Volume 27 Issue 6 - Publication Date: 1 June 2008
FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance
Mark Cummins and Paul Newman Mobile Robotics Group, University of Oxford, UK
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 of having come from the same place. We achieve this by learning a generative model of place appearance. By partitioning the learning problem into two parts, new place models can be learned online from only a single observation of a place. The algorithm complexity is linear in the number of places in the map, and is particularly suitable for online loop closure detection in mobile robotics.
Multimedia Key
= Video = Data = Code = Image
Example 1: Results for the New College Dataset. (48.2 MB) avi
Example 2: Results for the City Centre Dataset. (35.1 MB) avi
Example 3: Images, GPS coordinates and ground truth labels. (9 KB) htm
Example 4: Generalization Performance – Indoor Dataset A. (7.26 MB) avi
Example 5: Generalization Performance – Indoor Dataset B. (3.16 MB) avi
Return to Contents