DOI QR코드

DOI QR Code

Object Tracking Using Particle Filters in Moving Camera

움직임 카메라 환경에서 파티클 필터를 이용한 객체 추적

  • 고병철 (계명대학교 컴퓨터공학과 CVPR 연구실) ;
  • 남재열 (계명대학교 컴퓨터공학과 CVPR 연구실) ;
  • 곽준영 (계명대학교 컴퓨터공학과 CVPR 연구실)
  • Received : 2012.02.09
  • Accepted : 2012.04.27
  • Published : 2012.05.30

Abstract

This paper proposes a new real-time object tracking algorithm using particle filters with color and texture features in moving CCD camera images. If the user selects an initial object, this region is declared as a target particle and an initial state is modeled. Then, N particles are generated based on random distribution and CS-LBP (Centre Symmetric Local Binary Patterns) for texture model and weighted color distribution is modeled from each particle. For observation likelihoods estimation, Bhattacharyya distance between particles and their feature models are calculated and this observation likelihoods are used for weights of individual particles. After weights estimation, a new particle which has the maximum weight is selected and new particles are re-sampled using the maximum particle. For performance comparison, we tested a few combinations of features and particle filters. The proposed algorithm showed best object tracking performance when we used color and texture model simultaneously for likelihood estimation.

본 연구에서는 움직이는 CCD 카메라로부터 입력된 영상에서 색상 및 질감 성분을 기반으로 하는 파티클 필터를 이용하여 실시간으로 객체를 추적할 수 있는 알고리즘을 제안한다. 초기 영상에서 추적하고자 하는 객체를 선택하면 이를 타깃 파티클로 결정하고, 타깃 파티클로 부터 추적을 위한 초기 상태가 모델링 된다. 이후 프레임부터 N개의 파티클들이 랜덤 분포로 생성되고 각 파티클로 부터 질감 정보인 로컬 CS-LBP (Centre Symmetric Local Binary Patterns)모델과 색상 분포 모델이 특징 모델로 사용된다. 각 특징 모델에 대해 바타차리야 (Bhattacharyya) 거리를 사용하여 각 파티클과 타깃 파티클 간의 특징 관측 우도(likelihood)를 구하고 이를 각 파티클의 가중치로 설정 한다. 각 파티클의 가중치를 기반으로 가중치가 가장 높은 파티클을 새로운 타깃으로 설정하고, 각 파티클들을 재 샘플링 한다. 본 실험결과에서는 여러 가지 특징을 조합하여 실험을 하였고, 그 결과 색상 분포 모델과 로컬 CS-LBP를 조합했을 때 추적 성능이 가장 우수한 것을 확인할 수 있었다.

Keywords

References

  1. C. Yang, R. Duraiswami, and L. Davis "Fast Multiple Object Tracking via a Hierarchical Particle Filter," International Conference on Computer Vision, Vol. 1, pp.212-219, 2005.11
  2. D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. on Pattern Analysis and Machine Intelligence, Vo. 25, No. 5, pp. 564-577, 2003. https://doi.org/10.1109/TPAMI.2003.1195991
  3. A. Doucet, N. D. Freitas, and N. Gordon, "Sequential Monte Carlo Methods in Practice," Springer-Verlag, New York, 2001
  4. K. Deguchi, O. Kawanaka, and T. Okatani, "Object tracking by the mean-shift of regional color distribution combined with the particle-filter algorithm," 17th International Conference on Pattern Recognition, Vol. 3, pp. 506-509, 2004.
  5. M. Z. Islam, C. M. Oh, and C. W. Lee, "Video Based Moving Object Tracking by Particle Filter", International Journal of Signal Processing, Image Processing and Pattern, Vol. 2, No. 1, pp.120-132, 2009.
  6. D. A. Klein, D. Schulz, S. Frintrop, and A. B. Cremers, "Adaptive Real-Time Video-Tracking for Arbitrary Objects", IEEE/RSJ International Conference of Intelligent Robots and Systems, pp. 772-777, 2010.
  7. D. Sidibe, D. Fofi, and F. Meriaudeau, "Using visual saliency for object tracking with particle filters," 18th European Signal Processing Conference, pp. 1-5, 2010.
  8. Z. H. Khan, I. Y. Gu, and A. G. Backhouse, "Robust Visual Object Tracking Using Multi-Mode Anisotropic Mean Shift and Particle Filters," IEEE Trans. on Circuits and Systems for Video Technology, Vol. 21, pp.74-87, 2011. https://doi.org/10.1109/TCSVT.2011.2106253
  9. D. P. Chau, F. Bremond, M. Thonnat, and E. Corvee, "Robust Mobile Object Tracking Based on Multiple Feature Similarity and Trajectory Filtering," International Conference on Computer Vision Theory and Applications, pp. 1-7, 2011.
  10. K. Nummiaro, E.K. Meier, and L.V. Cool, "An adaptive color-based particle filter," Image and Vision Computing, Vol. 21, No. 1, pp. 99-110, 2003. https://doi.org/10.1016/S0262-8856(02)00129-4
  11. B. C. Ko, S. H. Kim, J. Y. Nam, "X-ray Image Classification using Random Forests with Local Wavelet-Based CS-Local Binary Patterns," Journal of Digital Imaging, Vol. 24, pp. 1141-1151, Nov. 2011 https://doi.org/10.1007/s10278-011-9380-3
  12. M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, "A tutorial on particle filters for online nonlinear/non-gaussian Bayesian tracking," IEEE Trans. on Signal Processing, Vol. 5, No. 2, pp. 174-188, 2002.
  13. D. Comaniciu, V. Ramesh, and P. Meer. "Real-Time Tracking of Non-Rigid Objects using Mean Shift," IEEE International Conference on Computer Vision and Pattern Recognition, pp. 142-149, 2000.
  14. F. Yin, D. Markris, and S. Velastin, "Performance evaluation of object tracking algorithms," IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, pp. 1-8, 2007.

Cited by

  1. Object Segmentation/Detection through learned Background Model and Segmented Object Tracking Method using Particle Filter vol.20, pp.8, 2016, https://doi.org/10.6109/jkiice.2016.20.8.1537