Stereo Matching as a Nearest-Neighbor Problem

We propose a representation of images, called intrinsic curves, that transforms stereo matching from a search problem into a nearest-neighbor problem. Intrinsic curves are the paths that a set of local image descriptors trace as an image scanline is traversed from left to right. Intrinsic curves are ideally invariant with respect to disparity. Stereo correspondence then becomes a trivial lookup problem in the ideal case. We also show how to use intrinsic curves to match real images in the presence of noise, brightness bias, contrast fluctuations, moderate geometric distortion, image ambiguity, and occlusions. In this case, matching becomes a nearest-neighbor problem, even for very large disparity values.

[1]  Peng-Seng Toh,et al.  Occlusion detection in early vision , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[2]  T. O. Binford,et al.  Geometric Constraints In Stereo Vision , 1980, Optics & Photonics.

[3]  Jeffrey K. Uhlmann,et al.  Satisfying General Proximity/Similarity Queries with Metric Trees , 1991, Inf. Process. Lett..

[4]  Jitendra Malik,et al.  Computational framework for determining stereo correspondence from a set of linear spatial filters , 1992, Image Vis. Comput..

[5]  Kenichi Kanatani,et al.  Detection of Surface Orientation and Motion from Texture by a Stereological Technique , 1984, Artif. Intell..

[6]  David Mumford,et al.  A Bayesian treatment of the stereo correspondence problem using half-occluded regions , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  V. Arnold,et al.  Ordinary Differential Equations , 1973 .

[8]  Thomas O. Binford,et al.  Depth from Edge and Intensity Based Stereo , 1981, IJCAI.

[9]  Andrew Blake,et al.  Shape from Texture: Estimation, Isotropy and Moments , 1990, Artif. Intell..

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

[11]  R. Manmatha,et al.  A framework for recovering affine transforms using points, lines or image brightnesses , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[12]  J P Frisby,et al.  PMF: A Stereo Correspondence Algorithm Using a Disparity Gradient Limit , 1985, Perception.

[13]  Larry H. Matthies,et al.  Error analysis of a real-time stereo system , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  W. Eric L. Grimson,et al.  Computational Experiments with a Feature Based Stereo Algorithm , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  James J. Little,et al.  Direct evidence for occlusion in stereo and motion , 1990, Image Vis. Comput..

[16]  Roberto Manduchi,et al.  Stereo Without Search , 1996, ECCV.

[17]  Aaron F. Bobick,et al.  Disparity-Space Images and Large Occlusion Stereo , 1994, ECCV.

[18]  Jitendra Malik,et al.  A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters , 1991, ECCV.

[19]  Narendra Ahuja,et al.  Matching Two Perspective Views , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  N. G. Parke,et al.  Ordinary Differential Equations. , 1958 .

[21]  Alessandro Verri,et al.  Motion analysis from first-order properties of optical flow , 1992, CVGIP Image Underst..

[22]  Takeo Kanade,et al.  Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Roberto Cipolla,et al.  Extracting the Affine Transformation from Texture Moments , 1994, ECCV.

[24]  D. Struik.  Lectures on classical differential geometry , 1951 .

[25]  Jitendra Malik,et al.  Determining Three-Dimensional Shape from Orientation and Spatial Frequency Disparities , 1991, ECCV.

[26]  Alan C. Bovik,et al.  Shape-from-texture by wavelet-based measurement of local spectral moments , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[27]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Peter N. Yianilos,et al.  Data structures and algorithms for nearest neighbor search in general metric spaces , 1993, SODA '93.

[29]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.