Abstract

Gradient similarity is a simple, yet powerful, data descriptor which shows robustness in stereo matching. In this paper, a RGB vector space is defined for stereo matching. Based on the adaptive support-weight approach, a matching algorithm, which uses the pixel gradient similarity, color similarity, and proximity in RGB vector space to compute the corresponding support-weights and dissimilarity measurements, is proposed. The experimental results are evaluated on the Middlebury stereo benchmark, showing that our algorithm outperforms other stereo matching algorithms and the algorithm with gradient similarity can achieve better results in stereo matching.

© 2012 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. X. Ding, L. Xu, H. Wang, X. Wang, and G. Lv, “Stereo depth estimation under different camera calibration and alignment errors,” Appl. Opt. 50, 1289–1301 (2011).
    [CrossRef]
  2. D. Mukherjee and G. Wang, “Stereo correspondence based on curvelet decomposition, support weights, and disparity calibration,” J. Opt. Eng. 49, 077003 (2010).
    [CrossRef]
  3. A. Klaus, M. Sormann, and K. Karner, “Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure,” in 18th International Conference Pattern Recognition (IEEE, 2006), pp. 15–18.
  4. Q. Yang, L. Wang, and N. Ahuja, “A constant-space belief propagation algorithm for stereo matching,” in Proceedings of IEEE Conference Computer Vision and Pattern Recognition (IEEE, 2010), pp. 1458–1465.
  5. J. Sun, N.-N. Zheng, and H.-Y. Shum, “Stereo matching using belief propagation,” IEEE Trans. Pattern Anal. Machine Intell. 25, 787–800 (2003).
    [CrossRef]
  6. L. Hong and G. Chen, “Segment-based stereo matching using graph cuts,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2004), pp. I-74–78.
  7. N. Papadakis and V. Caselles, “Multi-label depth estimation for graph cuts stereo problems,” J. Math. Imaging Vision 38, 70–82 (2010).
    [CrossRef]
  8. D. Miyazaki, Y. Matsushita, and K. Ikeuchi, “Interactive shadow removal from a single image using hierarchical graph cut,” IPSJ Trans. Comp. Vis. Appl. 2, 235–252 (2010).
    [CrossRef]
  9. F.-Z. Wang, D.-G. Huang, and G. Sen, “Belief propagation stereo matching based on differential geometry constraint of disparity,” in Proceedings of the International Conference on Digital Manufacturing and Automation (IEEE, 2010), pp. 324–327.
  10. L. De-Maeztu, A. Villanueva, and R. Cabgeza, “Stereo matching using gradient similarity and locally adaptive support-weight,” Patt. Recogn. Lett. 32, 1643–1651 (2011).
    [CrossRef]
  11. T. Kanada and M. Okutomi, “A stereo matching algorithm with an adaptive window: theory and experiment,” IEEE Trans. Pattern Anal. Machine Intell. 16, 920–932 (1994).
    [CrossRef]
  12. K. Zhang, J. Lu, and G. Lafruit, “Scalable stereo matching with locally adaptive polygon approximation,” in Proceedings of the 15th IEEE International Conference Image Processing (IEEE, 2008), pp. 313–316.
  13. G. Luo, X. Yang, and Q. Xu, “Fast stereo matching algorithm using adaptive window,” in International Symposiums Information Processing (2008), pp. 25–30.
  14. X. Su and T. M. Khoshgoftaar, “Arbitrarily-shaped window based stereo matching using the go-light optimization algorithm,” in IEEE International Conference Image Processing (IEEE, 2007), pp. VI-556–559.
  15. J. Lu, K. Zhang, G. Lafruit, and F. Catthoor, “Real-time stereo matching: a cross-based local approach,” in IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2009), pp. 733–736.
  16. A. Hosni, M. Bleyer, and M. Gelautz, “Local stereo matching using geodesic support weights,” in 16th IEEE International Conference Image Processing (IEEE, 2009), pp. 2093–2096.
  17. Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
    [CrossRef]
  18. W. Hu, K. Zhang, L. Sun, J. Li, Y. Li, and S. Yang, “Virtual support window for adaptive-weight stereo matching,” in Visual Communications and Image Processing (IEEE, 2011), pp. 1–4.
    [CrossRef]
  19. L. Nalpantidis, and A. Gasteratos, “Biologically and psychophysically inspired adaptive support weights algorithm for stereo correspondence,” Robot. Auton. Syst. 58457–464 (2010).
    [CrossRef]
  20. K.-J. Yoon and I.-S. Kweon, “Adaptive support-weight approach for correspondence search,” IEEE Trans. Pattern Anal. Mach. Intell. 28, 650–656 (2006).
    [CrossRef]
  21. F. He and F. Da, “Stereo matching based on dissimilar intensity support,” in Proceedings of the Chinese Conference on Pattern Recognition CCPR (2010), pp. 1–5.
  22. C. Connolly and T. Fleiss, “A study of efficiency and accuracy in the transformation from RGB to CIELAB color space,” in IEEE International Conference on Image Processing (IEEE, 1997), pp. 1046–1048.
  23. G. Yingnan, Z. Yan, and C. Hexin, “Improved belief propagation based on RGB vector measure for stereo matching,” in Proceedings of 2011, International Conference on Wireless Communications and Signal Processing (WCSP) (IEEE, 2011), pp. 1–5.
  24. S. Hermann and T. Vaudrey, “The Gradient—A powerful and robust cost function for stereo matching,” in 2010 25th International Conference of Image and Vision Computing (IEEE, 2010), pp. 1–8.
  25. F. Tombari, S. Mattoccia, and L. Di Stefano, “Segmentation-based adaptive support for accurate stereo correspondence,” in Proceedings of the Pacific-Rim Symposium on Image and Video Technology (IEEE, 2007), pp. 427–428.
  26. Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform, and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
    [CrossRef]
  27. I. Park and H. Byun, “Depth map refinement using multiple patch-based depth image completion via local stereo warping,” J. Opt. Eng. 49, 077033 (2010).
    [CrossRef]
  28. R. Gupta and S.-Y. Cho, “A correlation-based approach for real-time stereo matching,” in Advances in Visual Computing, Vol. 6454 of Lecture Notes in Computer Science (Springer, 2010).
  29. D. Scharsterein and R. Szeliski, “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,” in Proceedings of IEEE Workshop on Stereo and Multi-Baseline Vision (IEEE, 2002), pp. 131–140.

