A Robust Method for Estimating Image Geometry With Local Structure Constraint

Abstract

The estimation of image geometry benefits many applications in the field of computer vision, such as stereo correspondence, 3-D reconstruction, and camera self-calibration. It is very challenging since the proportion of inliers in putative correspondences is usually very low, and traditional image geometry estimation methods (such as Ransac) suffer from low accuracy at a high outlier ratio. In this paper, we tackle the two-view image geometry estimation problem and propose a new robust estimation method $L_{2}E$ -LSC (short for $L_{2}E$ with local structure constraint) based on the $L_{2}E$ algorithm. In particular, we first establish initial correspondences by feature description matches, and then estimate the fundamental matrix and homography using $L_{2}E$ -LSC and get the refined correspondences. The $L_{2}E$ -LSC is able to robustly deal with the noise and outliers contained in point correspondences. Extensive experiments conducted on real images from public available datasets have demonstrated that it can achieve good estimation accuracy and superior performance over previous approaches, particularly when there are severe outliers.