The linear geo-photometric constraint for image matching, structure reconstruction, image synthesis and object recognition

Author

Xu, Gang ; Guo, Guodong

Author_Institution

Lab. of Comput. Vision, Ritsumeikan Univ., Shiga, Japan

fYear

1999

fDate

1999

Firstpage

55

Lastpage

62

Abstract

We show that under orthographic projection (can be relaxed to weak perspective, or scaled orthographic projection) and with a fixed camera and fixed light sources, the images of a moving Lambertian surface can be modelled as a linear combination of three distinct images, with identical coefficients for both shape and intensity. We call this the linear geo-photometric constraint. Using this new constraint, we can match images, reconstruct structure, synthesize new images and recognize objects. Experimental results are shown

Keywords

cameras; computer graphics; image matching; image reconstruction; object recognition; experimental results; fixed camera; fixed light sources; image matching; image shape; image synthesis; intensity; linear geophotometric constraint; moving Lambertian surface; object recognition; orthographic projection; structure reconstruction; Cameras; Image matching; Image recognition; Image reconstruction; Light sources; Shape; Surface reconstruction;

fLanguage

English

Publisher

ieee

Conference_Titel

Multi-View Modeling and Analysis of Visual Scenes, 1999. (MVIEW '99) Proceedings. IEEE Workshop on

Conference_Location

Fort Collins, CO

Print_ISBN

0-7695-0110-9

Type

conf

DOI

10.1109/MVIEW.1999.781083

Filename

781083