Epipolar geometry estimation based on genetic algorithm under different strategies

The paper addresses the problem of robust fundamental matrix estimation employing a new method based on genetic algorithms under different strategies, which use each gene to stand for a pair of correspondences, take every chromosome as a minimum subset for epipolar geometry estimation, and compute the fundamental matrix according to the length of the chromosomes. The method eventually converges to a globally optimal solution and is relatively unaffected by outliers. Experiments with both synthetic data and real images show that our method is more robust and precise than other typical methods.