Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Stereo Matching using Belief Propagation with Line Grouping

신뢰확산 알고리듬을 이용한 선 그룹화 기반 스테레오 정합

  • Kim Bong-Gyum (School of Electronic Engineering, Kumoh National Institute of Technology) ;
  • Eem Jae-Kwon (School of Electronic Engineering, Kumoh National Institute of Technology)
  • 김봉겸 (금오공과대학교 전자공학부) ;
  • 임재권 (금오공과대학교 전자공학부)
  • Published : 2005.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

In the Markov network which models disparity map with the Markov Random Fields(MRF), the belief propagation algorithm is operated by message passing between nodes corresponding to each pixel. The initial message value is converged by iterations of the algorithm and the algorithm requires many iterations to get converged messages. In this paper, we simplify the algorithm by regarding the objects in the disparity map as combinations of lines with same message valued nodes to reduce iterations of the algorithm.

변이 영상을 마코브 랜덤필드(MRF)로 모델링한 마코브 네트워크에서 신뢰확산 알고리듬은 각 화소에 대응되는 노드들 사이에 메시지를 전달하는 방식으로 이루어진다. 최초 메시지는 알고리듬의 반복을 통해 특정한 값으로 수렴하게 되며, 수렴된 값을 얻기 위해서는 많은 알고리듬의 반복이 필요하다. 본 논문에서는 알고리듬의 반복을 줄이기 위해 영상내 물체들을 선들의 조합 구성으로 보고 각각의 선들은 같은 메시지를 갖는 노드들의 집합으로 간주하여 기존의 신뢰확산 알고리듬을 단순화하였다.

Keywords

References

  1. M. Z. Brown, D. Burschka, and G.D. Hager, 'Advance in Computational Stereo', IEEE Trans. Pattern Analysis and Machine Intelligence, vol.25, no.8, pp.993-1008, 2003 https://doi.org/10.1109/TPAMI.2003.1217603
  2. Y. Boykov, O. Veksler, and R. Zabih, 'Fast Approximate Energy Minimization via Graph Cuts', IEEE Trans. Pattern Analysis and Machine Intelligence, vol.23, no.11, pp,1222-1239, 2001 https://doi.org/10.1109/34.969114
  3. J. Sun, H-Y Shum, and N-N Zheng, 'Stereo Matching Using Belief Propagation', IEEE Trans. Pattern Analysis and Machine Intelligence, vol.25, no.7, pp.787-800, 2003 https://doi.org/10.1109/TPAMI.2003.1206509
  4. P. Smyth, 'Belief Networks, Hidden Markov, Models, and Markov Random Fields: a Unifying View', Pattern Recognition Letters, vol.18, pp,1261-1268, 1997 https://doi.org/10.1016/S0167-8655(97)01050-7
  5. J. Pearl, Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, Morgan Kaufmann Publishers, 1998
  6. D. Scharstein and R. Szeliski, 'A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms', Int'l J. Computer Vision, vol.47, no.1, pp.7-42, 2002 https://doi.org/10.1023/A:1014573219977
  7. M. F. Tappen and W.T. Freeman, 'Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters', Proc. IEEE Int'l Conf. Computer Vision, vol.2, pp.900-906, 2003