Efficient Path-Based Stereo Matching With Subpixel Accuracy

This paper presents an efficient algorithm to achieve accurate subpixel matchings for calculating correspondences between stereo images based on a path-based matching algorithm. Compared with point-by-point stereo-matching algorithms, path-based algorithms resolve local ambiguities by maximizing the cross correlation (or other measurements) along a path, which can be implemented efficiently using dynamic programming. An effect of the global matching criterion is that cross correlations at all pixels contribute to the criterion; since cross correlation can change significantly even with subpixel changes, to achieve subpixel accuracy, it is no longer sufficient to first find the path that maximizes the criterion at integer pixel locations and then refine to subpixel accuracy. In this paper, by writing bilinear interpolation using integral images, we show that cross correlations at all subpixel locations can be computed efficiently and, thus, lead to a subpixel accuracy path-based matching algorithm. Our results show the feasibility of the method and illustrate significant improvement over existing path-based matching methods.

[1]  Kyung-tai Kim,et al.  Automatic Film Line Scratch Removal System based on Spatial Information , 2007, 2007 IEEE International Symposium on Consumer Electronics.

[2]  Philip L. Davidson,et al.  Real-time stereo vision using semi-global matching on programmable graphics hardware , 2006, SIGGRAPH '06.

[3]  Takafumi Aoki,et al.  A High-Accuracy Passive 3D Measurement System Using Phase-Based Image Matching , 2006, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[4]  Jian Guo Liu,et al.  Sub-Pixel Stereo-Matching for DEM Generation from Narrow Baseline Stereo Imagery , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[5]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[6]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[7]  Falko Kuester,et al.  VirtualizeMe: interactive model reconstruction from stereo video streams , 2008, VRST '08.

[8]  Gerhard Tröster,et al.  Architecture and applications of the FingerMouse: a smart stereo camera for wearable computing HCI , 2008, Personal and Ubiquitous Computing.

[9]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[10]  Lin Wu,et al.  3D Reconstruction for Telerobotic Welding , 2007, 2007 International Conference on Mechatronics and Automation.

[11]  Changming Sun,et al.  Fast Stereo Matching by Iterated Dynamic Programming and Quadtree Subregioning , 2004, BMVC.

[12]  Jianguo Liu,et al.  Phase correlation pixel‐to‐pixel image co‐registration based on optical flow and median shift propagation , 2008 .

[13]  Sergio Taraglio,et al.  A hybrid approach for stereo disparity computation , 1999, Machine Vision and Applications.

[14]  Changming Sun,et al.  Fast Stereo Matching Using Rectangular Subregioning and 3D Maximum-Surface Techniques , 2002, International Journal of Computer Vision.

[15]  Ying Wang,et al.  Efficient and accurate subpixel path based stereo matching , 2008, 2008 19th International Conference on Pattern Recognition.

[16]  Ye Zhang,et al.  On 3-D scene flow and structure recovery from multiview image sequences , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[17]  B. Kisacanin,et al.  Integral Image Optimizations for Embedded Vision Applications , 2008, 2008 IEEE Southwest Symposium on Image Analysis and Interpretation.

[18]  Amar Mitiche,et al.  Selective image diffusion: application to disparity estimation , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[19]  Vladimir Kolmogorov,et al.  Computing visual correspondence with occlusions using graph cuts , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[20]  P. Anandan,et al.  A computational framework and an algorithm for the measurement of visual motion , 1987, International Journal of Computer Vision.

[21]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[22]  Ding Liu,et al.  A New Stereo Matching Method Based on Sub-pixel Corner Detection , 2008, 2008 International Conference on Computer Science and Software Engineering.

[23]  Manu Bansal,et al.  A Wavelet-Based Multiresolution Approach to Solve the Stereo Correspondence Problem Using Mutual Information , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[24]  Seth J. Teller,et al.  Video matching , 2004, Encyclopedia of Multimedia.

[25]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[26]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[27]  Simone Frintrop,et al.  A Real-time Visual Attention System Using Integral Images , 2007, ICVS 2007.

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

[29]  Edwin R. Hancock,et al.  A statistical approach to sparse multi-scale phase-based stereo , 2007, Pattern Recognit..

[30]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[31]  Bärbel Mertsching,et al.  Stereo matching with occlusion detection using cost relaxation , 2005, IEEE International Conference on Image Processing 2005.

[32]  Julie Delon,et al.  Small Baseline Stereovision , 2007, Journal of Mathematical Imaging and Vision.

[33]  Kwanghoon Sohn,et al.  3D reconstruction of stereo images for interaction between real and virtual worlds , 2003, The Second IEEE and ACM International Symposium on Mixed and Augmented Reality, 2003. Proceedings..

[34]  Margrit Gelautz,et al.  Graph-cut-based stereo matching using image segmentation with symmetrical treatment of occlusions , 2007, Signal Process. Image Commun..

[35]  Franklin C. Crow,et al.  Summed-area tables for texture mapping , 1984, SIGGRAPH.

[36]  Suhaib A. Fahmy.  Generalised Parallel Bilinear Interpolation Architecture for Vision Systems , 2008, 2008 International Conference on Reconfigurable Computing and FPGAs.

[37]  Floris H. P. van Velden,et al.  Gap Filling Strategies for 3-D-FBP Reconstructions of High-Resolution Research Tomograph Scans , 2008, IEEE Transactions on Medical Imaging.

[38]  Uwe Franke,et al.  Real-time stereo vision for urban traffic scene understanding , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[39]  Gonzalo Pajares,et al.  On combining support vector machines and simulated annealing in stereovision matching , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[40]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Gyung-bum Kim,et al.  An accurate and robust stereo matching algorithm with variable windows for 3D measurements , 2004 .

[42]  Gyung-Bum Kim,et al.  A hybrid stereo vision method using a correlation function and variable window based on voxel components , 2006 .

[43]  Richard Szeliski,et al.  Symmetric Sub-Pixel Stereo Matching , 2002, ECCV.

[44]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.