Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 11 Issue 12
VISION-LIST Digest Thu Apr 02 13:04:13 PDT 92 Volume 11 : Issue 12
- Send submissions to Vision-List@ADS.COM
- Vision List Digest available via COMP.AI.VISION newsgroup
- If you don't have access to COMP.AI.VISION, request list
membership to Vision-List-Request@ADS.COM
- Access Vision List Archives via anonymous ftp to FTP.ADS.COM
Today's Topics:
Find a shape template inside an image
Astron. images (HST, other) by anon. ftp
Analogic SCSI Frame Grabber DASM-FGM
Want info about camera calibration
Re: CIE to RGB routines
IEEE T-PAMI Old Issues Wanted !!
Duda and Hart Text
Post-doctoral research position
SPIE Conference Call
CFP: Workshop on 2D & 3D Spatial Data
Advance Information - ECAI92 (long)
SPECIAL OFFER (long)
Post-Doc position wanted (long)
----------------------------------------------------------------------
Date: Thu, 2 Apr 92 16:34:41 EDT
From: ronse@geocub.greco-prog.fr (Christian RONSE)
Subject: find a shape template inside an image
A student of mine is considering the following problem. You have a
given shape template, and a picture. Find the shape inside the
picture; it may have been subjected to a translation and a rotation,
and perhaps even a bilateral symmetry on top of it.
The relative difficulty comes from the fact that you combine rotations
and translations. With translations alone, this is a classical
template matching problem that has been solved by morphological
operations (erosion, hit-or-miss transformation).
I think this has been done before (maybe in computational geometry and
robotics), but I can't remember any references. Could anyone supply me
with some bibliographical data? Thanks.
Christian Ronse ronse@geocub.greco-prog.fr
Tel. (33) 56.84.69.33
LaBRI Fax. (33) 56.84.66.69
Universite Bordeaux-I
351 cours de la Liberation
33405 TALENCE
FRANCE
------------------------------
Date: Wed, 25 Mar 92 09:44:41 +0100
From: fmurtagh@eso.org
Subject: Astron. images (HST, other) by anon. ftp
IMAGE RESTORATION OF HUBBLE SPACE TELESCOPE IMAGES
Some test cases have been put in the ST-ECF anonymous ftp account (address:
ns3.hq.eso.org, 134.171.11.4; cd to pub/testimages). At the moment there
are images, point spread functions, and restorations of Jupiter's moon Io,
and of Supernova 1987a.
It is not implied that the restored images are the best that one can do. The
intention is to provide images as examples, to facilitate assessment of
alternative restoration procedures.
The HST images are in subdirectories under
pub/testimages/testimages-HST-restoration
The images are in FITS format.
A number of ground-based images are available in
pub/testimages/testimages-DAW1989
These cover a range of objects (globular clusters, faint galaxy fields,
other extended objects). These images were used for comparative assessment of
photometry software. Discussion and results may be found in the proceedings
of the ESO/ST-ECF Data Analysis Workshop 1989, published in the European
Southern Obs. Conf. & Workshop Proc. series. Color reproductions of these
images were also published in these proceedings. These 15 images are in FITS
format, and additionally there is a compressed tar file containing all images.
Some tabular results, which go with contributions in the proceedings, are also
available in subdirectories.
Fionn Murtagh
ST-ECF, Garching/Munich
fmurtagh@eso.org
------------------------------
From: Shmuel Peleg <peleg@shum.huji.ac.il>
Date: Thu, 26 Mar 92 16:31:53 +0200
Subject: Analogic SCSI Frame Grabber DASM-FGM
We have just received a SCSI Frame Grabber by Analogic (DASM-FGM).
Does anyone have any software to interface with this device? All help
is greatly appreciated.
Shmuel Peleg
peleg@cs.huji.ac.il
------------------------------
Date: Wed, 25 Mar 92 17:42:06 -0600
From: vlakshmi@ho06.eng.ua.edu (Venkatraman Lakshminarayanan)
Subject: Want info about camera calibration
Dear Netters,
I am looking for some info about camera calibration.
