Copy Link
Add to Bookmark
Report
VISION-LIST Digest 1988 08 22
Vision-List Digest Mon Aug 22 15:14:45 PDT 1988
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Thesis on computer vision wanted.
Autonomous Land Vehicle Research, U. of Bristol, UK
Neural Computation
Camera stabilization
Re: request for image processing software and source for workstations
Character recognition references
----------------------------------------------------------------------
Date: 9 Aug 88 13:25:37 GMT
From: Mike Green <mcvax!cs.kl.ac.uk!mike@uunet.UU.NET>
Subject: Thesis on computer vision wanted.
Keywords: Please Help
Organization: U. of Keele, Staffs. U.K.
I have a reference to a thesis :-
A Representation for Visual Information
by J.L. Crowley.
1981 Carnegie-Mellon University.
Could anyone who knows where I can get hold of a copy, in any
format, of this thesis please e-mail me.
Thanks,
Mike Green, Computer Science, Keele University, Staffordshire, UK.
JANET: mike@uk.ac.kl.cs
BITNET: mike%uk.ac.kl.cs@uk.ac
ARPANET: mike%uk.ac.kl.cs@nss.cs.ucl.ac.uk
(last resort :-() UUCP: mcvax!ukc!kl-cs!mike
------------------------------
Date: Wed, 10 Aug 88 09:22:43 +0100
Subject: Autonomous Land Vehicle Research, U. of Bristol, UK
From: Phill Everson <everson%COMPSCI.BRISTOL.AC.UK@CUNYVM.CUNY.EDU>
I have been asked by a couple of people to give a summary of the
Autonomous Land Vehicle research going on here at the University of
Bristol, UK. The following are the abstracts of 3 papers to be
presented at the AVC88 conference in, I think, Manchester (UK), next
month. The work is mostly done on transputers with some development
work on Sun workstations. My involvement was primarily whilst an
undergraduate - I am now working in Medical Image Processing.
Phill Everson
University of Bristol, UK
;;;;;;;;;;;
Feature Extraction for Vision Guided Road Vehicles
BT Thomas, EL Dagless, RA Lotufo, DJ Milford, AD Morgan, JF Morrissey
This paper reports the early results of an investigation conducted at
the University of Bristol into autonomous road vehicle control. The
emphasis of the work is on real-time vision, with the objective of
steering a vehicle on well-defined roads at speeds up to 60 km/hr.
This report gives an overview of the computer hardware and the
low-level vision algorithms currently being explored. Our algorithms
fall into two categories: bootstrap and real-time analysis. For the
bootstrap mode we present a basic edge-detection and surface
segmentation approach and an alternative method based on texture
analysis. Our current emphasis is on real-time analysis techniques.
Her we present only single straightforward real-time algorithm, more
complex approaches being given in companion papers.
;;;;;;;;;;;;;;;
Road Edge Extraction Using a Plan-View Image Transformation
RA Lotufo, EL Dagless, DJ Milford, BT Thomas
A new technique to extract road edges in the road-following algorithm
for autonomous road vehicle navigation is described. It is based on
finding road edges on a subsampled plan-view of a portion of the road
ahead of the vehicle. The method is illustrated in the real-time
identification ofroad edges using a fast vertical edge detector and
link operator applied to the transformed plan view. Location of both
road edges at 20 frames per second is demonstrated.
;;;;;;;;;;;;;;;;;
Road Edge Tracking For Robot Following
AD Morgan, EL Dagless, DJ Milford, BT Thomas
The problem of navigating a robot along a road is approached by means
of creating and updating a simple representation of the road from a
sequence of images. The representation chosen is a 4-parameter model
that describes the width, direction and simple curvature of the road in
a vehicle centred (X,Y,Z) world coordinate system. The model is
created from tracking along major edge features in an image and
applying constraints to select road edge candidates. Updating consists
of tracking a set of measured edge points from frame to frame (assuming
that vehicle motion is known) and using a weighted least squares
process to find the 4 parameters of the road model. A number of
constraint and filtering processes representing knowledge of how a
vehicle moves on a road have been applied.
