| | |
Summary: Independent 3D Motion Detection Based on
Depth Elimination in Normal Flow Fields
Antonis A. Argyrosy z Stelios C. Orphanoudakis y
yCVRL/ICS/FORTH zCVAP/NADA/KTH
POBox 1385 Heraklion, Crete, GR-711-10, Greece Stockholm, S-100 44, Sweden
E-mail: fargyros,orphanoug@ics.forth.gr E-mail: argyros@nada.kth.se
Abstract
This paper considers a specific problem of visual percep-
tion of motion, namely the problem of visual detection of
independent 3D motion. Most of the existing techniques for
solving this problem rely on restrictive assumptions about
the environment, the observer's motion, or both. Moreover,
they are based on the computation of optical flow, which
amounts to solving the ill-posed correspondence problem.
In this work, independent motion detection is formulated as
robust parameter estimation applied to the visual input ac-
quired by a binocular, rigidly moving observer. Depth and
motion measurements are combined in a linear model. The
parameters of this model are related to the parameters of
self-motion (egomotion) and the parameters of the stereo-
|
