Bags of Binary Words for Fast Place Recognition in Image Sequences

We propose a novel method for visual place recognition using bag of words obtained from accelerated segment test (FAST)+BRIEF features. For the first time, we build a vocabulary tree that discretizes a binary descriptor space and use the tree to speed up correspondences for geometrical verification....

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on robotics Vol. 28; no. 5; pp. 1188 - 1197
Main Authors: Galvez-López, D., Tardos, J. D.
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.10.2012
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Acceleration
Applied sciences
Artificial intelligence
Bag of binary words
Cameras
Computer science; control theory; systems
computer vision
Control theory. Systems
Data processing. List processing. Character string processing
Exact sciences and technology
Feature extraction
Geometry
Indexes
Memory organisation. Data processing
Pattern recognition. Digital image processing. Computational geometry
place recognition
Robotics
Robots
simultaneous localization and mapping (SLAM)
Software
Vectors
Vocabulary
Cartography
Computer vision
Vocabulary
Image recognition
Tree(graph)
Moving robot
Competitiveness
Information retrieval
Pattern recognition
simultaneous localization and mapping (SLAM)
Binary code
Robotics
Bag of words
Bag of binary words
Binary descriptor
place recognition
Selection criterion
Feature extraction
Localization
Pattern extraction
Execution time
ISSN:1552-3098, 1941-0468
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a novel method for visual place recognition using bag of words obtained from accelerated segment test (FAST)+BRIEF features. For the first time, we build a vocabulary tree that discretizes a binary descriptor space and use the tree to speed up correspondences for geometrical verification. We present competitive results with no false positives in very different datasets, using exactly the same vocabulary and settings. The whole technique, including feature extraction, requires 22 ms/frame in a sequence with 26 300 images that is one order of magnitude faster than previous approaches.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ISSN:1552-3098
1941-0468
DOI:10.1109/TRO.2012.2197158