------------------------------
Date: Thu, 11 Aug 88 17:41:04 edt
From: terry@cs.jhu.edu (Terry Sejnowski <terry@crabcake.cs.JHU.EDU>)
Subject: Neural Computation
Announcement and
Call for Papers
NEURAL COMPUTATION
First Issue: Spring 1989
Editor-in-Chief
Terrence Sejnowski
The Salk Institute and
The University of California at San Diego
Neural Computation will provide a unique interdisciplinary forum
for the dissemination of important research results and for
reviews of research areas in neural computation.
Neural computation is a rapidly growing field that is attracting
researchers in neuroscience, psychology, physics, mathematics,
electrical engineering, computer science, and artificial
intelligence. Researchers within these disciplines address,
from special perspectives, the twin scientific and engineering
challenges of understanding the brain and building computers.
The journal serves to bring together work from various
application areas, highlighting common problems and techniques
in modeling the brain and in the design and construction of
neurally-inspired information processing systems.
By publishing timely short communications and research reviews,
Neural Computation will allow researchers easy access to
information on important advances and will provide a valuable
overview of the broad range of work contributing to neural
computation. The journal will not accept long research
articles.
The fields covered include neuroscience, computer science,
artificial intelligence, mathematics, physics, psychology,
linguistics, adaptive systems, vision, speech, robotics, optical
computing, and VLSI.
Neural Computation is published quarterly by The MIT Press.
Board of Editors
Editor-in-Chief: Terrence Sejnowski, The Salk Institute and
The University of California at San Diego
Advisory Board:
Shun-ichi Amari, University of Tokyo, Japan
Michael Arbib, University of Southern California
Jean-Pierre Changeux, Institut Pasteur, France
Leon Cooper, Brown University
Jack Cowan, University of Chicago
Jerome Feldman, University of Rochester
Teuovo Kohonen, University of Helsinki, Finland
Carver Mead, California Institute of Technology
Tomaso Poggio, Massachusetts Institute of Technology
Wilfrid Rall, National Institutes of Health
Werner Reichardt, Max-Planck-Institut fur Biologische Kybernetik
David A. Robinson, Johns Hopkins University
David Rumelhart, Stanford University
Bernard Widrow, Stanford University
Action Editors:
Joshua Alspector, Bell Communications Research
Richard Andersen, MIT
James Anderson, Brown University
Dana Ballard, University of Rochester
Harry Barrow, University of Sussex
Andrew Barto, University of Massachusetts
Gail Carpenter, Northeastern University
Gary Dell, University of Rochester
Gerard Dreyfus, Paris, France
Jeffrey Elman, University of California at San Diego
Nabil Farhat, University of Pennsylvania
Francois Fogelman-Soulie, Paris, France
Peter Getting, University of Iowa
Ellen Hildreth, Massachusetts Institute of Technology
Geoffrey Hinton, University of Toronto, Canada
Bernardo Huberman, Xerox, Palo Alto
Lawrence Jackel, AT&T Bell Laboratories
Scott Kirkpatrick, IBM Yorktown Heights
Christof Koch, California Institute of Technology
Richard Lippmann, Lincoln Laboratories
Stephen Lisberger, University of California San Francisco
James McClelland, Carnegie-Mellon University
Graeme Mitchison, Cambridge University, England
David Mumford, Harvard University
Erkki Oja, Kuopio, Finland
Andras Pellionisz, New York University
Demetri Psaltis, California Institute of Technology
Idan Segev, The Hebrew University
Gordon Shepherd, Yale University
Vincent Torre, Universita di Genova, Italy
David Touretzky, Carnegie-Mellon University
Roger Traub, IBM Yorktown Heights
Les Valiant, Harvard University
Christoph von der Malsburg, University of Southern California
David Willshaw, Edinburgh, Scotland
John Wyatt, Massachusetts Institute of Technology
Steven Zucker, McGill University, Canada
Instructions to Authors
The journal will consider short communications, having no more
than 2000 words of text, 4 figures, and 10 citations; and area
reviews which summarize significant advances in a broad area of
research, with up to 5000 words of text, 8 figures, and 100
citations. The journal will accept one-page summaries for
proposed reviews to be considered for solicitation.
