Alignment of uncalibrated images for multi-view classification

Date
2011
Advisor
Instructor
Source Title
2011 18th IEEE International Conference on Image Processing
Print ISSN
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
2365 - 2368
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Abstract

Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pair-wise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of images is necessary prior to distance computation. We propose a method for the registration of uncalibrated images that capture the same 3D scene or object. We model the depth map of the scene as an algebraic surface, which yields a warp model in the form of a rational function between image pairs. The warp model is computed by minimizing the registration error, where the registered image is a weighted combination of two images generated with two different warp functions estimated from feature matches and image intensity functions in order to provide robust registration. We demonstrate the flexibility of our alignment method by experimentation on several wide-baseline image pairs with arbitrary scene geometries and texture levels. Moreover, the results on multi-view image classification suggest that the proposed alignment method can be effectively used in graph-based classification algorithms for the computation of pairwise distances where it achieves significant improvements over distance computation without prior alignment. © 2011 IEEE.

Course
Other identifiers
Book Title
Keywords
3D scenes, Algebraic surfaces, Alignment methods, Classification algorithm, Depth Map, Distance computation, Euclidean distance, Feature match, Graph-based, Image alignment, Image intensity functions, Image pairs, Image warping, Multi-view image, Multi-views, Pairwise distances, Registered images, Registration error, Robust registration, Similarity measure, Uncalibrated images, Wide-baseline images, Algorithms, Alignment, Image analysis, Image classification, Image matching, Image registration, Rational functions, Three dimensional
Citation
Published Version (Please cite this version)