Multi-Camera Very Wide Baseline Feature Matching Based On View-Adaptive Junction Detection
Authors: Maykel Pérez and Luis Salgado and Jon Arróspide and Javier Marinas and Marcos Nieto
Date: 05.09.2012
Abstract
This paper presents a strategy for solving the feature matching problem in calibrated very wide-baseline camera settings. In this kind of settings, perspective distortion, depth discontinuities and occlusion represent enormous challenges. The proposed strategy addresses them by using geometrical information, specifically by exploiting epipolarconstraints. As a result it provides a sparse number of reliable feature points for which 3D position is accurately recovered. Special features known as junctions are used for robust matching. In particular, a strategy for refinement of junction end-point matching is proposed which enhances usual junction-based approaches. This allows to compute cross-correlation between perfectly aligned plane patches in both images, thus yielding better matching results. Evaluation of experimental results proves the effectiveness of the proposed algorithm in very wide-baseline environments.
BIB_text
@Article {
author = {Maykel Pérez and Luis Salgado and Jon Arróspide and Javier Marinas and Marcos Nieto},
title = {Multi-Camera Very Wide Baseline Feature Matching Based On View-Adaptive Junction Detection},
keywds = {
Junctions,Feature extraction,Image edge detection,Detectors,Correlation,Geometry,Cameras,cross-correlation,wide baseline,feature matching,projec
}
abstract = {
This paper presents a strategy for solving the feature matching problem in calibrated very wide-baseline camera settings. In this kind of settings, perspective distortion, depth discontinuities and occlusion represent enormous challenges. The proposed strategy addresses them by using geometrical information, specifically by exploiting epipolarconstraints. As a result it provides a sparse number of reliable feature points for which 3D position is accurately recovered. Special features known as junctions are used for robust matching. In particular, a strategy for refinement of junction end-point matching is proposed which enhances usual junction-based approaches. This allows to compute cross-correlation between perfectly aligned plane patches in both images, thus yielding better matching results. Evaluation of experimental results proves the effectiveness of the proposed algorithm in very wide-baseline environments.
}
isbn = {978-1-4673-2448-9},
isi = {1},
date = {2012-09-05},
year = {2012},
}
author = {Maykel Pérez and Luis Salgado and Jon Arróspide and Javier Marinas and Marcos Nieto},
title = {Multi-Camera Very Wide Baseline Feature Matching Based On View-Adaptive Junction Detection},
keywds = {
Junctions,Feature extraction,Image edge detection,Detectors,Correlation,Geometry,Cameras,cross-correlation,wide baseline,feature matching,projec
}
abstract = {
This paper presents a strategy for solving the feature matching problem in calibrated very wide-baseline camera settings. In this kind of settings, perspective distortion, depth discontinuities and occlusion represent enormous challenges. The proposed strategy addresses them by using geometrical information, specifically by exploiting epipolarconstraints. As a result it provides a sparse number of reliable feature points for which 3D position is accurately recovered. Special features known as junctions are used for robust matching. In particular, a strategy for refinement of junction end-point matching is proposed which enhances usual junction-based approaches. This allows to compute cross-correlation between perfectly aligned plane patches in both images, thus yielding better matching results. Evaluation of experimental results proves the effectiveness of the proposed algorithm in very wide-baseline environments.
}
isbn = {978-1-4673-2448-9},
isi = {1},
date = {2012-09-05},
year = {2012},
}