2011

X. Ding, L. Xu, H. Wang, X. Wang, and G. Lv, “Stereo depth estimation under different camera calibration and alignment errors,” Appl. Opt. 50, 1289–1301 (2011).
[CrossRef]

L. De-Maeztu, A. Villanueva, and R. Cabgeza, “Stereo matching using gradient similarity and locally adaptive support-weight,” Patt. Recogn. Lett. 32, 1643–1651 (2011).
[CrossRef]

2010

L. Nalpantidis, and A. Gasteratos, “Biologically and psychophysically inspired adaptive support weights algorithm for stereo correspondence,” Robot. Auton. Syst. 58457–464 (2010).
[CrossRef]

D. Mukherjee and G. Wang, “Stereo correspondence based on curvelet decomposition, support weights, and disparity calibration,” J. Opt. Eng. 49, 077003 (2010).
[CrossRef]

N. Papadakis and V. Caselles, “Multi-label depth estimation for graph cuts stereo problems,” J. Math. Imaging Vision 38, 70–82 (2010).
[CrossRef]

D. Miyazaki, Y. Matsushita, and K. Ikeuchi, “Interactive shadow removal from a single image using hierarchical graph cut,” IPSJ Trans. Comp. Vis. Appl. 2, 235–252 (2010).
[CrossRef]

I. Park and H. Byun, “Depth map refinement using multiple patch-based depth image completion via local stereo warping,” J. Opt. Eng. 49, 077033 (2010).
[CrossRef]

2008

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform, and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

2006

K.-J. Yoon and I.-S. Kweon, “Adaptive support-weight approach for correspondence search,” IEEE Trans. Pattern Anal. Mach. Intell. 28, 650–656 (2006).
[CrossRef]

2003

J. Sun, N.-N. Zheng, and H.-Y. Shum, “Stereo matching using belief propagation,” IEEE Trans. Pattern Anal. Machine Intell. 25, 787–800 (2003).
[CrossRef]

1994

T. Kanada and M. Okutomi, “A stereo matching algorithm with an adaptive window: theory and experiment,” IEEE Trans. Pattern Anal. Machine Intell. 16, 920–932 (1994).
[CrossRef]

Ahuja, N.