All I have is a pair of stereo images and I need to obtain the camera
parameters from them.Ofcourse, I am using a cross-correlation
technique to locate corresponding points in the images and am so far
successful at finding them. Thus, I have corresponding image points in
the left and right images ( and hence the disparities ) and from these
,if I can find out camera parameters , I can calculate the real depth
of the object( scene ) points. I know that a paper by D.Gennery in
1979 Image Understanding Workshop deals with this stuff. I have put
the article on Inter Library Loan , but that doesn't seem to work.
So, I will really appreciate if anyone could get me any
suggestions/tips about the same.
Thanks in advance.
sincerely,
Venkatraman Lakshminarayanan ** phone : (205) - 349 - 2701
EE, University of Alabama ** email : vlakshmi@ho12.eng.ua.edu
------------------------------
Date: 31 Mar 92 17:14:58 GMT
From: trejo@kahuna.navy.mil (Len Trejo)
Organization: "Navy Personnel R & D Center"
Subject: Re: CIE to RGB routines
In article <9203240500.AA08296@euler.ads.com>, Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) writes:
|> Date: Thu, 12 Mar 92 14:18:26 CST
|> From: braker@shadow.brooks.af.mil (Jim Brakefield MSEE)
|> Subject: CIE to RGB routines
|>
|> I'm trying to implement CIE to RGB conversion. I have typed in the
|> implied math from pg. 348-350 of Fundamentals of Three-Dimensional
|> Graphics by Alan Watt, Addison-Wesley 1989. It doesn't quite work
|> (its off by some scaling factor). Is there any Fortran, C or Pascal
|> code out there that does this. Input is CIE x y & Y of the red, green
|> and blue phosphours. Output desired is a matrix that takes a given
|> X Y & Z and converts it to RGB brightness levels.
A few years ago, I wrote some transformation routines in C for work in
generating stimuli for psychology experiments on color CRTs. I did write
one program to convert CIE x,y,Y to RGB tristimulus values. I'm not sure
this is what Jim wants, but I'll send it in anyway. Of course, no warranty
of any kind is implied. This program was for my use only and hasn't been
rigorously tested. Mapcie also prints the r,b,L values for the Boynton-
Macleod chromaticity diagram, in fact, that's what I really wrote it for;
the RGB output is just an added feature. Another program, Maprb, takes
the output r,b,L values from mapcie and maps them into the rgb luminance
values of a color CRT, based on an interpolation from a lookup table of
measured luminances for each phosphor gamma function. It assumes gun
independence. Anyway, here's the code. Hope it's of some value; but
I can't support it if there are problems.
[ I removed the code for brevity. Please email a request for this code
to trejo@kahuna.navy.mil . phil... ]
USENET : trejo@nprdc.navy.mil UUCP: ucsd!nprdc!trejo
U.S. Mail: Leonard J. Trejo, Ph. D. Phone: (619) 553-7711
Neurosciences Division (AV) 553-7711
NPRDC, Code 141
San Diego, CA 92152-6800
(The opinions expressed here are my own, are unofficial, and do not
necessarily reflect the views of the Navy Department.)
------------------------------
Date: Thu, 26 Mar 92 13:38:33 -0500
From: minzhi@eniac.seas.upenn.edu (Min-Zhi Shao)
Subject: IEEE T-PAMI Old Issues Wanted !!
Hello,
Could anyone tell me where I can get *discounted* old issues of
IEEE Transactions on Pattern Analysis and Machine Intelligence?
Many Thanks!
Min-Zhi Shao
minzhi@graphics.cis.upenn.edu
------------------------------
Date: Thu, 02 Apr 92 14:35:08 GMT
From: kfieldin@smaug (Kenneth H. Fielding)
Organization: Air Force Institute of Technology
Subject: Duda and Hart Text
I am looking for copies of the Book "Pattern classification and
Scene Analysis".
