Improved motion stereo matching based on a modified dynamic programming

Author

Mozerov, Mikhail ; Kober, Vitaly ; Choi, Tae S.

Author_Institution

Lab. of Digital Opt., Inst. of Inf. Trans. Problems, Moscow, Russia

Volume

2

fYear

2000

fDate

2000

Firstpage

501

Abstract

A new method for computing precise depth map estimates of 3D shape of a moving object is proposed. 3D shape recovery in motion stereo is formulated as a matching optimization problem of multiple stereo images. The proposed method is a heuristic modification of dynamic programming applied to two-dimensional optimization problem. 3D shape recovery using real motion stereo images demonstrates a good performance of the algorithm in terms of reconstruction accuracy

Keywords

dynamic programming; image motion analysis; image reconstruction; optimisation; stereo image processing; 3D shape; 3D shape recovery; depth map estimates; modified dynamic programming; motion stereo matching; moving object; multiple stereo images; optimization; optimization problem; real motion stereo images; reconstruction accuracy; Belts; Cameras; Computational complexity; Dynamic programming; Image reconstruction; Optical variables control; Optimization methods; Pixel; Shape; Stereo image processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on

Conference_Location

Hilton Head Island, SC

ISSN

1063-6919

Print_ISBN

0-7695-0662-3

Type

conf

DOI

10.1109/CVPR.2000.854894

Filename

854894