A Robust Method for Estimating the Fundamental Matrix

摘要

Two images of a single scene/object are related by the epipolar geometry, which can be described by a 3x3 singular matrix called the fundamental matrix in uncalibrated system. It captures all geometric information contained in two images, and robust estimation of fundamental matrix is the key step in many applications such as scene modeling. In this paper, we apply a maximum likelihood estimation method-MAPSAC to estimate the fundamental matrix, and compare it with iterative least squares and linear method followed by nonlinear. The results show that MAPSAC method yield accurate and robust fundamental matrix.