Abstract
In this paper, a new algorithm is presented to compute the disparity map from a stereo pair of images by using Belief Propagation (BP). While many algorithms have been proposed in recent years, the real-time computation of an accurate disparity map is still a challenging task. The computation time and run-time memory requirements are two very important factors for all real-time applications. The proposed algorithm divides the matching process into two steps; they are initial matching and disparity map refinement. Initial matching is performed by memory efficient hierarchical belief propagation algorithm that uses less than half memory at run-time and minimizes the energy function at much faster rate as compare to other hierarchical BP algorithms that makes it more suitable for real-time applications. Disparity map refinement uses a simple but very effective single-pass approach that improves the accuracy without affecting the computation cost. Experiments by using Middlebury dataset demonstrate that the performance of our algorithm is the best among other real-time stereo matching algorithms.
Similar content being viewed by others
References
Scharstein D, Szeliski R (2002) A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int J Comput Vis 47(1):7–42
Boykov Y, Veksler O, Zabih R (2001) Fast approximate energy minimization via graph cuts. IEEE Trans Pattern Anal Mach Intell 23(11):1222–1239
Veksler O (1999) Efficient graph-based energy minimization methods in computer vision, PhD thesis, Cornell University, July 1999
Hong L, Chen G (2004) Segment-based stereo matching using graph cuts. Proc IEEE Conf Comput Vis Pattern Recognit 1:1–75, 1–81
Felzenszwalb PF, Huttenlocher DP (2004) Efficient belief propagation for early vision. In: CVPR
Sun J, Zheng NN, Shum HY (2003) Stereo matching using belief propagation. IEEE Trans Pattern Anal Mach Intell 25(7):787–800
Sun J, Li Y, Kang SB, Shum H-Y (2005) Symmetric stereo matching for occlusion handling. IEEE Conf Comput Vis Pattern Recognit 2:399–406
Birchfield S, Tomasi C (1998) Depth discontinuities by pixel-to-pixel stereo. In: IEEE International Conference on Computer Vision, pp 1073–1080
Veksler O (2005) Stereo correspondence by dynamic programming on a tree. IEEE Conf Comput Vis Pattern Recognit 2:384–390
Forstmann S, Ohya J, Kanou Y, Schmitt A, Thuering S (2004) Real-time stereo by using dynamic programming. In: IEEE Computer Vision and Pattern Recognition Workshop, p 29
Yang Q, Wang L, Yang R, Wang S, Liao M, Nister D (2006) Real-time global stereo matching using hierarchical belief propagation. In: BMVC
Yang Q, Wang L, Yang R, Stewenius H, Nister D (2009) Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. IEEE Trans Pattern Anal Mach Intell 31(3):492–504
Zhou X, Wang R (2006) Symmetric pixel-group based stereo matching for occlusion handling. In: ICPR
Klaus A, Sormann M, Karner K (2008) Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In: ICPR
Taguchi Y, Wilburn B, Zitnick CL (2008) Stereo reconstruction with mixed pixels using adaptive over segmentation. In: IEEE International Conference on Computer Vision, pp 1–8
Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 24(5):603–619
Tappen MF, Freeman WT (2003) Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters. IEEE Int Conf Comput Vis
Yoon K-J, Kweon IS (2006) Adaptive support-weight approach for correspondence search. IEEE Trans Pattern Anal Mach Intell 28(4):650–656
Yoon K-J, Kweon IS (2007) Stereo matching with the distinctive similarity measure. IEEE Int Conf Comput Vis
Kosov S, Thormahlen T, Seidel H-P (2009) Accurate real-time disparity estimation with variational methods. In: ISVC, vol 5875, pp 796–807
Zhang K, Lu J, Lafruit G, Lauwereins R, Van Gool L (2009) Real-time accurate stereo with bitwise fast voting on CUDA. IEEE Int Conf Comput Vis Workshop
Tombari F, Mattoccia S, Di Stefano L, Addimanda E (2008) Near real-time stereo based on effective cost aggregation. In: ICPR, pp 1–4
Wang L, Liao M, Gong M, Yang R, Nister D (2006) High-quality real-time stereo using adaptive cost aggregation and dynamic programming. In: 3DPVT
Gong M, Yang YH (2005) Near real-time reliable stereo matching using programmable graphics hardware. IEEE Conf Comput Vis Pattern Recognit
Acknowledgments
The author would like to thank Daniel Scharstein and Richard Szeliski for making stereo images with ground truth data available.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gupta, R.K., Cho, SY. Stereo correspondence using efficient hierarchical belief propagation. Neural Comput & Applic 21, 1585–1592 (2012). https://doi.org/10.1007/s00521-012-0831-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-012-0831-7