Q. Yang, L. Wang, and N. Ahuja, “A constant-space belief propagation algorithm for stereo matching,” in Proceedings of IEEE Conference Computer Vision and Pattern Recognition (IEEE, 2010), pp. 1458–1465.

Bleyer, M.

A. Hosni, M. Bleyer, and M. Gelautz, “Local stereo matching using geodesic support weights,” in 16th IEEE International Conference Image Processing (IEEE, 2009), pp. 2093–2096.

Byun, H.

I. Park and H. Byun, “Depth map refinement using multiple patch-based depth image completion via local stereo warping,” J. Opt. Eng. 49, 077033 (2010).
[CrossRef]

Cabgeza, R.

L. De-Maeztu, A. Villanueva, and R. Cabgeza, “Stereo matching using gradient similarity and locally adaptive support-weight,” Patt. Recogn. Lett. 32, 1643–1651 (2011).
[CrossRef]

Caselles, V.

N. Papadakis and V. Caselles, “Multi-label depth estimation for graph cuts stereo problems,” J. Math. Imaging Vision 38, 70–82 (2010).
[CrossRef]

Catthoor, F.

J. Lu, K. Zhang, G. Lafruit, and F. Catthoor, “Real-time stereo matching: a cross-based local approach,” in IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2009), pp. 733–736.

Chen, G.

L. Hong and G. Chen, “Segment-based stereo matching using graph cuts,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2004), pp. I-74–78.

Cho, S.-Y.

R. Gupta and S.-Y. Cho, “A correlation-based approach for real-time stereo matching,” in Advances in Visual Computing, Vol. 6454 of Lecture Notes in Computer Science (Springer, 2010).

Connolly, C.

C. Connolly and T. Fleiss, “A study of efficiency and accuracy in the transformation from RGB to CIELAB color space,” in IEEE International Conference on Image Processing (IEEE, 1997), pp. 1046–1048.

Da, F.

F. He and F. Da, “Stereo matching based on dissimilar intensity support,” in Proceedings of the Chinese Conference on Pattern Recognition CCPR (2010), pp. 1–5.

De-Maeztu, L.

L. De-Maeztu, A. Villanueva, and R. Cabgeza, “Stereo matching using gradient similarity and locally adaptive support-weight,” Patt. Recogn. Lett. 32, 1643–1651 (2011).
[CrossRef]

Di Stefano, L.

F. Tombari, S. Mattoccia, and L. Di Stefano, “Segmentation-based adaptive support for accurate stereo correspondence,” in Proceedings of the Pacific-Rim Symposium on Image and Video Technology (IEEE, 2007), pp. 427–428.

Ding, X.

Fleiss, T.

C. Connolly and T. Fleiss, “A study of efficiency and accuracy in the transformation from RGB to CIELAB color space,” in IEEE International Conference on Image Processing (IEEE, 1997), pp. 1046–1048.

Gasteratos, A.

L. Nalpantidis, and A. Gasteratos, “Biologically and psychophysically inspired adaptive support weights algorithm for stereo correspondence,” Robot. Auton. Syst. 58457–464 (2010).
[CrossRef]

Gelautz, M.

A. Hosni, M. Bleyer, and M. Gelautz, “Local stereo matching using geodesic support weights,” in 16th IEEE International Conference Image Processing (IEEE, 2009), pp. 2093–2096.

Gu, Z.

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform, and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Gupta, R.

R. Gupta and S.-Y. Cho, “A correlation-based approach for real-time stereo matching,” in Advances in Visual Computing, Vol. 6454 of Lecture Notes in Computer Science (Springer, 2010).

He, F.

F. He and F. Da, “Stereo matching based on dissimilar intensity support,” in Proceedings of the Chinese Conference on Pattern Recognition CCPR (2010), pp. 1–5.

Hermann, S.

S. Hermann and T. Vaudrey, “The Gradient—A powerful and robust cost function for stereo matching,” in 2010 25th International Conference of Image and Vision Computing (IEEE, 2010), pp. 1–8.

Hexin, C.

G. Yingnan, Z. Yan, and C. Hexin, “Improved belief propagation based on RGB vector measure for stereo matching,” in Proceedings of 2011, International Conference on Wireless Communications and Signal Processing (WCSP) (IEEE, 2011), pp. 1–5.

Hong, L.

L. Hong and G. Chen, “Segment-based stereo matching using graph cuts,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2004), pp. I-74–78.

Hosni, A.

