FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance

@article{Cummins2008FABMAPPL,
  title={FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance},
  author={Mark Joseph Cummins and Paul Newman},
  journal={The International Journal of Robotics Research},
  year={2008},
  volume={27},
  pages={647 - 665}
}
  • M. Cummins, P. Newman
  • Published 1 June 2008
  • Computer Science
  • The International Journal of Robotics Research
This paper describes a probabilistic approach to the problem of recognizing places based on their appearance. The system we present is not limited to localization, but can determine that a new observation comes from a previously unseen place, and so augment its map. Effectively this is a SLAM system in the space of appearance. Our probabilistic approach allows us to explicitly account for perceptual aliasing in the environment—identical but indistinctive observations receive a low probability… 
Probabilistic localization and mapping in appearance space
TLDR
A new probabilistic approach to the problem of place recognition for mobile robots, called Fast Appearance Based Mapping or FAB-MAP, which incorporates correlations between visual features in a novel way, and achieves extreme efficiency, allowing it to apply to navigation problems on the largest scale.
FAB-MAP: Appearance-Based Place Recognition and Mapping using a Learned Visual Vocabulary Model
TLDR
It is demonstrated that place recognition performance can be improved by learning an approximation to the joint distribution over visual elements, and an efficient bail-out strategy for multi-hypothesis testing is defined to improve system speed.
Building beliefs: Unsupervised generation of observation likelihoods for probabilistic localization in changing environments
TLDR
A probabilistic localization system that generates an appropriate observation model online, unlike existing systems which require pre-determined belief models, and the dual-model system outperforms a single-model or pre-trained approach and state-of-the-art localization techniques.
Augmenting appearance-based localization and navigation using belief update
TLDR
The appearance-based localization approach provides a complete solution to the deployment of a robot in a relatively small environment, such as a house, or a work place, allowing the robot to robustly navigate the environment after minimal training.
Topological SLAM Using Fast Vision Techniques
TLDR
Experiments in an indoor environment show that the proposed technique is capable of dealing with perceptual aliasing using visual observations only and successfully performs topological SLAM.
Vision-based Markov localization across large perceptual changes
TLDR
This paper presents an approach to localize a mobile robot with a low frequency camera with respect to an image sequence, recorded previously within a different season, using a discrete Bayes filter and a sensor model based on whole image descriptors.
Visual topological SLAM and global localization
TLDR
This work proposes an extension of this work by integrating metrical information from robot odometry in the topological map, so as to obtain a globally consistent environment model.
Learning place-dependant features for long-term vision-based localisation
TLDR
This paper presents an alternative approach to the problem of outdoor, persistent visual localisation against a known map that leverages prior experiences of a place to learn place-dependent feature detectors, features that are unique to each place in the authors' map and used for localisation.
NOSeqSLAM: Not only Sequential SLAM
TLDR
This paper proposes a not only sequential approach to localization; specifically, instead of linearly searching for sequences, it constructs a directed acyclic graph and search for any kind of sequences and demonstrates that it outperforms the SeqSLAM approach.
...
...

References

SHOWING 1-10 OF 50 REFERENCES
Probabilistic Appearance Based Navigation and Loop Closing
  • M. Cummins, P. Newman
  • Computer Science
    Proceedings 2007 IEEE International Conference on Robotics and Automation
  • 2007
TLDR
A principled probabilistic framework for navigation using only appearance data, which is particularly suitable for online loop closure detection in mobile robotics.
Combining Visual and Spatial Appearance for Loop Closure Detection in SLAM
TLDR
This paper describes a system for use on a mobile robot that detects potential loop closures using both the visual and spatial appearance of the local scene using a principled and robust description of local spatial appearance using laser rangefinder data.
Vision-based global localization and mapping for mobile robots
TLDR
Experiments show that global localization can be achieved accurately using the scale-invariant landmarks, and the approach of pairwise submap alignment with backward correction in a consistent manner produces a better global 3-D map.
Detecting Loop Closure with Scene Sequences
  • K. Ho, P. Newman
  • Computer Science
    International Journal of Computer Vision
  • 2006
TLDR
An extension of the loop closing technique to a multi-robot mapping problem in which the outputs of several, uncoordinated and SLAM-enabled robots are fused without requiring inter-vehicle observations or a-priori frame alignment.
A probabilistic model for appearance-based robot localization
Probabilistic location recognition using reduced feature set
  • Fayin Li, J. Kosecka
  • Computer Science
    Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006.
  • 2006
TLDR
A two stage approach for localization in indoor environments where the environment is partitioned into several locations, each characterized by a set of scale-invariant keypoints and their associated descriptors, yielding a substantial speedup in recognition and capability of handling larger environments.
Mobile robot localization from learned landmarks
  • Robert Sim, G. Dudek
  • Computer Science
    Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190)
  • 1998
TLDR
This work presents an approach to vision-based mobile robot localization using a landmark tracking and interpolation method which obtains an estimate accurate to a fraction of the environment sampling density.
Appearance-based place recognition for topological localization
  • I. Ulrich, I. Nourbakhsh
  • Computer Science
    Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065)
  • 2000
TLDR
This paper presents a new appearance-based place recognition system for topological localization that uses a panoramic vision system to sense the environment and correctly classified between 87% and 98% of the input color images.
Localisation using an image-map
TLDR
A voting technique for a 3d structure and a run-time efficiency of kd-tree are improved to allow a quick finding of similar images and a quick localisation of a visual map using images from a typical digital camera.
Outdoor SLAM using visual appearance and laser ranging
  • P. Newman, Dave Cole, K. Ho
  • Computer Science
    Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006.
  • 2006
TLDR
A 3D SLAM system using information from an actuated laser scanner and camera installed on a mobile robot to detect loop closure events using a novel appearance-based retrieval system that is robust to repetitive visual structure and provides a probabilistic measure of confidence.
...
...