author = {Tom Botterill and Steven Mills and Richard Green},
title = {Bag-of-Words-driven Single Camera Simultaneous Localisation and Mapping},
journal = {Journal of Field Robotics},
year = {2011},
volume = {28},
abstract={This paper describes BoWSLAM, a scheme for a robot to reliably navigate and map a priori
unknown environments, in real-time, using monocular vision alone. BoWSLAM can navigate challenging
dynamic and self-similar environments, and can recover from gross errors. Key innovations
allowing this include new uses for the Bag-of-Words image representation; this is used to select the
best set of frames to reconstruct positions from; and to give efficient wide-baseline correspondences
between many pairs of frames, providing multiple position hypotheses. A graph-based representation
of these position hypotheses enables the modeling and optimisation of errors in scale in a dual graph,
and the selection of only reliable position estimates in the presence of gross outliers. BoWSLAM is
demonstrated mapping a 25 minute 2.5km trajectory through a challenging and dynamic outdoor
environment without any other sensor input; considerably further than previous single camera SLAM