If you have the book and would like to sell it please contact me at
kfieldin@galaxy.afit.af.mil
------------------------------
Date: Wed, 1 Apr 1992 13:54:59 GMT
From: bergevin@bersimis.gel.ulaval.ca (Robert Bergevin)
Organization: Universite Laval, Ste-Foy, Quebec (Canada)
Subject: Post-doctoral research position
Post-doctoral Research Position
Computer Vision and Digital Systems Laboratory
Department of Electrical Engineering
Laval University
Quebec, Canada
A post-doctoral position in computer vision is presently available at
the Computer Vision and Digital Systems Laboratory, Laval University,
Quebec (Canada). Candidates in all domains of computer vision are
invited to apply. Experience with 3D range image processing and
analysis would be a definitive asset. Interests in parallel and
distributed architectures and systems is also desirable.
The candidate will participate in the research activities of the
Laboratory; more specifically those related to our membership in the
Institute for Robotics and Intelligent Systems (IRIS), a major
constituent of the Networks of Centres of Excellence Program of the
Government of Canada.
The Computer Vision and Digital Systems Laboratory is a rapidly
growing research group with more than 40 active graduate students, 7
professors, and support staff. The group is involved in a large number
of national research projects and keeps strong links with other
academic, industrial and governmental laboratories. Research
facilities include a large network of up-to-date Unix (Sun)
workstations, Silicon Graphics, Convex, Maspar MP-1102, Volvox
(transputer-based) computers, as well as intensity, range, and
infrared imaging laboratories and a robotic workcell. Active
collaboration is well established locally with the mechanical
engineering (robotics) and computer science (knowledge-based vision)
departments.
Informal enquiries may be made to Dr. Denis Poussart by e-mail
(poussart@gel.ulaval.ca) or phone (418 656-3554). Applications should
include a resume and the names of two referees and should be sent to
Dr. Denis Poussart, Department of Electrical Engineering, Laval
University, Ste-Foy (Quebec), Canada, G1K 7P4. A one year position is
offered, renewable for a second year upon agreement of both parties.
The starting date is on or after May 1, 1992.
Robert Bergevin phone: (418) 656-2131 x4848
Computer Vision and Digital Systems Laboratory fax: (418) 656-3594
Electrical Engineering Department e-mail: bergevin@gel.ulaval.ca
------------------------------
Date: Fri, 27 Mar 92 17:15:18 PST
From: schenker@telerobotics.jpl.nasa.gov (Paul Schenker)
Subject: SPIE Conference Call
Call for Papers:
SPIE OE/TECHNOLOGY '92
15-20 November 1992
Boston, Massachusetts
SENSOR FUSION V
Conference Chair: Paul S. Schenker, Jet Propulsion Lab.
PROGRAM COMMITTEE:
Mongi A. Abidi, Univ. of Tennessee/Knoxville
Terrance E. Boult, Columbia Univ.
Theodore J. Broida, Hughes Aircraft Co.
Gregory D. Hager, Yale Univ.
Terrance L. Huntsberger, Univ. of South Carolina
Daryl T. Lawton, Georgia Institute of Technology
Ren C. Luo, North Carolina State Univ.
Gerard T. McKee, Univ. of Reading (UK)
David P. Miller, Jet Propulsion Lab.
Bobby S. Y. Rao, UC Berkeley
Michael Seibert, MIT/Lincoln Lab.
Charles V. Stewart, Rennselaer Polytechnic Institute
Stelios C. A. Thomopoulos, Pennsylvania State Univ.
Sensor fusion addresses the problem of robustly integrating data taken
from multiple, redundant information sources. For example, the data of
interest might be visual in form, and acquired over multiple/stereo
views, successive time intervals, multiple resolutions, or different
spectral bands. Computer techniques for fusing such data are a logical
extension of machine vision; and, associated problems in multi-camera
calibration, 3-D shape recovery, and 3-D object recognition have all
been common paper topics in past years. From a biological perspective,
developing detailed computational models for visual data fusion can
provide important insights to human psychological performance and
neurophysiological architecture. This also has been a major theme in
our conference.
