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

Authors:
Cong Liu;Wangge Wan;Youyong Wu
Affiliations:
Shanghai University, ShangHai, China;Shanghai University, ShangHai, China;Shanghai University, ShangHai, China
Venue:
Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
Year:
2009

Citing 11
Cited 0

A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Asymmetrical Occlusion Handling Using Graph Cut for Multi-View Stereo

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Shape and the Stereo Correspondence Problem

International Journal of Computer Vision
Surface Geometric Constraints for Stereo in Belief Propagation

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Dense Photometric Stereo: A Markov Random Field Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time stereo vision using semi-global matching on programmable graphics hardware

ACM SIGGRAPH 2006 Sketches
Large scale evolutionary optimization using cooperative coevolution

Information Sciences: an International Journal
A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Rethinking the prior model for stereo

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Evolutionary optimization with Markov random field prior

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

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.