A. Hosni, M. Bleyer, and M. Gelautz, “Local stereo matching using geodesic support weights,” in 16th IEEE International Conference Image Processing (IEEE, 2009), pp. 2093–2096.

Hu, W.

W. Hu, K. Zhang, L. Sun, J. Li, Y. Li, and S. Yang, “Virtual support window for adaptive-weight stereo matching,” in Visual Communications and Image Processing (IEEE, 2011), pp. 1–4.
[CrossRef]

Huang, D.-G.

F.-Z. Wang, D.-G. Huang, and G. Sen, “Belief propagation stereo matching based on differential geometry constraint of disparity,” in Proceedings of the International Conference on Digital Manufacturing and Automation (IEEE, 2010), pp. 324–327.

Ikeuchi, K.

D. Miyazaki, Y. Matsushita, and K. Ikeuchi, “Interactive shadow removal from a single image using hierarchical graph cut,” IPSJ Trans. Comp. Vis. Appl. 2, 235–252 (2010).
[CrossRef]

Kanada, T.

T. Kanada and M. Okutomi, “A stereo matching algorithm with an adaptive window: theory and experiment,” IEEE Trans. Pattern Anal. Machine Intell. 16, 920–932 (1994).
[CrossRef]

Karner, K.

A. Klaus, M. Sormann, and K. Karner, “Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure,” in 18th International Conference Pattern Recognition (IEEE, 2006), pp. 15–18.

Khoshgoftaar, T. M.

X. Su and T. M. Khoshgoftaar, “Arbitrarily-shaped window based stereo matching using the go-light optimization algorithm,” in IEEE International Conference Image Processing (IEEE, 2007), pp. VI-556–559.

Klaus, A.

A. Klaus, M. Sormann, and K. Karner, “Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure,” in 18th International Conference Pattern Recognition (IEEE, 2006), pp. 15–18.

Kweon, I.-S.

K.-J. Yoon and I.-S. Kweon, “Adaptive support-weight approach for correspondence search,” IEEE Trans. Pattern Anal. Mach. Intell. 28, 650–656 (2006).
[CrossRef]

Lafruit, G.

K. Zhang, J. Lu, and G. Lafruit, “Scalable stereo matching with locally adaptive polygon approximation,” in Proceedings of the 15th IEEE International Conference Image Processing (IEEE, 2008), pp. 313–316.

J. Lu, K. Zhang, G. Lafruit, and F. Catthoor, “Real-time stereo matching: a cross-based local approach,” in IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2009), pp. 733–736.

Li, J.

W. Hu, K. Zhang, L. Sun, J. Li, Y. Li, and S. Yang, “Virtual support window for adaptive-weight stereo matching,” in Visual Communications and Image Processing (IEEE, 2011), pp. 1–4.
[CrossRef]

Li, Y.

W. Hu, K. Zhang, L. Sun, J. Li, Y. Li, and S. Yang, “Virtual support window for adaptive-weight stereo matching,” in Visual Communications and Image Processing (IEEE, 2011), pp. 1–4.
[CrossRef]

Liu, Y.

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform, and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Lu, J.

J. Lu, K. Zhang, G. Lafruit, and F. Catthoor, “Real-time stereo matching: a cross-based local approach,” in IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2009), pp. 733–736.

K. Zhang, J. Lu, and G. Lafruit, “Scalable stereo matching with locally adaptive polygon approximation,” in Proceedings of the 15th IEEE International Conference Image Processing (IEEE, 2008), pp. 313–316.

Luo, G.

G. Luo, X. Yang, and Q. Xu, “Fast stereo matching algorithm using adaptive window,” in International Symposiums Information Processing (2008), pp. 25–30.

Lv, G.

Matsushita, Y.

D. Miyazaki, Y. Matsushita, and K. Ikeuchi, “Interactive shadow removal from a single image using hierarchical graph cut,” IPSJ Trans. Comp. Vis. Appl. 2, 235–252 (2010).
[CrossRef]

Mattoccia, S.

F. Tombari, S. Mattoccia, and L. Di Stefano, “Segmentation-based adaptive support for accurate stereo correspondence,” in Proceedings of the Pacific-Rim Symposium on Image and Video Technology (IEEE, 2007), pp. 427–428.

Miyazaki, D.

D. Miyazaki, Y. Matsushita, and K. Ikeuchi, “Interactive shadow removal from a single image using hierarchical graph cut,” IPSJ Trans. Comp. Vis. Appl. 2, 235–252 (2010).
[CrossRef]

Mukherjee, D.

