Geodesic tree-based dynamic programming for fast stereo reconstruction

In this paper, we present a novel tree-based dynamic programming (TDP) algorithm for efficient stereo reconstruction. We employ the geodesic distance transformation for tree construction, which results in sound image over-segmentation and can be easily parallelized on graphic processing unit (GPU). Instead of building a single tree to convey message in dynamic programming (DP), we construct multiple trees according to the image geodesic distance to allow for parallel message passing in DP. In addition to efficiency improvement, the proposed algorithm provides visually sound stereo reconstruction results. Compared with previous related approaches, our experimental results demonstrate superior performance of the proposed algorithm in terms of efficiency and accuracy.

[1]  Ingemar J. Cox,et al.  A Maximum Likelihood Stereo Algorithm , 1996, Comput. Vis. Image Underst..

[2]  Andreas Klaus,et al.  Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[3]  Olga Veksler,et al.  Stereo correspondence by dynamic programming on a tree , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Daniel P. Huttenlocher,et al.  Efficient Belief Propagation for Early Vision , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[5]  Ruigang Yang,et al.  Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation and Occlusion Handling , 2006, CVPR.

[6]  Minglun Gong,et al.  Fast stereo matching using reliability-based dynamic programming and consistency constraints , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Miao Liao,et al.  Real-time Global Stereo Matching Using Hierarchical Belief Propagation , 2006, BMVC.

[8]  Yan Zhou,et al.  Minimum Spanning Tree Based Clustering Algorithms , 2006, 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06).

[9]  D. Nistér,et al.  Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation, and Occlusion Handling , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Carlo Tomasi,et al.  A Pixel Dissimilarity Measure That Is Insensitive to Image Sampling , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Vladimir Kolmogorov,et al.  Multi-camera Scene Reconstruction via Graph Cuts , 2002, ECCV.

[12]  Michael Garland,et al.  Designing efficient sorting algorithms for manycore GPUs , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.

[13]  Alan Brunton,et al.  Belief Propagation on the GPU for Stereo Vision , 2006, The 3rd Canadian Conference on Computer and Robot Vision (CRV'06).

[14]  Andrew Blake,et al.  GeoS: Geodesic Image Segmentation , 2008, ECCV.

[15]  Carsten Rother,et al.  A stereo approach that handles the matting problem via image warping , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Miao Liao,et al.  High-Quality Real-Time Stereo Using Adaptive Cost Aggregation and Dynamic Programming , 2006, Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06).

[17]  Cheng Lei,et al.  Region-Tree Based Stereo Using Dynamic Programming Optimization , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).