EC%8B%9D_%EB%AC%B8%EB%B2%95.
  17. Context-free Grammar, Wikipedia [Internet], https://ko.wikipedia.org/wiki/%EB%AC%B8%EB%A7%A5_%EC%9E%90%EC%9C%A0_%EB%AC%B8%EB%B2%95.
  18. Pushdown Automaton, Wikipedia [Internet], https://ko.wikipedia.org/wiki/%ED%91%B8%EC%8%9C%EB%8B%A4%EC%9A%B4_%EC%9E%90%EB%8F%99_%EA%B8%B0%EA%B3%84.
  19. Azure Kinect DK Hardware Specifications, Microsoft [Internet], https://docs.microsoft.com/ko-kr/azure/kinect-dk/hardware-specification.