Vision, combined with force, tactility, and kinesthesia, comprise the
basic multi-sensory elements of the human perception-action loop. In
this regard, vision is an "active" information source, capable of
being directed and focused to the needs of the task at hand. Modeling
this sensory-motor behavior, as with the study of computational vision
noted above, is important to understanding human performance/factors.
Similarly, real-time computer implementation of models is a basis for
multi-sensory perception in robots. Thus, another strong interest area
for conference participants has been improved robotic sensing, with
the goal of broadening the 3-D visual object recognition paradigm to
integrate positional and force data acquired from robot manipulators.
Other data sources include active ranging and proximity sensing, based
on structured light, laser, acoustic and/or other modes. Topics of
interest in the robotics area include both "automated" and
"man-in-loop" applications, for example: remote sensing, target
detection-tracking-and-recognition, computer- assisted
telemanipulation and navigation, 3-D geometric database visualization,
and virtual reality/multi-media interfaces. Recent meetings also
incorporated topics on distributed detection & decision, as applies to
such problems as modeling data fusion in spatially dispersed sensor
arrays, decision-making in human organizations, and
command-control-communication within distributed information networks.
One of the most enjoyable aspects of the Sensor Fusion conference is
its technical breadth. Speakers of past years include workers from
applied mathematics, artificial intelligence, computer science,
engineering, psychology, neuroscience, and theoretical biology. We
continue to foster this diversity, and indeed, papers that contrast
and compare approaches to sensor fusion being developed within these
multiple disciplines, and/or synthesize fresh theoretical viewpoints
across disciplines, are encouraged.
In summary, we invite papers in the interdisciplinary area of
multi-sensory data fusion and its applications; technical areas of
interest include, but are not limited to:
o modeling and calibration of multiple sensors
o estimation of 3-D shape and motion
o 3-D object modeling and recognition
o active vision, task-driven sensing, and sensor planning
o integration of visual, tactile, force, and kinematic information
o computing architectures and programming environments
o distributed detection & decision networks
o robot control based on real-time multi-sensor inputs
o man-machine interactive 3-D modeling and perception
Abstract Due Date: APRIL 20, 1990
Manuscript Due Date: AUGUST 24, 1990
The Proceedings will be distributed at the conference.
Format for abstract submission:
- paper title
- authors' full names and affiliations
- complete addresses for all authors
- phone, FAX, and e-mail for all authors
- 200 words text (approx.)
- 50-100 word principal author biography
Submit four copies by mail or tele-FAX to:
1) SPIE
attn: OE/TECHNOLOGY '92 -- Sensor Fusion V
P.O. Box 10
Bellingham, WA 98227-0010
(FAX: 206/647-1445)
(Phone: 206/676-3290)
OR submit directly by e-mail to:
2) schenker@telerobotics.jpl.nasa.gov
Dr. Paul S. Schenker
Jet Propulsion Laboratory
4800 Oak Grove Drive/ MS 198-219
Pasadena, CA 91109
ADDITIONAL INFORMATION: The Sensor Fusion V conference is held as one part of
the larger OPTCON '92 meeting. OPTCON '92 will include not only related SPIE
OE/TECHNOLOGY' 92 meetings on Image Processing, Visual Communications, Machine
Vision, Visual & Graphics Modeling, Robotics, et al., but also a variety of affiliated OSA, IEEE/Lasers and Electro-Optics(LEOS) meetings on the visual
and optical sciences. For further information, contact SPIE, as shown above.
