Dense versus Sparse Approaches for Estimating the Fundamental Matrix

There are two main strategies for solving correspondence problems in computer vision: sparse local feature based approaches and dense global energy based methods. While sparse feature based methods are often used for estimating the fundamental matrix by matching a small set of sophistically optimise...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision Vol. 96; no. 2; pp. 212 - 234
Main Authors: Valgaerts, Levi, Bruhn, Andrés, Mainberger, Markus, Weickert, Joachim
Format: Journal Article
Language:English
Published: Boston Springer US 01.01.2012
Springer
Springer Nature B.V
Subjects:
Algorithms
Analysis
Applied sciences
Artificial Intelligence
Computer Imaging
Computer Science
Computer science; control theory; systems
Computer vision
Correspondence
Energy
Energy use
Estimates
Estimating
Exact sciences and technology
Feature based
Geometry
Image Processing and Computer Vision
Image processing systems
Machine vision
Methods
Optimization
Partial differential equations
Pattern Recognition
Pattern Recognition and Graphics
Pattern recognition. Digital image processing. Computational geometry
State of the art
Strategy
Studies
Variational methods
Vision
Vision systems
Performance evaluation
3D reconstruction
Fundamental matrix
Optical flow
Energy method
Computer vision
Image processing
Correspondence principle
Modeling
Image reconstruction
Problem solving
Variational calculus
Tridimensional image
ISSN:0920-5691, 1573-1405
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:There are two main strategies for solving correspondence problems in computer vision: sparse local feature based approaches and dense global energy based methods. While sparse feature based methods are often used for estimating the fundamental matrix by matching a small set of sophistically optimised interest points, dense energy based methods mark the state of the art in optical flow computation. The goal of our paper is to show that this separation into different application domains is unnecessary and can be bridged in a natural way. As a first contribution we present a new application of dense optical flow for estimating the fundamental matrix. Comparing our results with those obtained by feature based techniques we identify cases in which dense methods have advantages over sparse approaches. Motivated by these promising results we propose, as a second contribution, a new variational model that recovers the fundamental matrix and the optical flow simultaneously as the minimisers of a single energy functional. In experiments we show that our coupled approach is able to further improve the estimates of both the fundamental matrix and the optical flow. Our results prove that dense variational methods can be a serious alternative even in classical application domains of sparse feature based approaches.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-011-0466-7