A survey addressing the fundamental matrix estimation problem

Abstract

Epipolar geometry is a key point in computer vision and the fundamental matrix estimation is the only way to compute it. This article surveys several methods of fundamental matrix estimation which have been classified into linear methods, iterative methods and robust methods. All of these methods have been programmed and their accuracy analysed using real images. A summary, accompanied with experimental results, is given and the code is available in Internet(http://eia.udg.es/"armangue/research).

Two quantitative measures of inlier distributions for precise fundamental matrix estimation

“…Because the fundamental matrix contains the intrinsic parameters and the rigid transformation between both cameras, it is widely used in various areas such as stereo matching, image rectification, outlier detection and computation of projective invariants. Several algorithms for the estimation of a fundamental matrix are categorized into three methods: the linear, the iterative and the robust (Salvi et al, 2001). The linear and the iterative methods use some points to estimate the fundamental matrix.…”

A Realistic 3-D Reverse Modeling System Based on Real-World Sampling Dataset

“…In general, the 3-D coordinates of a calibration object are very difficult to accurately measure. So some other calibration approaches like [10], which do not have such a rigorous requirement, have been presented. But they often produce inaccurate calibration results.…”

Outlier rejection by oriented tracks to aid pose estimation from video

“…These techniques-designed to increase the robustness of the epipolar geometry estimation-include robust geometry estimators as well as prefiltering techniques. The effects of outliers on the epipolar geometry estimation can be alleviated through robust algorithms (Zhang, 1998;Pollefeys et al, 1999;Salvi et al, 2001). However, the computational cost of these algorithms greatly increases with the percentage of outliers present in the data.…”