Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Stereo Matching Method Based on the Dynamic Programming to Reduce the Streaking Phenomena

스트리킹 현상을 감소시키기 위한 다이내믹 프로그래밍 기반의 스테레오 정합 방법

  • 박장호 (광운대학교 실감미디어 연구소) ;
  • 최현준 (안양대학교 정보통신공학과) ;
  • 서영호 (광운대학교 실감미디어 연구소) ;
  • 김동욱 (광운대학교 실감미디어 연구소)
  • Received : 2010.01.14
  • Accepted : 2010.02.20
  • Published : 2010.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

The dynamic programming based methods, a kind of globally optimizing stereo matching methods, has the inherent advantage that the occlusion regions can be found during the process. But it also has a serious drawback of streaking phenomena. This paper focuses on reducing the streaking phenomena by adjusting the penalties in calculating the cost matrix and re-establishing the optimal path in the back-tracing process using the boundary information of the image. Especially we use a pixel expansion method in re-establishing the path, which is the results from expanding the pixel information of the ones just left the boundaries. Experiments with the four image pairs provided by the Middlebury site showed the results that the proposed method has the disparity error ratio of 6.33% and the rank is 29, which is competitive to the best method among the previously published dynamic programming based methods.

다이내믹 프로그래밍 기반의 스테레오 정합 기법은 전체 영상 또는 한 열의 영상정보를 특정 화소의 정합에 모두 사용하는 전역-대상 기법으로 정합 연산시 폐색영역을 찾을 수 있다는 장점을 가지고 있다. 본 논문에서는 영상의 특징점, 즉 경계정보를 추가로 사용하여 스트리킹 현상을 감소시키고 변이지도의 오차율을 줄이는 방법을 제안한다. 이 방법은 기본적으로 경로선택에 있어서의 페널티를 대상화소의 주변 화소들에 따라 조정한다. 또한 경계정보를 사용하여 특정 화소에 대한 신뢰성을 재검사하는데, 이 신뢰성 재검사는 역추적과정에서 실시한다. Middlebury에서 제공하는 네 쌍의 영상으로 실험한 결과 제안한 기법의 에러율을 6.33% 29위에 랭크됐다. 이 결과는 이전에 제안된 다이내믹 프로그래밍 기반의 정합 기법 중 가장 좋은 결과이다.

Keywords

Acknowledgement

Grant : 대화형 디지털 홀로그램 통합서비스 시스템의 구현을 위한 신호처리 요소 기술 및 SoC 개발

Supported by : 한국산업기술평가관리원

References

  1. D. SchSarstein and R. Szeliski, "A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms," International Journal of Computer Vision, Vol. 47, Issue 1-3, pp. 7-42, April 2002. https://doi.org/10.1023/A:1014573219977
  2. ISO/IEC MPEG & ITU-T VCEG, "Multiview Video plus Depth (MVD) Format for Advanced 3D Video Systems," JVT-W100, April 2007.
  3. Federico Tombari, Stefano Mattoccia, and Luigi Di Stefano, "Segmentation-Based Adaptive Support for Accurate Stereo Correspondence," LNCS 4872, pp.427-438, 2007.
  4. Tae-june Kim, Ji-sang Yoo, "Hierarchical Stereo Matching with Color Information", 한국통신학회논문지, 제34권, 제3호, pp.279-287, 2009.
  5. Z. F. Wang and Z. G. Zheng, "A Region Based Stereo Matching Algorithm Using Cooperative Optimization," IEEE Conf. on Computer Vision and Pattern Recognition. pp. 1-8, June 2008.
  6. Q. Yang, et al., "Spatial-Depth Super Resolution for Range Images," IEEE Conf. on Computer Vision and Pattern Recognition. pp. 17-22, June 2007.
  7. Y. Taguchi, B. Wilburn, and C. L. Zitnick, "Stereo Reconstruction with Mixed Pixels using Adaptive Over-Segmentation," IEEE Conf. on Computer Vision and Pattern Recognition, June 2008.
  8. Q. Yang, et al, "Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation, and Occlusion Handling", IEEE Trans. on Pattern Analysis and Machine Intelligence. Vol. 31, No. 3, pp. 495-504, March 2009.
  9. V. Kolmogorov and R. Zabih, "Computing Visual Correspondence with Occlusions via Graph Cuts," ICCV2001, Vol. 2, pp. 508-515, 2001.
  10. H. Chen, "Stereo Matching by Dynamic Programming Based on Occlusion Detection," IEEE Intl. Conf. on Mechatronics and Automation, pp. 2445-2449, 2007.
  11. 주재흠, 오종규, 설성욱, 이철훈, 남기곤, "에지 정보를 강조한 동적계획법에 의한 스테레오 정합," 대한전자공학회논문지, 제36권, 제10호, pp. 123-131, 1999.
  12. J. Zhas and J. Katupitiya, "A Dymanic Programming Approach Based Stereo Vision Algorithm Improving Object Boarder Performance," IEEE/ERJ Intl. Conf. on Intelligent Robotics and Systems, pp. 5315-5320, Oct. 2006.
  13. O. Veksler, "Stereo Correspondence by Dynamic Programming on a Tree," IEEE Conf. on CVRP, pp. 20-25, June 2005.
  14. M. Bleyer and M. Gelautz, "Simple but Effective Tree Structure for Dynamic Programming-Based Stereo Matching," Intl. Conf. on Computer Vision Theory and Applications. pp. 415-422, 2008.
  15. C. Leung, B. Appleton, and C. Sun, "Iterated Dynamic Programming and Quadtree Subregioning for Fast Stereo Matching," J. of Image and Vision Computing, Vol. 26, pp. 1371-1383, 2008. https://doi.org/10.1016/j.imavis.2007.11.013
  16. C. Lei, S.elzer, J. and Y. H. Yang, "Region-Tree Based Stereo Using Dynamic Programming Optimization," IEEE Conf. on Computer Vision and Pattern Recognition, Vol. 2, pp.2378-2385, 2006.
  17. Y. Wei, L. Quan, "Region-based Progressive Stereo Matching," IEEE Proceeding, Vol. 1, No. 27, pp. 106-113, July 2004.
  18. M. Gong, Y. H. Yang, "Fast Unambiguous Stereo Matching Using Reliability-Based Dynamic Programming," IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 27, No 6, pp. 998-1003, June 2005. https://doi.org/10.1109/TPAMI.2005.120
  19. M. Gong, Y. H. Yang, "Near Real-time Reliable Stereo Matching using Programmable Graphics Husiwuse," IEEE Conf. on Computer Vision and Pattern Recognition, Vol. 1, pp.20-25, June, 2005.
  20. M. Gong, Y. H. Yang, "Real-Time Stereo Matching Using Orthogonal Reliability-Based Dynamic Programming," IEEE Transactions on Image processing, Vol. 16, No 3, pp. 879-884, Mar 2007. https://doi.org/10.1109/TIP.2006.891344
  21. H. Hirschumuller, "Stereo Processing by Semiglobal Matching and Mutual Information," IEEE Trans. on Pattern Analysis and Machine Intelligence. Vol. 30, No.2, pp. 328-341, Feb. 2008. https://doi.org/10.1109/TPAMI.2007.1166
  22. http://vision.middlebury.edu/stereo/
  23. R. C. Gonzalez and R. E. Woods, Digital Image Processing. Pearson Prentice Hall, NJ, 2008.