Morphological processing of stereoscopic image superimpositions for disparity map estimation

This paper deals with the problem of depth map computation from a pair of rectified stereo images and presents a novel solution based on the morphological processing of disparity space volumes. The reader is guided through the four steps composing the proposed method: the segmentation of stereo images, the diffusion of superimposition costs controlled by the segmentation, the resulting generation of a sparse disparity map which finally drives the estimation of the dense disparity map. An objective evaluation of the algorithm's features and qualities is provided and is accompanied by the results obtained on Middlebury's 2014 stereo database.

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

[2]  Yann LeCun,et al.  Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches , 2015, J. Mach. Learn. Res..

[3]  Aaron F. Bobick,et al.  Large Occlusion Stereo , 1999, International Journal of Computer Vision.

[4]  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.

[5]  M. Bleyer,et al.  Near Real-Time Stereo With Adaptive Support Weight Approaches , 2010 .

[6]  Tarkan Aydin,et al.  Stereo depth estimation using synchronous optimization with segment based regularization , 2010, Pattern Recognit. Lett..

[7]  Jian Sun,et al.  Symmetric stereo matching for occlusion handling , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  M.B.H. Weiss.  Models of grids , 2004, 1st IEEE International Workshop on Grid Economics and Business Models, 2004. GECON 2004..

[9]  Fernand Meyer,et al.  The Viscous Watershed Transform , 2005, Journal of Mathematical Imaging and Vision.

[10]  Richard Szeliski,et al.  Efficient High-Resolution Stereo Matching Using Local Plane Sweeps , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Cevahir Çigla,et al.  Information permeability for stereo matching , 2013, Signal Process. Image Commun..

[12]  Enric Meinhardt,et al.  MGM: A Significantly More Global Matching for Stereovision , 2015, BMVC.

[13]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

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

[15]  Serge Beucher,et al.  The Morphological Approach to Segmentation: The Watershed Transformation , 2018, Mathematical Morphology in Image Processing.

[16]  Xi Wang,et al.  High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth , 2014, GCPR.