J. Civera, Andrew Davison, J. Montiel
It has recently been demonstrated that the fundamental com-
puter vision problem of structure from motion with a single camera can
be tackled using the sequential, probabilistic methodology of monocu-
lar SLAM (Simultaneous Localisation and Mapping). A key part of this
approach is to use the priors available on camera motion and scene struc-
ture to aid robust real-time tracking and ultimately enable metric motion
and scene reconstruction. In particular, a scene ob ject of known size is
normally used to initialise tracking.
In this paper we show that real-time monocular SLAM can be initialised
with no prior knowledge of scene ob jects within the context of a powerful
new dimensionless understanding and parameterisation of the problem.
When a single camera moves through a scene with no extra sensing, the
scale of the whole motion and map is not observable, but we show that
up-to-scale quantities can be robustly estimated.
Further we describe how the monocular SLAM state vector can be par-
titioned into two parts: a dimensionless part, representing up-to-scale
scene and camera motion geometry, and an extra metric parameter rep-
resenting scale. The dimensionless parameterisation permits tuning of
the probabilistic SLAM filter in terms of image values, without any as-
sumptions about scene scale, but scale information can be put back into
the estimation if it becomes available.
Experimental results with real image sequences showing SLAM without
an initialisation ob ject, different image tuning examples and scenes with
the same underlying dimensionless geometry are presented.
pubs.doc.ic.ac.uk: built & maintained by Ashok Argent-Katwala.