Premium
Topological map learning from outdoor image sequences
Author(s) -
He Xuming,
Zemel Richard S.,
Mnih Volodymyr
Publication year - 2006
Publication title -
journal of field robotics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.152
H-Index - 96
eISSN - 1556-4967
pISSN - 1556-4959
DOI - 10.1002/rob.20170
Subject(s) - image (mathematics) , topological map , feature (linguistics) , artificial intelligence , manifold (fluid mechanics) , topology (electrical circuits) , computer science , computer vision , pattern recognition (psychology) , geography , mathematics , engineering , combinatorics , robot , mobile robot , mechanical engineering , linguistics , philosophy
We propose an approach to building topological maps of environments based on image sequences. The central idea is to use manifold constraints to find representative feature prototypes, so that images can be related to each other, and thereby to camera poses in the environment. Our topological map is built incrementally, performing well after only a few visits to a location. We compare our method to several other approaches to representing images. During tests on novel images from the same environment, our method attains the highest accuracy in finding images depicting similar camera poses, including generalizing across considerable seasonal variations. © 2007 Wiley Periodicals, Inc.