All papers should be submitted to the editor-in-chief. Authors
may recommend one or more of the action editors. Accepted
papers will appear with the name of the action aditor that
communicated the paper.
Before January 1, 1989, please address submissions to:
Dr. Terrence Sejnowski
Biophysics Department
Johns Hopkins University
Baltimore, MD 21218
After January 1, 1989, please address submissions to:
Dr. Terrence Sejnowski
The Salk Institute
P.O. Box 85800
San Diego, CA 92138
Subscription Information
Neural Computation
Annual subscription price (four issues):
$90.00 institution
$45.00 individual
(add $9.00 surface mail or $17.00 airmail postage
outside U.S. and Canada)
Available from:
MIT Press Journals
55 Hayward Street
Cambridge, MA 02142
USA
617-253-2889
------------------------------
Date: 12 Aug 1988 16:20:52-GMT-0:00
From: Farzin Deravi <eederavi%PYRAMID.SWANSEA.AC.UK@cunyvm.cuny.edu>
Subject: Camera stabilization
I am looking for information on camera stabilization and sensors for
this purpose suitable for moving vehicles. In particular
could you please answer the following questions:
1) What is the Steadicam Gyro? How can I find one?? How does it work???
2) What is Sorbothane shock mounting?
3) What are accelerometers and rate gyros? Any suppliers??
Any other related information would be grately appreciated.
Farzin Deravi, | UUCP : ...!ukc!pyr.swan.ac.uk!eederavi|
Image Processing Laboratory, | JANET : eederavi@uk.ac.swan.pyr |
Electrical Engineering Dept., | voice : +44 792 295583 |
University of Wales, | Fax : +44 792 295532 |
Swansea, SA2 8PP, U.K. | Telex : 48358 |
[ 1) The Steadicam is an apparatus worn on the shoulders and in front
which provides inertial (passive) camera stabilization. It has been
used extensively by the film industry. They cost quite a bit of
money (they're usually rented), and the operator requires fairly
involved training. The parameters of stabilization is not provided
as is (since it is passive).
2) Don't know.
3) Accelerometers provide measures the acceleration of a moving body.
Accelerometers, rate gyros, tachometers, north seekers, and complete
stabilization systems are available from Humphrey Inc. (619) 565-6631
(USA). Fraser-Volpe Corp. also has an inertial, mirror based lens
to better stabilize the image from a moving camera (215)443-5240
(USA).
phil... ]
------------------------------
Date: Sat, 6 Aug 88 15:21:53 EDT
From: msl@vml3.psych.nyu.edu (Michael Landy)
Subject: Re: request for image processing software and source for workstations
In response to Patrick C. Beard's request for image processing software for
workstations which includes source code:
I distribute a general UNIX-based software system for image processing that
I co-wrote. It is quite general and extensive, and has been described in
articles in Computer Vision, Graphics, and Image Processing, and in
Behavior Research Methods, Instrumentation, and Computers (both of these
articles were published in 1984). It is a commercial
product, with discounting for educational, non-profit, and US government
institutions. It is general UNIX software, and is not optimized for a
particular workstation. It is currently used on Vaxen, uVaxen, Suns,
Masscomps, Apollos, IBM AT's, and a number of other machines running Unix.
If this is of interest to you, let me know.
