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

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

영역 분할 기법과 경계 보존 변이 평활화를 이용한 스테레오 영상의 변이 추정

Disparity Estimation using a Region-Dividing Technique and Edge-preserving Regularization

  • 김한성 (연세대학교 전기전자공학과) ;
  • 손광훈 (연세대학교 전기전자공학과)
  • 발행 : 2004.11.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 스테레오 영상으로부터 자연스러우면서도 정확한 변이 정보를 추출하기 위한 변이 추정 알고리듬을 제안한다. 제안된 알고리듬은 영역 분할 기법을 이용한 계층적 변이 추정부와 편미분 방정식(PDE: Partial Differential Equation)을 이용한 에너지 기반 경계 보존 변이 평활화부로 구성되어 있다. 제안된 계층적 변이 추정 기법은 빠르면서도 신뢰도 있는 변이를 제공하며, 이러한 변이장은 정확도와 평활화도를 함께 고려한 에너지 모델의 최소화 기법에 의해 자연스럽고 정밀한 최종 변이장으로 추출된다. 에너지 모델의 최소화 과정은 대응되는 Euler-Lagrange 방정식으로 변형되어 유한차분법(FDM: Finite difference Method)을 이용한 근사화를 통해 구현된다. 실험을 통해 제안된 변이 추정 기법은 다양한 환경의 영상에 대해서도 자연스러우면서도 정확하고, 경계가 잘 보존된 변이를 추정해 낼 수 있음을 검증하였다.

We propose a hierarchical disparity estimation algorithm with edge-preserving energy-based regularization. Initial disparity vectors are obtained from downsampled stereo images using a feature-based region-dividing disparity estimation technique. Dense disparities are estimated from these initial vectors with shape-adaptive windows in full resolution images. Finally, the vector fields are regularized with the minimization of the energy functional which considers both fidelity and smoothness of the fields. The first two steps provide highly reliable disparity vectors, so that local minimum problem can be avoided in regularization step. The proposed algorithm generates accurate disparity map which is smooth inside objects while preserving its discontinuities in boundaries. Experimental results are presented to illustrate the capabilities of the proposed disparity estimation technique.

키워드

참고문헌

  1. R. M. Haralick and L.G. Shapiro, 'Image Matching,' Chap. 16 in Computer and Robot Vision, vol.2, Addison-Wesley, 1993
  2. D. Scharstein and R. Szeliski, 'A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms,' IJCV, vo1.47, pp.7-42, 2002 https://doi.org/10.1023/A:1014573219977
  3. http://www.middlebury.edu/stereo
  4. M. Brown, D. Burschka and G.D. Hager, 'Advances in Computational Stereo,' IEEE Trans. PAMI, vol.24, pp.993-1008, 2003 https://doi.org/10.1109/TPAMI.2003.1217603
  5. J. Y. Goulermas and P. Liatsis, 'Hybrid Symbiotic Genetic Optimisation for Robust Edge-based Stereo Correspondence,' Pattern Recognition, vol.34, pp.2477-2496, 2001 https://doi.org/10.1016/S0031-3203(00)00163-1
  6. T. Lindeberg, 'Scale-space Behavior of Local Extrema and Blobs,' JMIV, vol.1, pp.65-99, 1992 https://doi.org/10.1007/BF00135225
  7. S.T. Barnard, 'Stochastic Stereo Matching Over Scale,' IJCV, vo1.3, pp.17 - 32, 1989 https://doi.org/10.1007/BF00054836
  8. L. Robert and R. Deriche, 'Dense Depth Map Reconstruction: A Minimization and Regularization Approach which Preserves Discontinuities,' LNCS, vol.1064, pp.439-451, 1996
  9. O. Faugeras and R. Keriven, 'Variational PrincipIes, Surface Evolution, PDE's, Level Set Methods and the Stereo Problem,' IEEE Trans. Image Proc., vol.7, pp.336 - 344, 1998 https://doi.org/10.1109/83.661183
  10. M. Mozerov, V. Kober and T. Choi, 'Improved Motion Stereo Matching based on a Modified Dynamic Programming,' Optical Eng, vol.40, pp.2234-2239, 2001 https://doi.org/10.1117/1.1404992
  11. C. J. Tasi and A. K. Katsaggelos, ' Dense Disparity Estimation with a Divide-and-Conquer Disparity Space Image Technique,' IEEE, Trans. Multimedia, Vol.1, No.1, pp.18-29, March, 1999 https://doi.org/10.1109/6046.748168
  12. K. Nishihara, 'Practical Real-time Imaging Stereo Matcher,' Optical. Eng., vol.23, pp.536 - 545, 1984
  13. R.E.H. Franich, 'Disparity Estimation in Stereoscopic Digital Images,' Doctoral dissertation, Technische Universiteit Delft, 1996
  14. O. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint, The MIT Press, London, 2001
  15. D. V. Papadimitriou and T. J. Dennis, 'Epipolar Line Estimation and Rectification for Stereo Image Pairs,' IEEE Transactions on Image Processing, Vol.5, No.4, pp.672-676, 1996 https://doi.org/10.1109/83.491345
  16. A. L. Yuille and T. Poggio. 'A Generalized Ordering Constraint for Stereo Correspondence,' A.I. Memo 777, AI Lab, MIT, 1984
  17. J. Canny, 'A Computational Approach to Edge Detection,' IEEE Tans. PAMI, vol.8, pp.679-698, 1986 https://doi.org/10.1109/TPAMI.1986.4767851
  18. E. Izquierdo, 'Stereo Matching for Enhanced Telepresence in 3D Videocommunications,' IEEE Trans. CSVT, vol.7, pp.629 - 643, 1997 https://doi.org/10.1109/76.611174
  19. J. Weickert, 'A Review of Nonlinear Diffusion Filtering,' LNCS, vol.1252, pp.3-28, 1997
  20. S. Geman and D.E. McClure, 'Bayesian Image Analysis: An Application to Single Photon Emission Tomography,' Proc. Statistical Computation Section, Amer. Statistical Assoc., Washington, DC, pp.12 - 18, 1985
  21. Y. Boykov, O. Veksler and R. Zabih, 'Fast Approximate Energy Minimization via Graph Cuts,' IEEE Trans. PAMI, vol.23, pp.1222-1239, 2001 https://doi.org/10.1109/34.969114
  22. S. Birchfield and C. Tomasi, 'Depth Discontinuities by Pixel-to-Pixel Stereo,' International Journal of Computer Vision, Vol.35, No.3, pp.269-293, December, 1999 https://doi.org/10.1023/A:1008160311296
  23. L. Zitnick and T. Kanade, 'A Cooperative Algorithm for Stereo Matching and Occlusion Detection,' IEEE Trans. PAMI, vol.22, pp.675-684, 2000 https://doi.org/10.1109/34.865184
  24. K. Muhlmann, D. Maier, J. Hesser and R. Manner, 'Calculating Dense Disparity Maps from Color Stereo Images, an Efficient Implementation,' IJCV, vol.47, pp.79-88, 2002 https://doi.org/10.1023/A:1014581421794