DOI QR코드

DOI QR Code

Markerless Motion Capture Algorithm for Lizard Biomimetics

소형 도마뱀 운동 분석을 위한 마커리스 모션 캡쳐 알고리즘

  • Kim, Chang Hoi (Nuclear Technology Convergence Division, Korea Atomic Energy Research Institute) ;
  • Kim, Tae Won (Nuclear Technology Convergence Division, Korea Atomic Energy Research Institute) ;
  • Shin, Ho Cheol (Nuclear Technology Convergence Division, Korea Atomic Energy Research Institute) ;
  • Lee, Heung Ho (Electrical Engineering Division, Chungnam National University)
  • 김창회 (한국원자력연구원 원자력융합기술개발부) ;
  • 김태원 (한국원자력연구원 원자력융합기술개발부) ;
  • 신호철 (한국원자력연구원 원자력융합기술개발부) ;
  • 이흥호 (충남대학교 전기공학과)
  • Received : 2013.07.11
  • Published : 2013.09.25

Abstract

In this paper, a algorithm to find joints of a small animal like a lizard from the multiple-view silhouette images is presented. The proposed algorithm is able to calculate the 3D coordinates so that the locomotion of the lizard is markerlessly reconstructed. The silhouette images of the lizard was obtained by a adaptive threshold algorithm. The skeleton image of the silhouette image was obtained by Zhang-Suen method. The back-bone line, head and tail point were detected with the A* search algorithm and the elimination of the ortho-diagonal connection algorithm. Shoulder joints and hip joints of a lizard were found by $3{\times}3$ masking of the thicked back-bone line. Foot points were obtained by morphology calculation. Finally elbow and knee joint were calculated by the ortho distance from the lines of foot points and shoulder/hip joint. The performance of the suggested algorithm was evaluated through the experiment of detecting joints of a small lizard.

본 논문에서는 마커를 부착하기 어려운 소형도마뱀의 관절을 측정하기 위한 마커리스 모션 캡쳐 알고리즘을 제안하였다. 제안한 알고리즘에서는 먼저 스테레오 비젼과 같은 다시점 영상에서 적응적 이진화를 통해 도마뱀의 실루엣 영상을 획득하고 세선화를 수행하여 도마뱀의 뼈대 영상을 획득한다. 이후, 직교-대각 성분 제거 알고리즘 및 A* Search를 통해 머리와 꼬리점, 및 머리와 꼬리를 잇는 척추라인을 구한다. 어깨관절과 고관절의 좌표는 $3{\times}3$ 마스크를 이용하여 척추라인과 다리가 만나는 지점을 구하여 획득하고 모폴로지 닫기 영상을 통해 발바닥 좌표들을 검출한다. 최종적으로 각각의 다리에서 어깨관절 및 고관절 좌표와 발바닥 좌표를 잇는 직선과 해당 다리의 뼈대 좌표간의 직교 거리 비교를 통해 무릎과 팔꿈치 좌표를 구한다. 최종적으로 제안한 알고리즘으로 검출된 각 관절의 다시점 영상의 2차원 좌표들로부터 각 관절의 3차원 좌표를 복원한다. 실제 도마뱀을 촬영한 스테레오 영상에 제안된 알고리즘을 적용하여 2차원 주요 관절 지점 검출 및 3차원 복원을 수행하여 제안된 알고리즘의 성능을 검증하였다.

Keywords

References

  1. Floyd. S., Keegan. T., Palmisano J, Sitti M, "A novel water running robot inspired by basilisk li zards.", Proc. of the IEEE/ RSJ intl. conf. on in tell. robot. and sys, pp. 5430-5436, Beijing, China, Oct. 2006.
  2. Jason. K. Moore, J.D.G. Kooijman, A.L. Schwab, "Rider motion identification during normal bicycli ng by means of principal component analysis", Multibody Syst Dyn, 25. pp. 225-244, 2011. https://doi.org/10.1007/s11044-010-9225-8
  3. Luca Ballan, Guido Maria Cortelazzo, "Marker-le ss motion capture of skinned models in a four c amera set-up using optical flow and silhouettes .", Proc. of 3D PVT'08, pp. 18 - 20, Georgia Ins titute of Technology, Atlanta, GA, USA, June 2008.
  4. Laurentini. A., "The Visual Hull Concept for Sil houette Based Image Understanding.", IEEE PAMI, Vol. 16, no. 2, pp. 150-162. 1994. https://doi.org/10.1109/34.273735
  5. Kutulakos, K. N. and Seitz, S. M., "A theory of shape by space carving", International Journal o f Computer Vision, 38(3), pp. 199-218, 2000. https://doi.org/10.1023/A:1008191222954
  6. R. Hartley and A. Zisserman., "Multiple View Geometry in Computer Vision.", Cambridge University Press, 2000.
  7. Gonzales. R.C. Woods. R.E., "Digital Image Processing.", Addison-Wesley, 2nd edition, Sep. 1993.
  8. Zhang. T. and Suen. C., "A fast parallel algorithm for thinning digital patterns.", Communications 27, pp. 235-239. 1984.
  9. S. Russell and P. Norvig., "Artificial Intelligence: AModern Approach." Prentice-Hall, 1995.
  10. Krishna, K., and M. Narasimha Murty., "Genetic K-means algorithm." IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 29.3 pp. 433-439, 1999. https://doi.org/10.1109/3477.764879
  11. Sangbae Kim, Matthew Spenko, Salomon Trujillo, Barrett Heyneman, Daniel Santos, Mark R. Cutkosky, "Smooth Vertical Surface Climbing Wit h Directional Adhsion", IEEE Trnasaction on Robotics, Vol. 24, No. 1, pp. 65-74, 2008. https://doi.org/10.1109/TRO.2007.909786
  12. C. Wright, A. Buchan, B. Brown, J. Geist, M. S chwerin, D. Rollinson, M. Tesch and H. Choset, "Design and Architecture of the Unified Modular Snake Robot", Proc. IEEE Int. Conf. Robotics and Automation (ICRA) 2012, pp. 4347-4354, 2012
  13. http://usavision.com/2011/11/17/us-airforce-develops-fly-bot/
  14. http://techcrunch.com/2011/06/01/darpa-video-sho ws-the-evolution-of-the-hummingbot-namo-uav/
  15. Ho Yeol Choi, In Kyu Park, "Multi-view Image Deblurring for 3D Shape Reconstruction", Journal of the Institute of Elecronics Engineers of Korea, Vol. 49, No. 11, pp. 47-55, 2012.
  16. HeeDong Kim, SeongDae Kim, Refinement of Depth Map for Shape from Silhouette Method and Multi-view Images", 2006 IEEK Autumn Conference, pp. 643-646, 2006.