Michael Landy
(212) 998-7857
landy@nyu.nyu.edu
SharpImage Software
P.O. Box 373, Prince Street Station
New York, NY 10012
------------------------------
Date: Tue, 16 Aug 88 09:03:46 EDT
From: oltz@tcgould.tn.cornell.edu (Michael Oltz)
Subject: Character recognition references
Some time ago, I requested references on algorithms for character
recognition. Several people sent responses, but I delayed summarizing
because I couldn't remember in which newsgroups I had originally asked.
So, I'll just guess. Thanks to all who responded.
>From: skahan@june.cs.washington.edu (Simon Kahan)
You might look at
"On the Recognition of Printed Characters of Any Font and Size"
in IEEE PAMI Volume 9, no. 2, March 87.
It covers specifically typeset fonts, and gives results from testing
on fonts that are different from the training fonts.
>From: Dr. Todd Kushner <kushner@cvl.umd.edu>
I like the text by H. S. Hou, ``Digital Document Processing,'' Wiley-
Interscience, New York, 1983 (chapter 6). A classic reference he
mentions is M. K. Hu, ``Visual Pattern Recognition by Moment Invariants,''
IRE Transactions on Information Theory, IT-8(1), pp. 179-187 (1962).
>From: webber@aramis.rutgers.edu (Bob Webber)
if you look at the ieee computer society publications catalog, you
will find a tutorial on character recognition (ieee tutorials are
really collections of papers that the editors think are ``fundamental'').
it is probably the best place to start.
>From: mcvax!crin.crin.fr!tombre@uunet.UU.NET (Karl Tombre)
Organization: CRIN - INRIA Lorraine, Nancy, France
Here are some references... Look especially at the publications of Baird et
al. from Bell Labs; they do very interesting work on omnifont character
recognition.
This is just a quick lookup in the bibliography file of our research group.
Not exhaustive at all. I only included references in english ; we also have
things in french...
The keywords are in french...
%A R.G. Casey
%A C.R. Jih
%T A Processor-Based OCR System
%D 1983
%J IBM Journal of Research and Development
%V 27
%N 4
%P 386-399
%K caracteres - reconnaissance - OCR - classification - arbre - decision - bayesien - separation
%A S. Kahan
%A T. Pavlidis
%A H. S. Baird
%T On the Recognition of Printed Characters of Any Font and Size
%D 1987
%J IEEE Transactions on PAMI
%V 9
%N 2
%P 274-288
%K caracteres - multipolice - LAG - reconnaissance - contextuel - spell
%A H.S. Baird
%A S. Kahan
%A Th. Pavlidis
%T Components of a Omnifont Page Reader
%D 1986
%J Proceedings of Eighth International Conference on Pattern Recognition
%P 344-348
%C Paris
%K caractere segmentation police
%A S.W. Lam
%A H.S. Baird
%T Performance Testing of Mixed-font Variable-size Character Recognizers
%D 1987
%J Proc. of Fifth Scandinavian Conference on Image Analysis
%P 563-570
%C Stockholm
%K caracteres - evaluation - test - estimation - performances
%A J. Mantas
%T An overview of character recognition methodolgies
%D 1986
%J Pattern recognition
%E Pergamon journals
%I Pattern recognition society
%V 19
%N 6
%P 425-430
%K caracteres manuscrits reconnaissance on-line script
%A M. Nadler
%T Survey of Document Segmentation and Coding Techniques
%D 1984
%J Computer Vision, Graphics and Image Processing
%V 28
%P 240-262
%K document - segmentation - codage - graphique - caractere - texte
%A J. SCHURMANN
%T A multifont word recognition system for postal adress reading
%D 1978
%J IEEE Transactions on computers
%E IEEE
%I IEEE
%V c-27
%N 8
%P 721-732
%K caracteres contexte classification polynomiale adresses postales
--
PLEASE IGNORE network address in header. Use the following:
Mike Oltz oltz@vax5.ccs.cornell.UUCP (607)255-8312
Interactive Media Center, Cornell Computer Services
215 Computing and Communications Center Ithaca NY 14853
------------------------------
End of VISION-LIST
********************