D. Mukherjee and G. Wang, “Stereo correspondence based on curvelet decomposition, support weights, and disparity calibration,” J. Opt. Eng. 49, 077003 (2010).
[CrossRef]

Nalpantidis, L.

L. Nalpantidis, and A. Gasteratos, “Biologically and psychophysically inspired adaptive support weights algorithm for stereo correspondence,” Robot. Auton. Syst. 58457–464 (2010).
[CrossRef]

Okutomi, M.

T. Kanada and M. Okutomi, “A stereo matching algorithm with an adaptive window: theory and experiment,” IEEE Trans. Pattern Anal. Machine Intell. 16, 920–932 (1994).
[CrossRef]

Papadakis, N.

N. Papadakis and V. Caselles, “Multi-label depth estimation for graph cuts stereo problems,” J. Math. Imaging Vision 38, 70–82 (2010).
[CrossRef]

Park, I.

I. Park and H. Byun, “Depth map refinement using multiple patch-based depth image completion via local stereo warping,” J. Opt. Eng. 49, 077033 (2010).
[CrossRef]

Scharsterein, D.

D. Scharsterein and R. Szeliski, “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,” in Proceedings of IEEE Workshop on Stereo and Multi-Baseline Vision (IEEE, 2002), pp. 131–140.

Sen, G.

F.-Z. Wang, D.-G. Huang, and G. Sen, “Belief propagation stereo matching based on differential geometry constraint of disparity,” in Proceedings of the International Conference on Digital Manufacturing and Automation (IEEE, 2010), pp. 324–327.

Shum, H.-Y.

J. Sun, N.-N. Zheng, and H.-Y. Shum, “Stereo matching using belief propagation,” IEEE Trans. Pattern Anal. Machine Intell. 25, 787–800 (2003).
[CrossRef]

Sormann, M.

A. Klaus, M. Sormann, and K. Karner, “Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure,” in 18th International Conference Pattern Recognition (IEEE, 2006), pp. 15–18.

Su, X.

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform, and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

X. Su and T. M. Khoshgoftaar, “Arbitrarily-shaped window based stereo matching using the go-light optimization algorithm,” in IEEE International Conference Image Processing (IEEE, 2007), pp. VI-556–559.

Sun, J.

J. Sun, N.-N. Zheng, and H.-Y. Shum, “Stereo matching using belief propagation,” IEEE Trans. Pattern Anal. Machine Intell. 25, 787–800 (2003).
[CrossRef]

Sun, L.

W. Hu, K. Zhang, L. Sun, J. Li, Y. Li, and S. Yang, “Virtual support window for adaptive-weight stereo matching,” in Visual Communications and Image Processing (IEEE, 2011), pp. 1–4.
[CrossRef]

Szeliski, R.

D. Scharsterein and R. Szeliski, “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,” in Proceedings of IEEE Workshop on Stereo and Multi-Baseline Vision (IEEE, 2002), pp. 131–140.

Tombari, F.

F. Tombari, S. Mattoccia, and L. Di Stefano, “Segmentation-based adaptive support for accurate stereo correspondence,” in Proceedings of the Pacific-Rim Symposium on Image and Video Technology (IEEE, 2007), pp. 427–428.

Vaudrey, T.

S. Hermann and T. Vaudrey, “The Gradient—A powerful and robust cost function for stereo matching,” in 2010 25th International Conference of Image and Vision Computing (IEEE, 2010), pp. 1–8.

Villanueva, A.

L. De-Maeztu, A. Villanueva, and R. Cabgeza, “Stereo matching using gradient similarity and locally adaptive support-weight,” Patt. Recogn. Lett. 32, 1643–1651 (2011).
[CrossRef]

Wang, F.-Z.

F.-Z. Wang, D.-G. Huang, and G. Sen, “Belief propagation stereo matching based on differential geometry constraint of disparity,” in Proceedings of the International Conference on Digital Manufacturing and Automation (IEEE, 2010), pp. 324–327.

Wang, G.

D. Mukherjee and G. Wang, “Stereo correspondence based on curvelet decomposition, support weights, and disparity calibration,” J. Opt. Eng. 49, 077003 (2010).
[CrossRef]

Wang, H.

Wang, L.

