Journal of the Institute of Electronics and Information Engineers (전자공학회논문지)

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

DOI QR Code

Boundary-preserving Stereo Matching based on Confidence Region Detection and Disparity Map Refinement

신뢰 영역 검출 및 시차 지도 재생성 기반 경계 보존 스테레오 매칭

  • Yun, In Yong (Department of Information and Communication Engineering Sungkyunkwan University) ;
  • Kim, Joong Kyu (Department of Information and Communication Engineering Sungkyunkwan University)
  • 윤인용 (성균관대학교 정보통신대학) ;
  • 김중규 (성균관대학교 정보통신대학)
  • Received : 2016.01.29
  • Accepted : 2016.04.26
  • Published : 2016.05.25
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose boundary-preserving stereo matching method based on adaptive disparity adjustment using confidence region detection. To find the initial disparity map, we compute data cost using the color space (CIE Lab) combined with the gradient space and apply double cost aggregation. We perform left/right consistency checking to sort out the mismatched region. This consistency check typically fails for occluded and mismatched pixels. We mark a pixel in the left disparity map as "inconsistent", if the disparity value of its counterpart pixel differs by a value larger than one pixel. In order to distinguish errors caused by the disparity discontinuity, we first detect the confidence map using the Mean-shift segmentation in the initial disparity map. Using this confidence map, we then adjust the disparity map to reduce the errors in initial disparity map. Experimental results demonstrate that the proposed method produces higher quality disparity maps by successfully preserving disparity discontinuities compared to existing methods.

본 논문에서는 신뢰 영역을 검출하고 이를 이용하여 미스 매치된 영역에 대한 홀을 채우고 적응적으로 시차 지도를 조정하여 경계를 보존하는 스테레오 정합 방법을 제안한다. 초기 시차 지도 추정을 위해 비용 계산은 색상(CIE Lab)과 경사도(Gradient)를 결합하여 이용하였고, 두 번의 비용 결합 함수를 적용 하여 시차 지도를 추정 하였다. 화소 불일치 영역을 검출하기 위해 왼쪽/오른쪽 교차 검사를 수행 하였다. 두 픽셀 위치에서의 차이가 1보다 크면 폐색 영역이거나 잘못된 매칭으로 판단하고 왼쪽 시차 지도에 표시 하였다. 초기 시차 지도에서 깊이 불연속성으로 인한 에러값을 구별하기 위해 Mean-shift segmentation을 사용하여 신뢰 지도를 구하고 초기 시차 지도 영상에서의 에러값을 줄이기 위해 신뢰 지도 결과를 이용하여 시차 지도 조정을 수행한다. 실험 결과 제안하는 방법이 기존의 다른 방법들과 비교하여 비교적 높은 정확도를 보이는 시차 지도를 생성 하는 것을 보였다.

Keywords

References

  1. W. Fife, J. Archibald, Improved census transforms for resource-optimized stereo vision, IEEE TCSVT 23, pp. 60-73, 2013.
  2. N.Y. Chang, T. Tsai, B. Hsu, Y. Chen, T. Chang, Algorithm and architecture of disparity estimation with mini-census adaptive support weight, IEEE TCSVT 20 (6), pp.792-805, 2010.
  3. X. Sun, X. Mei, S. Jiao, M. Zhou, H. Wang, Stereo Matching with Reliable Disparity Propagation, 3DIMPVT, 2011.
  4. C. Cigla, A.A. Alatan, Information Permeability for Stereo Matching, Elsevier Signal Processing: Image Communication, 2013.
  5. F. Tombari, S. Mattoccia, L. Di Stefano, E. Addimanda, Classification and Evaluation of Cost Aggregation Methods for Stereo Correspondence, CVPR, pp. 1-8, 2008.
  6. M. Gong, R.G. Yang, W. Liang, M.W. Gong, A performance study on different cost aggregation approaches used in real-time stereo matching, IJCV 75, pp. 283-296, 2007. https://doi.org/10.1007/s11263-006-0032-x
  7. K.-J. Yoon, I.S. Kweon, Adaptive support-weight approach for correspondence search, IEEE TPAMI 28, pp. 650-656, 2006. https://doi.org/10.1109/TPAMI.2006.70
  8. L. Di Stefano, F. Tombari, S. Mattoccia, Segmentation-based adaptive support for accurate stereo correspondence, IEEE Pacific-Rim Symp. Image and Video, 2007
  9. K. He, J. Sun, and X. Tang, Guided image filtering, ECCV, 2010
  10. A. Hosni, C. Rhemann, M. Bleyer, C. Rother, M. Gelautz, Fast cost-volumefiltering for visual correspondence and beyond, IEEE TPAMI 35 (2), pp. 504-511, 2013. https://doi.org/10.1109/TPAMI.2012.156
  11. V. Kolmogorov, R. Zabih, Computing Visual Correspondence with Occlusions Using Graph Cuts, ICCV, 2, pp. 508-515, 2001.
  12. A. Klaus, M. Sormann, K. Karner, Segment-based Stereo Matching Using Belief Propagation and a Self-adapting Dissimilarity Measure, ICPR, pp. 15-18, 2006.
  13. Z.F. Wang, Z.G. Zheng, A Region Based Stereo Matching Algorithm Using Cooperative Optimization, CVPR, pp. 1-8, 2009.
  14. J. Kim, K. Lee, B. Choi, S. Lee, A Dense Stereo Matching Using Two-pass Dynamic Programming with Generalized Ground Control Points, CVPR, pp. 1075-1082, 2005.
  15. H. Hirschmller, Stereo processing by semiglobal matching and mutual information, IEEE TPAMI 30, pp. 328-341, 2009.
  16. Q. Yang, L. Wang, R. Yang, H. Stewenius, D. Nister, Stereo matching with colorweighted correlation, hierarchical belief propagation and occlusion handling, IEEE TPAMI 31, pp. 492-504, 2009. https://doi.org/10.1109/TPAMI.2008.99
  17. H. Lei, C. K. Jung, Reliability-Based Discontinuity -Preserving Stereo Matching, IEEE TCSVT, 2015.
  18. D. Comanicu and P. Meer, "Mean shift: A robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Machine Intell., May 2002.
  19. X. Mei, X. Sun, M. Zhou, S. Jiao, H. Wang, X. Zhang, On building an accurate stereo matching system on graphics hardware, ICCV, pp 6-13, 2011.
  20. A. Hosni, M. Bleyer, C. Rhemann, M. Gelautz, C. Rother, REal-time local stereo matching using guided image filtering, ICME, pp, 1-6, 2011.
  21. http://www.middlebury.edulstereo/
  22. D. Scharstein and R. Szeliski, "A taxonomy and evaluation of dense two frame stereo correspondence algorithms," IJCV, vol. 47, no. 112/3, pp. 7-42, 2002. https://doi.org/10.1023/A:1014573219977
  23. Z. Ma, K. He, Y. Wei, J. Sun, E. Wu, Constant Time Weighted Median Filtering for Stereo Matching and Beyond, ICCV, pp. 1-8, 2013.
  24. M. Michael, J. Salmen, J. Stallkamp, M. Schlipsing, Real-time stereo vision: optimizing semi-global matching, in: Proc. IEEE Intelligent Vehicles Symposium (IV), pp. 1197-1202, 2013.
  25. N. Manap, J. Soraghan, Disparity refinement based on depth image layers separation for stereo matching algorithms, J. Telecommun. Electron. Comput. Eng. 4 (1), pp. 51-64, 2012.
  26. V. Gonzalez, I. Cabezas, Estimacion de puntos correspondientes mediante programacion dinamica, Congreso Multimedia, 2009.