A Two-Stage Correlation Method for Stereoscopic Depth Estimation

The computation of stereoscopic depth is an important field of computer vision. Although a large variety of algorithms has been developed, the traditional correlation-based versions of these algorithms are prevalent. This is mainly due to easy implementation and handling but also to the linear computational complexity, as compared to more elaborated algorithms based on diffusion processes, graph-cut or bilateral filtering. In this paper, we introduce a new two-stage matching cost for the traditional approach: the summed normalized cross-correlation (SNCC). This new cost function performs a normalized cross-correlation in the first stage and aggregates the correlation values in a second stage. We show that this new measure can be implemented efficiently and that it leads to a substantial improvement of the performance of the traditional stereo approach because it is less sensitive to high contrast outliers.

[1]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

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

[3]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

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

[5]  Du-Ming Tsai,et al.  Fast normalized cross correlation for defect detection , 2003, Pattern Recognit. Lett..

[6]  Darius Burschka,et al.  Advances in Computational Stereo , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Jonathan M. Garibaldi,et al.  Real-Time Correlation-Based Stereo Vision with Reduced Border Errors , 2002, International Journal of Computer Vision.

[8]  Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information , 2005, CVPR.

[9]  Pascal Fua,et al.  A parallel stereo algorithm that produces dense depth maps and preserves image features , 1993, Machine Vision and Applications.

[10]  In-So Kweon,et al.  Adaptive Support-Weight Approach for Correspondence Search , 2006, IEEE Trans. Pattern Anal. Mach. Intell..

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

[12]  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.

[13]  Yi Deng,et al.  A Fast Line Segment Based Dense Stereo Algorithm Using Tree Dynamic Programming , 2006, ECCV.

[14]  Sergiu Nedevschi,et al.  Road Surface and Obstacle Detection Based on Elevation Maps from Dense Stereo , 2007, 2007 IEEE Intelligent Transportation Systems Conference.

[15]  Heiko Hirschmüller,et al.  Evaluation of Cost Functions for Stereo Matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Heiko Wersing,et al.  Online Learning of Objects in a Biologically Motivated Visual Architecture , 2007, Int. J. Neural Syst..

[17]  Katsushi Ikeuchi,et al.  Disparity map refinement and 3D surface smoothing via Directed Anisotropic Diffusion , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[18]  Stefano Mattoccia,et al.  Accurate and Efficient Cost Aggregation Strategy for Stereo Correspondence Based on Approximated Joint Bilateral Filtering , 2009, ACCV.

[19]  Heiko Hirschmüller,et al.  Evaluation of Stereo Matching Costs on Images with Radiometric Differences , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.