Q. Yang, L. Wang, and N. Ahuja, “A constant-space belief propagation algorithm for stereo matching,” in Proceedings of IEEE Conference Computer Vision and Pattern Recognition (IEEE, 2010), pp. 1458–1465.

Wang, X.

Xu, L.

Xu, Q.

G. Luo, X. Yang, and Q. Xu, “Fast stereo matching algorithm using adaptive window,” in International Symposiums Information Processing (2008), pp. 25–30.

Yan, Z.

G. Yingnan, Z. Yan, and C. Hexin, “Improved belief propagation based on RGB vector measure for stereo matching,” in Proceedings of 2011, International Conference on Wireless Communications and Signal Processing (WCSP) (IEEE, 2011), pp. 1–5.

Yang, Q.

Q. Yang, L. Wang, and N. Ahuja, “A constant-space belief propagation algorithm for stereo matching,” in Proceedings of IEEE Conference Computer Vision and Pattern Recognition (IEEE, 2010), pp. 1458–1465.

Yang, S.

W. Hu, K. Zhang, L. Sun, J. Li, Y. Li, and S. Yang, “Virtual support window for adaptive-weight stereo matching,” in Visual Communications and Image Processing (IEEE, 2011), pp. 1–4.
[CrossRef]

Yang, X.

G. Luo, X. Yang, and Q. Xu, “Fast stereo matching algorithm using adaptive window,” in International Symposiums Information Processing (2008), pp. 25–30.

Yingnan, G.

G. Yingnan, Z. Yan, and C. Hexin, “Improved belief propagation based on RGB vector measure for stereo matching,” in Proceedings of 2011, International Conference on Wireless Communications and Signal Processing (WCSP) (IEEE, 2011), pp. 1–5.

Yoon, K.-J.

K.-J. Yoon and I.-S. Kweon, “Adaptive support-weight approach for correspondence search,” IEEE Trans. Pattern Anal. Mach. Intell. 28, 650–656 (2006).
[CrossRef]

Zhang, K.

K. Zhang, J. Lu, and G. Lafruit, “Scalable stereo matching with locally adaptive polygon approximation,” in Proceedings of the 15th IEEE International Conference Image Processing (IEEE, 2008), pp. 313–316.

J. Lu, K. Zhang, G. Lafruit, and F. Catthoor, “Real-time stereo matching: a cross-based local approach,” in IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2009), pp. 733–736.

W. Hu, K. Zhang, L. Sun, J. Li, Y. Li, and S. Yang, “Virtual support window for adaptive-weight stereo matching,” in Visual Communications and Image Processing (IEEE, 2011), pp. 1–4.
[CrossRef]

Zhang, Q.

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform, and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Zheng, N.-N.

J. Sun, N.-N. Zheng, and H.-Y. Shum, “Stereo matching using belief propagation,” IEEE Trans. Pattern Anal. Machine Intell. 25, 787–800 (2003).
[CrossRef]

Appl. Opt.

IEEE Trans. Pattern Anal. Mach. Intell.

K.-J. Yoon and I.-S. Kweon, “Adaptive support-weight approach for correspondence search,” IEEE Trans. Pattern Anal. Mach. Intell. 28, 650–656 (2006).
[CrossRef]

IEEE Trans. Pattern Anal. Machine Intell.

T. Kanada and M. Okutomi, “A stereo matching algorithm with an adaptive window: theory and experiment,” IEEE Trans. Pattern Anal. Machine Intell. 16, 920–932 (1994).
[CrossRef]

J. Sun, N.-N. Zheng, and H.-Y. Shum, “Stereo matching using belief propagation,” IEEE Trans. Pattern Anal. Machine Intell. 25, 787–800 (2003).
[CrossRef]

IPSJ Trans. Comp. Vis. Appl.

D. Miyazaki, Y. Matsushita, and K. Ikeuchi, “Interactive shadow removal from a single image using hierarchical graph cut,” IPSJ Trans. Comp. Vis. Appl. 2, 235–252 (2010).
[CrossRef]

J. Math. Imaging Vision

N. Papadakis and V. Caselles, “Multi-label depth estimation for graph cuts stereo problems,” J. Math. Imaging Vision 38, 70–82 (2010).
[CrossRef]

J. Opt. Eng.

D. Mukherjee and G. Wang, “Stereo correspondence based on curvelet decomposition, support weights, and disparity calibration,” J. Opt. Eng. 49, 077003 (2010).
[CrossRef]

I. Park and H. Byun, “Depth map refinement using multiple patch-based depth image completion via local stereo warping,” J. Opt. Eng. 49, 077033 (2010).
[CrossRef]

Patt. Recogn. Lett.

