DOI QR코드

DOI QR Code

Understanding of 3D Human Body Motion based on Mono-Vision

단일 비전 기반 인체의 3차원 운동 해석

  • 한영모 (한양사이버대학교 컴퓨터공학과)
  • Received : 2011.01.27
  • Accepted : 2011.05.03
  • Published : 2011.08.31

Abstract

This paper proposes a low-cost visual analyzer algorithm of human body motion for real-time applications such as human-computer interfacing, virtual reality applications in medicine and telemonitoring of patients. To reduce cost of its use, we design the algorithm to use a single camera. To make the proposed system to be used more conveniently, we avoid from using optical markers. To make the proposed algorithm be convenient for real-time applications, we design it to have a closed-form with high accuracy. To design a closed-form algorithm, we propose an idea that formulates motion of a human body joint as a 2D universal joint model instead of a common 3D spherical joint model, without any kins of approximation. To make the closed-form algorithm has high accuracy, we formulates the estimation process to be an optimization problem. Thus-desined algorithm is applied to each joint of the human body one after another. Through experiments we show that human body motion capturing can be performed in an efficient and robust manner by using our algorithm.

본 논문은인간-컴퓨터 인터페이스, 가상현실의 의학 응용, 환자의 원격 모니터링과 같은 실시간 응용 분야에 적합한 인체 운동의 시각적 해석 알고리즘 (visual analyzer algorithm)을 제안한다. 본 알고리즘을 사용할 때의 비용을 줄이기 위해서, 단수의 카메라를 사용하도록 설계한다. 그리고 제안한 알고리즘을 좀 더 편리하게 사용할 수 있도록 하기 위해서 광학적 표시자의 사용을 피한다. 제안하는 알고리즘이 실시간 사용에 편리하도록 하기 위해서, 폐쇄적 형태가 되도록 설계한다. 폐쇄적 형태의 알고리즘을 설계하기 위해서, 인체의 각 관절을 기존의 3차원 관절 모델 대신 어떤 형태의 근사화도 사용하지 않고도 2차원 관절 모델로 공식화하는 아이디어를 제안한다. 그리고 이 폐쇄적 형태의 알고리즘이 높은 정확도를 갖게 하기 위해서, 계산 알고리즘을 최적화 문제로 공식화한다. 이렇게 해서 설계된 알고리즘을 인체의 각 관절에 차례대로 적용한다.

Keywords

References

  1. K. Rohr, "Incremental recognition of pedestrians from image sequences," Proc. IEEE Comput. Vision and Pattern Recognition, pp.8-13, New York City, June, 1993. https://doi.org/10.1109/CVPR.1993.341008
  2. J. Zhao, "Moving posture recognition from perspective projections of jointed figure motion," PhD thesis, University of Pennsylvania, 1993.
  3. M. Yamamoto and K. Koshikawa, "Human motion analysis based on a robot arm model," Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp.664-665, 1991. https://doi.org/10.1109/CVPR.1991.139772
  4. C. Bregler, J. Malik and K. Pullen, "Twist based acquisition and tracking of animal and human kinematics", International Journal of Computer Vision, vol.56, No.3, pp.179-194, 2004. https://doi.org/10.1023/B:VISI.0000011203.00237.9b
  5. C. J. Taylor, "Reconstruction of Articulated Objects from Point Correspondences in a Single Uncalibrated Image," Computer Vision and Image Understanding,, Vol.80, No.10, pp.349-363, October, 2000. https://doi.org/10.1006/cviu.2000.0878
  6. R. M. Murray, Z. Li, and S. S. Sastry, "A mathematical introduction to robotic manipulation," CRC Press, pp. 28, 1994.
  7. A. Zomet, D. Feldman, S. Peleg, and D. Weinshall, "Mosaicing new views: the crossed-slits projection," IEEE T. Pattern Analysis and Machine Intelligence, Vol.25, No.6, pp.741-754, June, 2003. https://doi.org/10.1109/TPAMI.2003.1201823
  8. I. Z. Emiris, "Solving polynomial equations: foundations, algorithms, and applications," Springer Verlag, pp.33, July, 2005.
  9. A. Gritai and M. Shah, "Tracking of human body joints using anthropometry," International Conference of Multimedia and Expo, pp.1037-1040, 2006.
  10. Neil J. Gordon, Simon Maskell, Thiagalingam Kirubarajan, "Efficient particle filters for joint tracking and classification", Signal and Data Processing of Small Targets 2002, pp.439-449, 2002.
  11. S. U. Lee and I. Cohen, "3D Hand and Fingers Reconstruction from Monocular View," Proc. 17th Int. Conf. Pattern Recognition (ICPR04), pp.231-236, 2004. https://doi.org/10.1109/ICPR.2004.1334529
  12. D. E. Difranco, Tat-Jen CHAM, and James M. REHG, "Reconstruction of 3-D Finger Motion from 2-D Correspondences," Proc. Conf. Computer Vision and Pattern Recognition, pp.307.314, 2001.