Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/wiley/topological-map-learning-from-outdoor-image-sequences-Y5RroZzXUC
References (27)
-
Robert Sim, G. Dudek (2001)
Learning Generative Models of Scene FeaturesInternational Journal of Computer Vision, 60
-
B. Kuipers, P. Beeson (2002)
Bootstrap learning for place recognition -
S. Thrun, Wolfram Burgard, D. Fox (2005)
Probabilistic Robotics (Intelligent Robotics and Autonomous Agents) -
(2004)
2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28 - October 2, 2004 -
G. Grudic, J. Mulligan (2005)
Topological Mapping with Multiple Visual Manifolds -
Pablo Sala, Robert Sim, A. Shokoufandeh, Sven Dickinson (2004)
Landmark Selection for Vision-Based NavigationIEEE Transactions on Robotics, 22
-
A. Rahimi, B. Recht, Trevor Darrell (2005)
Learning appearance manifolds from video2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 1
-
Jihun Ham, Yuanqing Lin, Daniel Lee (2005)
Learning nonlinear appearance manifolds for robot localization2005 IEEE/RSJ International Conference on Intelligent Robots and Systems
-
D. Lowe (2004)
Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 60
-
G. Carneiro, A. Jepson (2005)
The distinctiveness, detectability, and robustness of local image features2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 2
-
J. Beis, D. Lowe (1997)
Shape indexing using approximate nearest-neighbour search in high-dimensional spacesProceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
-
A. Davison (2003)
Real-time simultaneous localisation and mapping with a single cameraProceedings Ninth IEEE International Conference on Computer Vision
-
Stephen Se, D. Lowe, J. Little (2005)
Vision-based global localization and mapping for mobile robotsIEEE Transactions on Robotics, 21
-
Stephen Se, D. Lowe, J. Little (2002)
Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual LandmarksThe International Journal of Robotics Research, 21
-
Iwan Ulrich, I. Nourbakhsh (2000)
Appearance-based Place Recognition for Topological Localization -
Robert Sim, G. Dudek (2004)
Self-Organizing Visual Maps -
Jürgen Wolf, Wolfram Burgard, H. Burkhardt (2002)
Using an Image Retrieval System for Vision-Based Mobile Robot Localization -
Geoffrey Hinton, S. Roweis (2002)
Stochastic Neighbor Embedding -
Llew Mason, Jonathan Baxter, P. Bartlett, Marcus Frean (2000)
Functional Gradient Techniques for Combining Hypotheses -
J. Kosecka, Xiaolong Yang (2004)
Location Recognition and Global Localization Based on Scale-Invariant Keypoints -
D. Robertson, R. Cipolla (2004)
An Image-Based System for Urban Navigation -
J. Tenenbaum, V. Silva, J. Langford (2000)
A global geometric framework for nonlinear dimensionality reduction.Science, 290 5500
-
Yoshua Bengio, Jean-François Paiement, Pascal Vincent, Olivier Delalleau, Nicolas Roux, M. Ouimet (2003)
Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering -
S. Perkins, Kevin Lacker, J. Theiler (2003)
Grafting: Fast, Incremental Feature Selection by Gradient Descent in Function SpaceJ. Mach. Learn. Res., 3
-
Y. Takeuchi, M. Hebert, H. Takeuchi
Finding Images of Landmarks in Video Sequences -
David Bradley, R. Patel, N. Vandapel, S. Thayer (2005)
Real-time image-based topological localization in large outdoor environments2005 IEEE/RSJ International Conference on Intelligent Robots and Systems
-
Michael Bowling, Dana Wilkinson, A. Ghodsi, Adam Milstein (2005)
Subjective Localization with Action Respecting Embedding
- Publisher
- Wiley
- Copyright
- Copyright © 2007 Wiley Periodicals, Inc., A Wiley Company
- ISSN
- 1556-4959
- eISSN
- 1556-4967
- DOI
- 10.1002/rob.20170
- Publisher site
- See Article on Publisher Site
Abstract
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.
Journal
Journal of Field Robotics – Wiley
Published: Nov 1, 2006