The Wavelet Digest Homepage
Return to the homepage
Search the complete Wavelet Digest database
Help about the Wavelet Digest mailing list
About the Wavelet Digest
The Digest The Community
 Latest Issue  Back Issues  Events  Gallery
The Wavelet Digest
   -> Volume 2, Issue 12


PhD Thesis available, Distributed Representation and Analysis
 
images/spacer.gifimages/spacer.gif Reply into Digest
Previous :: Next  
Author Message
Eero Simoncelli, GRASP Laboratory, Philadelphia.
Guest





PostPosted: Fri Nov 29, 2002 3:34 pm    
Subject: PhD Thesis available, Distributed Representation and Analysis
Reply with quote

PhD Thesis available, Distributed Representation and Analysis
of Visual Motion

PhD Thesis available:

Author: Eero Simoncelli
Advisor: Edward Adelson
Title: Distributed Representation and Analysis of Visual Motion
Institution: Massachusetts Institute of Technology
Department: Electrical Engineering and Computer Science

Requests for copies of this thesis should be sent (via electronic
or U.S. mail) to:

eero@central.cis.upenn.edu

Dr. Eero Simoncelli
GRASP Laboratory, 335C
3401 Walnut Street
Philadelphia, PA 19104-6228

Abstract:
This thesis describes some new approaches to the representation and
analysis of visual motion, as perceived by a biological or machine
visual system. We begin by discussing the computation of image motion
fields, the projection of motion in the three-dimensional world onto
the two-dimensional image plane. This computation is notoriously
difficult, and there are a wide variety of approaches that have been
developed for use in image processing, machine vision, and biological
modeling. We show that a large number of the basic techniques are
quite similar in nature, differing primarily in conceptual motivation,
and that they each fail to handle a set of situations that occur
commonly in natural scenery.

The central theme of the thesis is that the failure of these
algorithms is due primarily to the use of vector fields as a {em
representation} for visual motion. We argue that the translational
vector field representation is inherently impoverished and
error-prone. Furthermore, there is evidence that a direct optical
flow representation scheme is not used by biological systems for
motion analysis. Instead, we advocate {em distributed}
representations of motion, in which the encoding of image plane
velocity is implicit.

As a simple example of this idea, and in consideration of the errors
in the flow vectors, we re-cast the traditional optical flow problem
as a probabilistic one, modeling the measurement and constraint errors
as random variables. The resulting framework produces {em
probability distributions} of optical flow, allowing proper handling
of the uncertainties inherent in the optical flow computation, and
facilitating the combination with information from other sources. We
demonstrate the advantages of this probabilistic approach on a set of
examples. In order to overcome the temporal aliasing commonly found
in time-sampled imagery (eg, video), we develop a probabilistic
``coarse-to-fine" algorithm that functions much like a Kalman filter
over scale. We implement an efficient version of this algorithm and
show its success in computing Gaussian distributions of optical flow
for both synthetic and real image sequences.

We then extend the notion of distributed representation to a
generalized framework that is capable of representing multiple motions
at a point. We develop an example representation through a series of
modifications of the differential approach to optical flow estimation.
We show that this example is capable of representing multiple motions
at a single image location and we demonstrate its use near occlusion
boundaries and on simple synthetic examples containing transparent
objects.

Finally, we show that these distributed representation are effective
as models for biological motion representation. We show qualitative
comparisons of stages of the algorithm with neurons found in mammalian
visual systems, suggesting experiments to test the validity of the
model. We demonstrate that such a model can account quantitatively
for a set of psychophysical data on the perception of moving
sinusoidal plaid patterns.

Thesis Submission Date: January, 1993.
All times are GMT + 1 Hour
Page 1 of 1

 
Jump to: 
 


disclaimer - webmaster@wavelet.org
Powered by phpBB

This page was created in 0.027194 seconds : 18 queries executed : GZIP compression disabled