Volume XL-3/W2
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-3/W2, 197-204, 2015
https://doi.org/10.5194/isprsarchives-XL-3-W2-197-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-3/W2, 197-204, 2015
https://doi.org/10.5194/isprsarchives-XL-3-W2-197-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.

  10 Mar 2015

10 Mar 2015

ROBUST SPARSE MATCHING AND MOTION ESTIMATION USING GENETIC ALGORITHMS

M. Shahbazi1, G. Sohn2, J. Théau1, and P. Ménard3 M. Shahbazi et al.
  • 1Dept. of Applied Geomatics, Université de Sherbrooke, Boul. de l'Université, Sherbrooke, Québec, Canada
  • 2Dept. of Geomatics Engineering, York University, Keele Street, Toronto, Ontario, Canada
  • 3Centre de géomatique du Québec, Saguenay, Québec, Canada

Keywords: Genetic Algorithm, Structure from Motion, Epipolar Geometry, Image Matching, Outlier Detection

Abstract. In this paper, we propose a robust technique using genetic algorithm for detecting inliers and estimating accurate motion parameters from putative correspondences containing any percentage of outliers. The proposed technique aims to increase computational efficiency and modelling accuracy in comparison with the state-of-the-art via the following contributions: i) guided generation of initial populations for both avoiding degenerate solutions and increasing the rate of useful hypotheses, ii) replacing random search with evolutionary search, iii) possibility of evaluating the individuals of every population by parallel computation, iv) being performable on images with unknown internal orientation parameters, iv) estimating the motion model via detecting a minimum, however more than enough, set of inliers, v) ensuring the robustness of the motion model against outliers, degeneracy and poorperspective camera models, vi) making no assumptions about the probability distribution of inliers and/or outliers residuals from the estimated motion model, vii) detecting all the inliers by setting the threshold on their residuals adaptively with regard to the uncertainty of the estimated motion model and the position of the matches. 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, MSAC, MLESAC, Least Trimmed Squares and Least Median of Squares. Experimental results proved that the proposed approach perform better than others in terms of accuracy of motion estimation, accuracy of inlier detection and the computational efficiency.