Visual Tracking Using Monte Carlo Sampling and Background Subtraction

확률적 표본화와 배경 차분을 이용한 비디오 객체 추적

  • Kim, Hyun-Cheol (Dept. of Image Engineering. Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University) ;
  • Paik, Joon-Ki (Dept. of Image Engineering. Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University)
  • 김현철 (중앙대학교 첨단영상대학원) ;
  • 백준기 (중앙대학교 첨단영상대학원)
  • Received : 2010.12.09
  • Accepted : 2011.05.06
  • Published : 2011.09.25

Abstract

This paper presents the multi-object tracking approach using the background difference and particle filtering by monte carlo sampling. We apply particle filters based on probabilistic importance sampling to multi-object independently. We formulate the object observation model by the histogram distribution using color information and the object dynaminc model for the object motion information. Our approach does not increase computational complexity and derive stable performance. We implement the whole Bayesian maximum likelihood framework and describes robust methods coping with the real-world object tracking situation by the observation and transition model.

본 논문에서는 배경 차분에 의해 객체를 검출하고 확률적으로 표본화된 입자 필터링(particle filtering)기법을 사용한 다중객체 추적 기법을 제안한다. 확률적으로 표본화된 입자들을 사용하여 다중 객체에 독립적으로 적용할 때 발생하는 계산 복잡도(computational complexity)를 감소시키는 동시에 안정적인 추적을 가능하게 하였다. 객체의 색상정보를 사용한 히스토그램 분포에 의한 관측 모델(observation model)을 구성하고 객체의 움직임 정보를 위해 동적 모델을 공식화하여 영상을 해석하였다. 전체적인 추적 시스템은 베이시언 최대 우도 기법(Bayesian maximum likelihood method)을 근간으로 하되, 입자 필터링을 객체 추적에 적용하여 실용적인 현실 객체 추적 상황에도 강건하게 대처할 수 있음을 실험을 통해서 증명하였다.

Keywords

References

  1. A. Yilmaz and O. Javed, "Object Tracking: A Survey," ACM Computing Surveys, vol. 38, no. 4, Article 13, December 2006.
  2. J. Kwon and K. Lee, "Tracking of a Non-Rigid Object via Patch-based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo Sampling," Proc. IEEE Conf. Computer Vision, Pattern Recognition, pp.1208-1215, Miami, FL, USA, June 2009.
  3. Z. Khan, T. Balch, and F. Dellaert, "MCMC-Based Particle Filtering for Tracking a Variable Number of Interacting Targets," IEEE Trans. Pattern Analysis, Machine Intelligence, vol. 27, no. 11, pp-1819-1805, November, 2005.
  4. K. Smith, D. Gatica-Perez, and J. Odobez, "Using Particles to Track Varying Numbers of Interacting People," Proc. IEEE Conf. Computer Vision, Pattern Recognition, pp.962-969, San Diego CA, USA, June 2005.
  5. A. Jepson and D. Fleet, "Robust Online Appearance Models for Visual Tracking," IEEE Trans. Pattern Analysis, Machine Intelligence, vol. 25, no.10, pp. 1296-1311, October, 2005.
  6. R. Hess and A. Fern, "Discriminatively Trained Particle Filters for Complex Multi-Object Tracking," Proc. IEEE Conf. Computer Vision, Pattern Recognition, pp.240-247, Miami, FL, USA, June 2009.
  7. K. Okuma, A. Taleghani, N. De Freitas, "A Boosted Particle Filter: Mutitarget Detection and Tracking", European Conference on Computer Vision, pp. 28-39, Prague, Czech, May 2004.
  8. D. Comaniciu, V. Ramesh, V. Meer, "Real-time Tracking of Non-rigid Objects using Mean Shift", IEEE Conference on Computer Vision and Pattern Recognition, pp. 142-151, Hilton Head, South Carolina, USA, June 2000.
  9. P. Perez, C. Hue, J Vermaak, M. Gangnet, "Color-Based Probabilistic Tracking" European Conference on Computer Vision, pp. 661-675, Copenhagen, Denmark, May 2002.