Dense matching of two views with large displacement

Author

Yokoya, Naokazu

Author_Institution

Nara Inst. of Sci. & Technol., Japan

Volume

1

fYear

1994

fDate

13-16 Nov 1994

Firstpage

213

Abstract

This paper describes a method of establishing dense matching of two views with large displacements. The problem addressed is formulated as the minimization of an energy functional that combines a similarity term and a smoothness term. The minimization of the energy functional reduces to solving a large system of nonlinear equations which is a discretized version of the Euler-Lagrange equation for the energy minimization problem at each image point. A dense displacement map is computed by solving the system of equations using a coarse-to-fine approach. The method has been successfully experimented with two applications: (1) computing binocular disparities from stereo pair images and (2) computing a dense displacement vector field (optical flow) from two views in a time-varying image sequence

Keywords

image matching; image sequences; minimisation; nonlinear equations; stereo image processing; vectors; Euler-Lagrange equation; binocular disparities; coarse-to-fine approach; dense displacement vector field; dense matching; energy functional; energy minimization problem; gradient method; image point; large displacement; nonlinear equations; optical flow; similarity term; smoothness term; stereo pair images; time-varying image sequence; views; Application software; Computer applications; Feature extraction; Gradient methods; Image motion analysis; Image sequences; Nonlinear equations; Nonlinear optics; Optical computing; Stereo vision;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference

Conference_Location

Austin, TX

Print_ISBN

0-8186-6952-7

Type

conf

DOI

10.1109/ICIP.1994.413306

Filename

413306