L. De-Maeztu, A. Villanueva, and R. Cabgeza, “Stereo matching using gradient similarity and locally adaptive support-weight,” Patt. Recogn. Lett. 32, 1643–1651 (2011).
[CrossRef]

Pattern Recogn. Lett.

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Z. Gu, X. Su, Y. Liu, and Q. Zhang, “Local stereo matching with adaptive support-weight, rank transform, and disparity calibration,” Pattern Recogn. Lett. 29, 1230–1235 (2008).
[CrossRef]

Robot. Auton. Syst.

L. Nalpantidis, and A. Gasteratos, “Biologically and psychophysically inspired adaptive support weights algorithm for stereo correspondence,” Robot. Auton. Syst. 58457–464 (2010).
[CrossRef]

Other

W. Hu, K. Zhang, L. Sun, J. Li, Y. Li, and S. Yang, “Virtual support window for adaptive-weight stereo matching,” in Visual Communications and Image Processing (IEEE, 2011), pp. 1–4.
[CrossRef]

R. Gupta and S.-Y. Cho, “A correlation-based approach for real-time stereo matching,” in Advances in Visual Computing, Vol. 6454 of Lecture Notes in Computer Science (Springer, 2010).

D. Scharsterein and R. Szeliski, “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,” in Proceedings of IEEE Workshop on Stereo and Multi-Baseline Vision (IEEE, 2002), pp. 131–140.

F.-Z. Wang, D.-G. Huang, and G. Sen, “Belief propagation stereo matching based on differential geometry constraint of disparity,” in Proceedings of the International Conference on Digital Manufacturing and Automation (IEEE, 2010), pp. 324–327.

A. Klaus, M. Sormann, and K. Karner, “Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure,” in 18th International Conference Pattern Recognition (IEEE, 2006), pp. 15–18.

Q. Yang, L. Wang, and N. Ahuja, “A constant-space belief propagation algorithm for stereo matching,” in Proceedings of IEEE Conference Computer Vision and Pattern Recognition (IEEE, 2010), pp. 1458–1465.

L. Hong and G. Chen, “Segment-based stereo matching using graph cuts,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2004), pp. I-74–78.

K. Zhang, J. Lu, and G. Lafruit, “Scalable stereo matching with locally adaptive polygon approximation,” in Proceedings of the 15th IEEE International Conference Image Processing (IEEE, 2008), pp. 313–316.

G. Luo, X. Yang, and Q. Xu, “Fast stereo matching algorithm using adaptive window,” in International Symposiums Information Processing (2008), pp. 25–30.

X. Su and T. M. Khoshgoftaar, “Arbitrarily-shaped window based stereo matching using the go-light optimization algorithm,” in IEEE International Conference Image Processing (IEEE, 2007), pp. VI-556–559.

J. Lu, K. Zhang, G. Lafruit, and F. Catthoor, “Real-time stereo matching: a cross-based local approach,” in IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2009), pp. 733–736.

A. Hosni, M. Bleyer, and M. Gelautz, “Local stereo matching using geodesic support weights,” in 16th IEEE International Conference Image Processing (IEEE, 2009), pp. 2093–2096.

F. He and F. Da, “Stereo matching based on dissimilar intensity support,” in Proceedings of the Chinese Conference on Pattern Recognition CCPR (2010), pp. 1–5.

C. Connolly and T. Fleiss, “A study of efficiency and accuracy in the transformation from RGB to CIELAB color space,” in IEEE International Conference on Image Processing (IEEE, 1997), pp. 1046–1048.

G. Yingnan, Z. Yan, and C. Hexin, “Improved belief propagation based on RGB vector measure for stereo matching,” in Proceedings of 2011, International Conference on Wireless Communications and Signal Processing (WCSP) (IEEE, 2011), pp. 1–5.

S. Hermann and T. Vaudrey, “The Gradient—A powerful and robust cost function for stereo matching,” in 2010 25th International Conference of Image and Vision Computing (IEEE, 2010), pp. 1–8.

F. Tombari, S. Mattoccia, and L. Di Stefano, “Segmentation-based adaptive support for accurate stereo correspondence,” in Proceedings of the Pacific-Rim Symposium on Image and Video Technology (IEEE, 2007), pp. 427–428.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (5)

Fig. 1.
Fig. 1.

