Evolutionary optimization for robust epipolar-geometry estimation and outlier detection

DOI10.3390/A10030087MaRDI QIDQ1657044zbMATH OpenOpenAlexFDO

Authors Mozhdeh Shahbazi, Gunho Sohn, Jérôme Théau

Publication date 13 August 2018

Published in Algorithms (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.3390/a10030087

zbMATH Keywords

adaptive thresholdingepipolar geometryevolutionary searchgenetic algorithmguided samplingoutlier detectionsparse matching

Mathematics Subject Classification ID

Image analysis in multivariate analysis (62H35) Approximation methods and heuristics in mathematical programming (90C59)

Review text

Summary: In this paper, a robust technique based on a genetic algorithm is proposed for estimating two-view epipolar-geometry of uncalibrated perspective stereo images from putative correspondences containing a high percentage of outliers. The advantages of this technique are three-fold: (i) replacing random search with evolutionary search applying new strategies of encoding and guided sampling; (ii) robust and fast estimation of the epipolar geometry via detecting a more-than-enough set of inliers without making any assumptions about the probability distribution of the residuals; (iii) determining the inlier-outlier threshold based on the uncertainty of the estimated model. The proposed method was evaluated both on synthetic data and real images. The results were compared with the most popular techniques from the state-of-the-art, including RANSAC (random sample consensus), MSAC, MLESAC, Cov-RANSAC, LO-RANSAC, StaRSAC, Multi-GS RANSAC and least median of squares (LMedS). Experimental results showed that the proposed approach performed better than other methods regarding the accuracy of inlier detection and epipolar-geometry estimation, as well as the computational efficiency for datasets majorly contaminated by outliers and noise.

Recommendations

• Epipolar geometry estimation based on evolutionary agents
• scientific article; zbMATH DE number 2010171
• Two-view orthographic epipolar geometry: minimal and optimal solvers
• scientific article; zbMATH DE number 2044068
• Improving efficiency of linear techniques to estimate epipolar geometry

Cites work

• A consensus sampling technique for fast and robust model Fitting
• A real coded genetic algorithm for solving integer and mixed integer optimization problems
• Bayesian model estimation and selection for epipolar geometry and generic manifold fitting
• Epipolar geometry estimation based on evolutionary agents
• High-breakdown robust multivariate methods
• scientific article; zbMATH DE number 1229396 (Why is no real title available?)
• scientific article; zbMATH DE number 6159604 (Why is no real title available?)

Cited in

(1)

• Epipolar geometry estimation based on evolutionary agents

Describes a project that uses

Uses Software

• USAC
• NAPSAC

This page was built for publication: Evolutionary optimization for robust epipolar-geometry estimation and outlier detection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1657044)