Coarse-to-fine vision-based localization by indexing scale-Invariant features

This paper presents a novel coarse-to-fine global localization approach inspired by object recognition and text retrieval techniques. Harris-Laplace interest points characterized by scale-invariant transformation feature descriptors are used as natural landmarks. They are indexed into two databases:...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on systems, man and cybernetics. Part B, Cybernetics Vol. 36; no. 2; pp. 413 - 422
Main Authors: Junqiu Wang, Hongbin Zha, Cipolla, R.
Format: Journal Article
Language:English
Published: United States IEEE 01.04.2006
Subjects:
Algorithms
Artificial Intelligence
Coarse-to-fine localization
Computer vision
Cybernetics
Detectors
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image matching
Indexing
Information Storage and Retrieval - methods
Layout
Lighting
Localization
Mathematical models
Mobile robots
Object recognition
Orbital robotics
Pattern Recognition, Automated - methods
Position (location)
Reproducibility of Results
scale-invariant features
Sensitivity and Specificity
Spatial databases
vector space model
visual vocabulary
ISSN:1083-4419
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a novel coarse-to-fine global localization approach inspired by object recognition and text retrieval techniques. Harris-Laplace interest points characterized by scale-invariant transformation feature descriptors are used as natural landmarks. They are indexed into two databases: a location vector space model (LVSM) and a location database. The localization process consists of two stages: coarse localization and fine localization. Coarse localization from the LVSM is fast, but not accurate enough, whereas localization from the location database using a voting algorithm is relatively slow, but more accurate. The integration of coarse and fine stages makes fast and reliable localization possible. If necessary, the localization result can be verified by epipolar geometry between the representative view in the database and the view to be localized. In addition, the localization system recovers the position of the camera by essential matrix decomposition. The localization system has been tested in indoor and outdoor environments. The results show that our approach is efficient and reliable.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1083-4419
DOI:10.1109/TSMCB.2005.859085