Appearance-only SLAM at large scale with FAB-MAP 2.0
Top Cited Papers
- 12 November 2010
- journal article
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 30 (9), 1100-1123
- https://doi.org/10.1177/0278364910385483
Abstract
We describe a new formulation of appearance-only SLAM suitable for very large scale place recognition. The system navigates in the space of appearance, assigning each new observation to either a new or a previously visited location, without reference to metric position. The system is demonstrated performing reliable online appearance mapping and loop-closure detection over a 1000 km trajectory, with mean filter update times of 14 ms. The scalability of the system is achieved by defining a sparse approximation to the FAB-MAP model suitable for implementation using an inverted index. Our formulation of the problem is fully probabilistic and naturally incorporates robustness against perceptual aliasing. We also demonstrate that the approach substantially outperforms the standard term-frequency inverse-document-frequency (tf-idf) ranking measure. The 1000 km data set comprising almost a terabyte of omni-directional and stereo imagery is available for use, and we hope that it will serve as a benchmark for future systems.Keywords
This publication has 29 references indexed in Scilit:
- Highly scalable appearance-only SLAM - FAB-MAP 2.0Published by Robotics: Science and Systems Foundation ,2009
- Fast and Incremental Method for Loop-Closure Detection Using Bags of Visual WordsIEEE Transactions on Robotics, 2008
- Map Matching and Data Association for Large-Scale Two-dimensional Laser Scan-based SLAMThe International Journal of Robotics Research, 2008
- FAB-MAP: Probabilistic Localization and Mapping in the Space of AppearanceThe International Journal of Robotics Research, 2008
- Accelerated appearance-only SLAMPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Toward a Unified Bayesian Approach to Hybrid Metric--Topological SLAMIEEE Transactions on Robotics, 2008
- Total Recall: Automatic Query Expansion with a Generative Feature Model for Object RetrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- SURF: Speeded Up Robust FeaturesLecture Notes in Computer Science, 2006
- The anatomy of a large-scale hypertextual Web search engineComputer Networks and ISDN Systems, 1998
- Approximating discrete probability distributions with dependence treesIEEE Transactions on Information Theory, 1968