Robust epipolar geometry estimation using genetic algorithm

摘要

Epipolar geometry is an important constraint to establish the correspondences in stereo vision. The 3 × 3 fundamental matrix describes the epipolar geometry between two uncalibrated images. In this paper, we formulate the epipolar geometry estimation as a global optimization problem, and then we present a genetic algorithm for parameter searching. Experiments with simulated and real data show that our algorithm performs very well in terms of robustness to outliers, rate of convergence and quality of the final estimation.