한국정보과학회논문지:컴퓨팅의 실제 및 레터 (Journal of KIISE:Computing Practices and Letters)

한국정보과학회 (Korean Institute of Information Scientists and Engineers)
권호 표지

MLESAC 움직임 추정 기반의 파티클 필터를 이용한 3D 얼굴 추적

3D Face Tracking using Particle Filter based on MLESAC Motion Estimation

  • 성하천 (연세대학교 컴퓨터과학과) ;
  • 변혜란 (연세대학교 컴퓨터과학과)
  • 투고 : 2009.12.24
  • 심사 : 2010.04.01
  • 발행 : 2010.08.15
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

3D 얼굴 추적(Face tracking)은 보안감시, HCI(Human-Computer Interface), 엔터테인먼트(Entertainment)등 컴퓨터 비전과 관련된 여러 분야의 핵심 기술로서 많은 연구가 진행되고 있다. 하지만, 광범위한 응용분야에도 불구하고 3D 얼굴 추적의 기본적인 높은 연산 비용으로 인하여 그 응용 분야가 모바일 단말기 등의 저 사양 플랫폼에는 많은 한계가 있어왔다. 본 논문에서는 이러한 3D얼굴 추적의 연산 비용을 효과적으로 해결하고 폭 넓게 응용 분야를 확대하기 위하여 MLESAC(Maximum Likelihood Estimation by Sampling Consensus)을 이용한 움직임 추정(Motion Estimation) 기법과 기존의 파티클 필터(Particle Filter)를 결합하여 실행 속도 면에서 빠르면서도 성능 면에서도 우수한 3D 얼굴 추적 알고리즘을 제안한다.

3D face tracking is one of essential techniques in computer vision such as surveillance, HCI (Human-Computer Interface), Entertainment and etc. However, 3D face tracking demands high computational cost. It is a serious obstacle to applying 3D face tracking to mobile devices which usually have low computing capacity. In this paper, to reduce computational cost of 3D tracking and extend 3D face tracking to mobile devices, an efficient particle filtering method using MLESAC(Maximum Likelihood Estimation SAmple Consensus) motion estimation is proposed. Finally, its speed and performance are evaluated experimentally.

키워드

참고문헌

  1. M. Cascia, S. Sclaroff, V. Athitsos, Fast, reliable head tracking under varying illumination: an approach based on registration of texture-mapped 3d model," IEEE Trans. Pattern Anal. Mach. Intell., vol.22, no.4, pp.322-336 2000. https://doi.org/10.1109/34.845375
  2. J. Xiao, T. Kanade, J. Cohn, "Roust full motion recovery of head by dynamic templates and reregistration technique," Int. J. Imaging Syst. Technol., vol.13, pp.85-94, 2003. https://doi.org/10.1002/ima.10048
  3. G. Aggaward, A. Veeraraghavan, R. Chellappa, "3d facial pose tracking in uncalibrated videos," International Conference on Pattern Recognition and Machine Intelligence, vol.3776, pp.515-520, 2005.
  4. S. Chio, D. Kim, "Robust head tracking using 3D ellipsoidal head model in particle filter," Pattern Recognition, vol.41, no.9, pp.2901-2915, 2008. https://doi.org/10.1016/j.patcog.2008.02.002
  5. J. Sung, T. Kanade, D. Kim, "Pose Robust Face Tracking by Combining Active Appearance Models and Cylinder Head Models," Int. Journal of Computer Vision, vol.80, pp.260-274, 2008. https://doi.org/10.1007/s11263-007-0125-1
  6. L. Lu, X. Dai, and gd Hager, "Efficient particle filtering using. RANSAC with application to 3D face tracking," Image Vision. Computing, vol.24, no.6, pp.581-592, 2006. https://doi.org/10.1016/j.imavis.2005.08.003
  7. A. Doucet, S.J. Godsill, C. Andrieu, "On sequential Monte Carlo sampling methods for Bayesian filtering," Statist. Comput., vol.10, no.3, pp.197-209, 2000. https://doi.org/10.1023/A:1008935410038
  8. M. Isard and A. Blake, "Condensation-conditional density propagation for visual tracking," Int. Journal of Computer Vision, vol.29, no.1, pp.5-28, 1998. https://doi.org/10.1023/A:1008078328650
  9. P.H.S. Torr and A. Zisserman, "MLESAC: a new robust estimator with application to estimating image geometry," Computer Vision and Image Understanding, vol.78, no.1, pp.138-156, 2000. https://doi.org/10.1006/cviu.1999.0832
  10. H. Sung, H. Byun, "Fast 3D face tracking using feature selection and particle filter," Proc. of the KIISE Korea Computer Congress 2009, vol.36, no.1(C), pp.546-551, 2009. (in Korean)