Efficient large-scale geometric verification for structure from motion

•GPU-based fundamental matrix estimation algorithm.•GPU-based homography matrix estimation algorithm.•GPU-based fast optimization algorithm. Geometric verification is a fundamental problem in epipolar geometry, which estimates fundamental matrix and homography matrix to confirm that image pairs shar...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition letters 2019-07, Vol.125, p.166-173
Main Authors: Xu, Qingshan, Li, Jie, Tao, Wenbing, Ming, Delie
Format: Article
Language:English
Subjects:
Fundamental matrix
Geometric verification
Gpu-based model
Homography matrix
Large-scale SfM
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•GPU-based fundamental matrix estimation algorithm.•GPU-based homography matrix estimation algorithm.•GPU-based fast optimization algorithm. Geometric verification is a fundamental problem in epipolar geometry, which estimates fundamental matrix and homography matrix to confirm that image pairs share a common 3D structure. However, it still suffers from low efficiency when it encounters large-scale Structure from Motion (SfM). In this paper, we adopt the linear congruence algorithm to sample point-pairs in parallel. Then, we propose to simultaneously estimate a certain number of candidate fundamental/homography matrices in GPU to avoid the iterative random point sets sampling and perform matrix estimation based on these point sets, followed by best matrix selection and further parallel refinement. Experiments on extensive datasets show that our GPU-based geometric verification is up to seventy times faster than original iteration method while maintaining comparable satisfactory 3D reconstruction results.
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2018.09.028