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

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 reconstructi...

Full description

Saved in:
Bibliographic Details
Published in2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings Vol. 2; pp. II - 272
Main Authors Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2003
Subjects
Brightness
Computer science
Geometry
Image recognition
Image reconstruction
Image segmentation
Layout
Object recognition
Pattern matching
Shape
Online AccessGet full text

Cover

More Information
Summary: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.
ISBN:0769519008
9780769519005
ISSN:1063-6919
DOI:10.1109/CVPR.2003.1211480