Title:
Atlanta World: An Expectation Maximization Framework for Simultaneous Low-level Edge Grouping and Camera Calibration in Complex Man-made Environments
Atlanta World: An Expectation Maximization Framework for Simultaneous Low-level Edge Grouping and Camera Calibration in Complex Man-made Environments
Author(s)
Schindler, Grant
Dellaert, Frank
Dellaert, Frank
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
Edges in man-made environments, grouped according to
vanishing point directions, provide single-view constraints
that have been exploited before as a precursor to both scene
understanding and camera calibration. A Bayesian approach
to edge grouping was proposed in the Manhattan
World paper by Coughlan and Yuille, where they assume
the existence of three mutually orthogonal vanishing directions
in the scene. We extend the thread of work spawned
by Coughlan and Yuille in several signi cant ways. We propose
to use the expectation maximization (EM) algorithm
to perform the search over all continuous parameters that
in uence the location of the vanishing points in a scene.
Because EM behaves well in high-dimensional spaces, our
method can optimize over many more parameters than the
exhaustive and stochastic algorithms used previously for
this task. Among other things, this lets us optimize over
multiple groups of orthogonal vanishing directions, each of
which induces one additional degree of freedom. EM is also
well suited to recursive estimation of the kind needed for image
sequences and/or in mobile robotics. We present experimental
results on images of Atlanta worlds, complex urban
scenes with multiple orthogonal edge-groups, that validate
our approach. We also show results for continuous
relative orientation estimation on a mobile robot.
Sponsor
Date Issued
2004-06
Extent
Resource Type
Text
Resource Subtype
Post-print
Proceedings
Proceedings