L. Clemente, Andrew Davison, Ian Reid, J. Neira, J. Tardos
This paper presents a method for Simultaneous
Localization and Mapping (SLAM) relying on a monocular
camera as the only sensor which is able to build outdoor, closed-
loop maps much larger than previously achieved with such
input. Our system, based on the Hierarchical Map approach ,
builds independent local maps in real-time using the EKF-SLAM
technique and the inverse depth representation proposed in .
The main novelty in the local mapping process is the use of a
data association technique that greatly improves its robustness in
dynamic and complex environments. A new visual map matching
algorithm stitches these maps together and is able to detect
large loops automatically, taking into account the inobservability
of scale intrinsic to pure monocular SLAM. The loop closing
constraint is applied at the upper level of the Hierarchical Map
in near real-time.
We present experimental results demonstrating monocular
SLAM as a human carries a camera over long walked trajectories
in outdoor areas with people and other clutter, even in the more
difficult case of forward-looking camera, and show the closing of
loops of several hundred meters.
pubs.doc.ic.ac.uk: built & maintained by Ashok Argent-Katwala.