Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

An IntensityBased Method for the 3D Motion and Structure Estimation

Summary: An Intensity­Based Method
for the 3­D Motion and Structure Estimation
from Binocular Image Sequences
A. Luo and H. Burkhardt
Technische Informatik I der TU Hamburg­Harburg
Postfach 90 10 52, 21071 Hamburg 90, Germany
email: luo@tu­harburg.d400.de or burkhardt@tu­harburg.d400.de
This paper presents a new algorithm for estimating the 3­D motion and structure
from stereo image sequences. In order to overcome the inherent ambiguities of the
motion and structure estimation from a monocular image sequence and to improve
the performance of the binocular stereo methods, both the intensity­based methods
are directly integrated. Being different from other methods computing the structure
from stereo and motion, this method does not need to match separate monocular
optical flows, so that the high complexity of the algorithm is avoided. Instead of
simplified models that are often unreasonable, new models for 3­D piecewise smooth
structure and occlusion are put forward for Bayesian estimation. The experiments
show that the algorithm is effective and robust to improve the 3­D motion and
structure estimation.
Keywords: shape from motion, stereo and integration, motion estimation, piece­


Source: Albert-Ludwigs-Universität Freiburg, Institut für Informatik,, Lehrstuhls für Mustererkennung und Bildverarbeitung


Collections: Computer Technologies and Information Sciences