The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

Hierarchical Stereo Matching with Color Information

영상의 컬러 정보를 이용한 계층적 스테레오 정합

  • 김태준 (광운대학교 전자공학과 디지털 미디어 연구실) ;
  • 유지상 (광운대학교 전자공학과 디지털 미디어 연구실)
  • Published : 2009.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a hierarchical stereo matching with color information is proposed. To generate an initial disparity map, feature based stereo matching is carried out and to generate a final disparity map, hierarchical stereo matching is carried out. The boundary (edge) region is obtained by segmenting a given image into R, G, B and White components. From the obtained boundary, disparity is extracted. The initial disparity map is generated when the extracted disparity is spread to the surrounding regions by evaluating autocorrelation from each color region. The initial disparity map is used as an initial value for generating the final disparity map. The final disparity map is generated from each color region by changing the size of a block and the search range. 4 test images that are provided by Middlebury stereo vision are used to evaluate the performance of the proposed algorithm objectively. The experiment results show better performance compared to the Graph-cuts and Dynamic Programming methods. In the final disparity map, about 11% of the disparities for the entire image were inaccurate. It was verified that the boundary for the non-contiguous point was clear in the disparity map.

본 논문에서는 컬러 정보를 이용한 계층적 스테레오 정합 기법을 제안한다. 특징기반의 스테레오 정합 방법을 이용하여 초기 변이지도를 생성하고, 계층적 스테레오 정합 기법으로 최종 변이지도를 획득한다. 영상을 R, G, B, white 4개의 색상 성분으로 분할하여 영상의 경계(edge)를 추출하고, 추출된 경계에서 정합 창을 이용하여 변이(disparity)를 추정한다. 추정된 변이는 각 색상 성분에서 자기상관도(autocorrelation)에 따라 주변 영역으로 확산되어 초기 변이지도(disparity map)를 생성한다. 초기 변이지도는 최종 변이지도를 생성하기 위한 변이 탐색의 초기값으로 사용되고, 각 색상 성분에서 정합 창과 탐색 범위(search range)의 변화를 이용하여 최종 변이 지도를 생성시킨다. 본 논문에서는 Middlebury stereo vision의 4개의 실험 영상을 가지고 객관적 성능 평가를 하였다. 실험 결과 제안한 기법이 기존의 Graph-cuts와 Dynamic Programming 기법보다 우수한 성능을 보였다. 최종 변이지도의 부정확한 변이는 전체 영상에서 평균11% 존재했고, 변이지도에서 불연속점의 경계가 뚜렷한 것을 확인하였다.

Keywords

References

  1. Jong-Il Park, Seiki Inoue, 'Hierarchical Depth Mapping from Multiple Cameras,' Proceedings of the 9th International Conference on Image Analysis and Processing, Florence, vol. 1310, pp. 685-692, 1997 https://doi.org/10.1007/3-540-63507-6_261
  2. Cochran, S.D., Medioni, G., 3-D surface description from binocular stereo,' Pattern Analysis and Machine Intelligence, IEEE Transactions on,Vol. 14, Issue 10, Page(s):981–994, Oct. 1992 https://doi.org/10.1109/34.159902
  3. Y. Fisher, 'Fractal Image Compression,' Springer-verlage, New York, Inc. pp. 251∼,263, 1995
  4. Scharstein, D., Szeliski, R., Zabih, R., "A taxonomy and evaluation of dense two- frame stereo correspondence algorithms," Stereo and Multi-Baseline Vision, 2001. (SMBV 2001) Proceedings. IEEE Workshop on 9-10 Dec. 2001 Page(s):131 –140
  5. S. El-Etriby, A. Al-Hamadi, and B. Michaelis., "Dense stereo correspondence with slanted surface using phase-based algorithm," Industrial Electronics, 2007. IEEE International Symposium on 4-7 June 2007 Page(s):1807-1813 https://doi.org/10.1109/ISIE.2007.4374880
  6. A. Klaus, M. Sormann, K. Karner, 'Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure,' ICPR 2006. 18th International Conference on Volume3, 0-00 Page(s):15-18 https://doi.org/10.1109/ICPR.2006.1033
  7. Michael Bleyer and Margrit Gelautz, 'A Layered Stereo Algorithm using Segmentati- on and Global Visibility Constraits,' ICIP '04. Page(s):2997 - 3000 Vol. 5 https://doi.org/10.1109/ICIP.2004.1421743
  8. Brown, M.Z., Burschka, D., Hager, G.D., 'Advances in computational stereo,' Pattern Analysis and Machine Intelligence, IEEE Transactions on Vol. 25, Issue 8, Page(s):993 –1008, Aug. 2003 https://doi.org/10.1109/TPAMI.2003.1217603
  9. Fusiello, A., Roberto, V., Trucco, E., 'Efficient stereo with multiple windowing,' Computer Vision and Pattern Recognition, 1997. Proceedings, 1997 IEEE Computer Society Conference on 17-19 June 1997 Page(s):858 –863
  10. 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, Nov. 2001 https://doi.org/10.1109/34.969114
  11. P.F. Felzenszwalb and D.P. Huttenlocher, 'Efficient Belief Propagation for Early Vision,' Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2004
  12. Kuk-Jin Yoon, In-So Kweon, 'Locally adaptive support-weight approach for visual correspondence search,' Computer Vision and Pattern Recognition, 2005. IEEE Computer Society Conference on Volume2, Page(s):924 –931,20-25June2005 https://doi.org/10.1109/CVPR.2005.218
  13. O. Veksler, 'Fast Variable Window for Stereo Correspondence using Integral Images,' in Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 556-561, 2003
  14. R. C. Bolles, H. H. Baker, and M. J. Hannah, 'The JISCT stereo evaluation,' In DARPA Image Understanding Workshop, pages 263-274, 1993
  15. J. F. Canny, 'A Computational approach to edge detection,' IEEE TPAMI, 8(6):34-43, 1986 https://doi.org/10.1109/TPAMI.1986.4767851
  16. D. Terzopulos, 'Regularization of inverse visual problems involving discontinuities,' IEEE TPAMI, 8(4):413-424, 1986 https://doi.org/10.1109/TPAMI.1986.4767807