Scale Invariant Feature Transform on the Sphere: Theory and Applications

A SIFT algorithm in spherical coordinates for omnidirectional images is proposed. This algorithm can generate two types of local descriptors, Local Spherical Descriptors and Local Planar Descriptors. With the first ones, point matching between two omnidirectional images can be performed, and with th...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of computer vision Vol. 98; no. 2; pp. 217 - 241
Main Authors Cruz-Mota, Javier, Bogdanova, Iva, Paquier, Benoît, Bierlaire, Michel, Thiran, Jean-Philippe
Format Journal Article
LanguageEnglish
Published Boston Springer US 01.06.2012
Springer
Springer Nature B.V
Subjects
Algorithms
Analysis
Applied sciences
Artificial Intelligence
Computer Imaging
Computer Science
Computer science; control theory; systems
Computer vision
Exact sciences and technology
Image Processing and Computer Vision
Image processing systems
Invariants
Laboratories
Mapping
Matching
Pattern Recognition
Pattern Recognition and Graphics
Pattern recognition. Digital image processing. Computational geometry
Sensors
Spherical coordinates
Standard deviation
Studies
Transforms
Vision
Vision systems
Matching
Omnidirectional vision
(Spherical) image processing
Feature extraction
SIFT
Object detection
Performance evaluation
Scale invariance
Image registration
Computer vision
Panoramic photography
Image processing
Pattern recognition
Object recognition
Sphere
Computational geometry
Scene analysis
Spherical coordinate
Point estimation
Pattern extraction
Online AccessGet full text

Cover

More Information
Summary:A SIFT algorithm in spherical coordinates for omnidirectional images is proposed. This algorithm can generate two types of local descriptors, Local Spherical Descriptors and Local Planar Descriptors. With the first ones, point matching between two omnidirectional images can be performed, and with the second ones, the same matching process can be done but between omnidirectional and planar images. Furthermore, a planar to spherical mapping is introduced and an algorithm for its estimation is given. This mapping allows to extract objects from an omnidirectional image given their SIFT descriptors in a planar image. Several experiments, confirming the promising and accurate performance of the system, are conducted.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-011-0505-4