Image based reconstruction using hybrid optimization of simulated annealing and genetic algorithm

Abstract

This work deals with the problem of estimating depth information of 3-D surface from a pair of images. The proposed method relies on Second-order Priors on the smoothness of 3D surface which cause intractable (non-submodular) optimization problems; we solved it by using the strategy of Hybrid Optimization of Simulated Annealing and Genetic Algorithm. Experimental results demonstrate the Second-order priors are a better model of typical scenes than first-order priors and the performance of the hybrid algorithm outperforms SA and GA alone.