3D object modeling and recognition using affine-invariant patches and multi-view spatial constraints

Author

Rothganger, Fredrick ; Lazebnik, Svetlana ; Schmid, Cordelia ; Ponce, Jean

Author_Institution

Dept. of Comput. Sci., Illinois Univ., Urbana, IL, USA

Volume

2

fYear

2003

Abstract

This paper presents a representation for three-dimensional objects in terms of affine-invariant image patches and their spatial relationships. Multi-view constraints associated with groups of patches are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true three-dimensional affine and Euclidean models from multiple images and their recognition in a single photograph taken from an arbitrary viewpoint. The proposed approach does not require a separate segmentation stage and is applicable to cluttered scenes. Preliminary modeling and recognition results are presented.

Keywords

computer vision; image recognition; image reconstruction; image representation; image segmentation; object recognition; stereo image processing; 3D object modeling; Euclidean model; affine-invariant patch; arbitrary viewpoint; cluttered scene; geometric consistency; image matching; image recognition; image reconstruction; multiview spatial constraint; normalized representation; object appearance; object recognition; photograph object; spatial relationship; three-dimensional object representation; Brightness; Computer science; Geometry; Image recognition; Image reconstruction; Image segmentation; Layout; Object recognition; Pattern matching; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on

ISSN

1063-6919

Print_ISBN

0-7695-1900-8

Type

conf

DOI

10.1109/CVPR.2003.1211480

Filename

1211480