RGB vector space.

Fig. 2.
Fig. 2.

Stereo image pairs and their corresponding gradient maps.

Fig. 3.
Fig. 3.

Stereo matching model in the RGB vector space.

Fig. 4.
Fig. 4.

The comparison of results. (a) Left image. (b) Ground truth. (c) Disparity map generated by our algorithm. (d) Bad-pixel image of our algorithm. (e) Disparity map generated by adaptive support-weight approach. (f) Bad-pixel image of adaptive support-weight approach.

Fig. 5.
Fig. 5.

Three parts of ‘cones’. (a) Nonocc, non-occluded regions (white) and occluded and unknown regions (black). (b) All, all regions (white) and unknown regions (black). (c) Disc, regions near depth discontinuities (white), occluded and unknown regions (black), and other regions (gray).

Tables (6)

Tables Icon

Table 1. Performance Comparison for the Proposed Method with the Middlebury Stereo Benchmark (Error Threshold: 1.0)

Tables Icon

Table 2. Performance Comparison for the Proposed Method with the Middlebury Stereo Benchmark (Error Threshold: 0.5)

Tables Icon

Table 3. Comparison Results of the Proposed Method with and without Gradient (Error Threshold: 1.0)

Tables Icon

Table 4. Comparison Results of the Proposed Method with and without Gradient (Error Threshold: 0.5)

Tables Icon

Table 5. Comparison Results of the Proposed Method with and without Disparity Refinement (Error Threshold: 1.0)

Tables Icon

Table 6. Comparison Results of the Proposed Method with and without Disparity Refinement (Error Threshold: 0.5)

Equations (20)

Equations on this page are rendered with MathJax. Learn more.

gradf⃗(x,y)=f⃗xi⃗+f⃗yj⃗,
xf⃗(x,y)=d(x,y)dx|y=const=limΔx0f⃗(x+Δx,y)f⃗(x,y)Δx,
yf⃗(x,y)=d(x,y)dy|x=const=limΔy0f⃗(x,y+Δy)f⃗(x,y)Δy,
w(p⃗,p⃗L)=fs(Δcp⃗p⃗L)×fp(Δdisp⃗p⃗L)×fg(Δgrap⃗p⃗L),
fs(Δcp⃗p⃗L)=exp(Δcp⃗p⃗Lτc),
Δcp⃗p⃗L=p⃗p⃗L2=(prpLr)2+(pgpLg)2+(pbpLb)2,
fp(Δdisp⃗p⃗L)=exp(Δdisp⃗p⃗Lτdis),
Δdisp⃗p⃗L=disp⃗disp⃗L2=(xp⃗xp⃗L)2+(yp⃗yp⃗L)2
fg(Δgrap⃗p⃗L)=exp(Δgrap⃗p⃗Lτgra),
Δgrap⃗p⃗L=Δgraxp⃗p⃗L+Δgrayp⃗p⃗L
Δgraxp⃗p⃗L=graxp⃗graxp⃗L2=(graxprgraxpLr)2+(graxpggraxpLg)2+(graxpbgraxpLb)2,
Δgrayp⃗p⃗L=grayp⃗grayp⃗L2=(grayprgraypLr)2+(graypggraypLg)2+(graypbgraypLb)2.
w(p⃗,p⃗L)=exp(Δcp⃗p⃗Lτc)×exp(Δdisp⃗p⃗Lτdis)×exp(Δgrap⃗p⃗Lτgra).
E(p⃗,q⃗d)=1Np⃗LNp⃗,q⃗LdNq⃗dematching(p⃗L,q⃗Ld)×w(p⃗,p⃗L),
ematching(p⃗L,q⃗Ld)=ec(p⃗L,q⃗Ld)×egra(p⃗L,q⃗Ld),
ec(p⃗L,q⃗Ld)=exp((Δcp⃗Lq⃗Ld/ηcolor)),
egra(p⃗L,q⃗Ld)=exp((Δgraxp⃗Lq⃗Ldηgradient1+Δgrayp⃗Lq⃗Ldηgradient2)),
dp⃗=argmaxdDE(p⃗,q⃗d)
1NTx,yT(|dc(x,y)dt(x,y)|>δd),
dL(x,y)=dR(xdL(x,y),y),

Metrics