Journal of the Korea Computer Graphics Society (한국컴퓨터그래픽스학회논문지)

Korea Computer Graphics Society (한국컴퓨터그래픽스학회)
권호 표지
DOI QR코드

DOI QR Code

Real-time user motion generation and correction using RGBD sensor

RGBD 센서를 이용한 실시간 사용자 동작 생성 및 보정

  • Received : 2017.11.08
  • Accepted : 2017.12.07
  • Published : 2017.12.08
Download PDF
⟨ Previous Next ⟩

Abstract

We propose several techniques which can be employed in a 3D fitness program for monitoring and correcting user's posture. To implement a 3D fitness program, improved reference motion generating techniques and visualizing techniques are necessary. First, in order to understand the difference between the user and the reference movement of a professional, a retargeting method between two different body shapes are studied. Second, the problem of self-occlusion, which occurs when using a low-cost depth sensor to represent complex motions, is solved by using a sample database and time consistency. The system proposed in this paper evaluates the user's posture considering the physical characteristics of the user, and then provides feedback to the user.

본 연구는 사용자의 자세를 모니터링하고 수정하기 위해 3D 피트니스 프로그램에 사용할 수 있는 몇 가지 기술을 제안한다. 첫 번째로 사용자와 전문가의 레퍼런스 동작간의 차이를 알기위해 두 가지 다른 신체 구조 사이의 리타게팅 기법을 연구했다. 두번째로 복잡한 운동 동작을 표현하는데 생기는 저가형 깊이 센서의 문제인 자가가림(Self-occlusion) 문제를 예제 데이터베이스와 시간 일관성을 활용하여 해결하였다. 마지막으로 사용자가 취하는 자세가 코치의 자세와 얼마나 다른지 알 수 있도록 피드백 해주는 UI를 제작하였다. 본 논문에서 제안하는 시스템은 사용자의 신체적 차이를 고려하여 사용자의 자세를 평가 한 다음 사용자의 자세에 대한 피드백을 받을 수 있도록 한다.

Keywords

References

  1. Park, Sang Il, and Jessica K. Hodgins. "Capturing and animating skin deformation in human motion." ACM Transactions on Graphics (TOG). Vol. 25. No. 3. ACM, 2006.
  2. De Aguiar, Edilson, et al. "Marker-less deformable mesh tracking for human shape and motion capture." Computer Vision and Pattern Recognition, 2007. CVPR'07. IEEE Conference on. IEEE, 2007.
  3. Badler, Norman I., Michael J. Hollick, and John P. Granieri. "Real-Time control of a virtual human using minimal sensors." (1993).
  4. Lee, Jehee, et al. "Interactive control of avatars animated with human motion data." ACM Transactions on Graphics (TOG). Vol. 21. N0. 3. ACM, 2002.
  5. Chai, Jinxiang, and Jessica K. Hodgins. "Performance animation from low dimensional control signals." ACM Transactions on Graphics (TOG). Vol. 24. No. 3. ACM, 2005.
  6. Vlasic, Daniel, et al. "Articulated mesh animation from multi-view silhouettes." ACM Transactions on Graphics (TOG). Vol. 27. No. 3. ACM, 2008.
  7. Loper, Matthew, Naureen Mahmood, and Michael J. Black. "MoSh: motion and shape capture from sparse markers." ACM Transactions on Graphics (TOG) 33.6 (2014) 220.
  8. Shotton, Jamie, et al. "Real-time human pose recognition in parts from single depth images." Communications of the ACM 56.1 (2013): 116-124. https://doi.org/10.1145/2398356.2398381
  9. Baak, Andreas, et al. "A data-driven approach for real-time full body pose reconstruction from a depth camera." Consumer Depth Cameras for Computer vision. Springer London, 2013. 71-98.
  10. Caillette, Fabrice, Aphrodite Galata, and Toby Howard. "Real-Time 3-D Human Body Tracking using Variable Length Markov Models." BMVC. 2005.
  11. Kwok, Tsz-Ho, Kwok-Yun Yeung, and Charlie CL Wang. "Volumetric Template Fitting for Human Body Reconstruction from Incomplete Data." Journal of Manufacturing Systems 33.4 (2014): 678-689. https://doi.org/10.1016/j.jmsy.2014.05.009
  12. P. J. Besl and N. D. McKay, "A method for registration of 3-D shapes," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239-256, Feb. 1992. https://doi.org/10.1109/34.121791
  13. Yang Chen, Gerard Medioni, Object modelling by registration of multiple range images, In Image and Vision Computing, Volume 10, Issue 3, 1992, Pages 145-155, ISSN 0262-8856 https://doi.org/10.1016/0262-8856(92)90066-C