Stereo Matching as a Nearest-Neighbor Problem

Authors:
Carlo Tomasi;Roberto Manduchi
Affiliations:
Stanford Univ., Stanford, CA;Stanford Univ., Stanford, CA
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1998

Citing 4
Cited 8

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Matching Two Perspective Views

IEEE Transactions on Pattern Analysis and Machine Intelligence
Error Analysis of a Real-Time Stereo System

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Stereo Without Search

Stereo Without Search

Fast and Accurate Handwritten Character Recognition Using Approximate Nearest Neighbours Search on Large Databases

Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Advances in Computational Stereo

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast and versatile algorithm for nearest neighbor search based on a lower bound tree

Pattern Recognition
Markov random field approach to region extraction using Tabu Search

Journal of Visual Communication and Image Representation
An effective stereo matching algorithm with optimal path cost aggregation

DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Background updating with the use of intrinsic curves

ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
Toward visually inferring the underlying causal mechanism in a traffic-light-controlled crossroads

ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems
Using normal vectors for stereo correspondence construction

KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part I

Quantified Score

Hi-index	0.14

Visualization

Abstract

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.