------------------------------
Date: Tue, 31 Mar 1992 16:03:13 +0800
From: Geoff West <geoff@marsh.cs.curtin.edu.au>
Subject: CFP: Workshop on 2D & 3D Spatial Data
Call for Participation in the
Workshop on Two and Three dimensional
Spatial Data:
Representation and Standards
Held under the auspices of The Australian Pattern Recognition Society
OVERVIEW
It is proposed to hold a two day workshop on issues of representation
and standards of 2D and 3D spatial representations. This will be held in
Perth at Curtin University on the 7th and 8th of December 1992. The format
of the workshop will be a number of invited talks by both national
and international researchers. There will be time for discussion and
presentations by Australian researchers and commercial users.
WORKSHOP CONTENTS
The choice and use of representations for two and three dimensional
data and information is crucial to the disciplines of:
Computer Vision Pattern Recognition
Geographical Information Systems Computer Graphics
Medical Databases and Applications Remote Sensing
Computer Aided Design Image Processing
Man Machine Interface Virtual Reality
Each of these fields is concerned with the processing and analysis of
information that can be represented using a variety of techniques. The
choice of the particular technique is, to a large extent, dependent on
the application and available technology. It is a truism that each
discipline makes use of its own particular representation(s) which leads
to incompatibility with other disciplines.
It is becoming obvious that there is an increasing interdependence in
the above disciplines for representing objects and environments. There
is therefore a need to bring together researchers and users in different
disciplines to interact and address the issues that arise in different
forms of spatial representation. The topics covered in this workshop will
include (but not be limited to):
1/ Techniques for two and three dimensional spatial representation.
There are a large number of different representations e.g. octrees,
quadtrees, BReps, CSG trees used by many practitioners in different
disciplines. Presentations of new techniques, extensions and use in
new areas will be favoured.
2/ Compatibility and standardisation of various representations.
There is increasing commonality between the various disciplines e.g.
computer graphics, vision and CAGD, and GIS and remote sensing.
Presentation on issues concerned with standardisation of representations
across disciplines and interchange of data will be welcome.
3/ Abstract models for representing environments.
There is a need and interest in different types of representation e.g.
functional and teleological that can be used to represent spatial data
to capture meaning which is difficult to represent in the more traditional
methods. Presentations of new models in these and similar directions are
welcome.
4/ Tools for manipulating spatially organised data.
One of the biggest problems with any representation is the manipulation,
display etc. of the data. While each discipline has its own means of
handling data there is little exchange of ideas across the disciplines.
We welcome presentations that describe new tools or the application of
existing tools to other disciplines.
WHO SHOULD ATTEND
The workshop should be suitable for people from the academic, applied and
industrial research and development communities. It is important for all
three areas to be well represented to allow cross fertilisation between
'cutting edge' research and end users.
DEADLINES AND FORMAT
Abstract due: August 31st 1992
Final paper: November 15th 1992
The abstract should not exceed two A4 pages. The final paper will be
expected to exceed 5 pages in 10 point Times font. All papers should
be sent to Mrs M Simpson as the address below.
ORGANISING COMMITTEE
S.Venkatesh, G. West Department of Computer Science
B. White School of Mathematics and Statistics
Curtin University of Technology,
PO Box U1987, Perth, 6001.
Fax: (09) 351-2819
(09) 351-3197
Tel: (09) 351-3005 G West.
(09) 351-2407 S Venkatesh
(09) 351-7120 B White
Email: aprs_workshop@cutmcvax.cs.curtin.edu.au
Please return to: Mary Simpson, School of Computing,
Curtin University,
GPO Box U1987,
Perth 6001,
Western Australia.
Tel: (09) 351-7298
Fax: (09) 351-2819
I am interested in the workshop and would like to be on the mailing list:
Name:
Address:
Tel:
Email:
Email: geoff@cutmcvax.cs.curtin.edu.au | ... __o
Fax: 61 9 351 2819 |... -\<,
Tel: 61 9 351 3005 |....(_)/(_)
------------------------------
Date: Wed, 1 Apr 1992 14:36:26 GMT
From: paolo@ai.univie.ac.at (paolo petta)
Organization: ECAI92 Vienna Conference Service
Subject: Advance Information - ECAI92
=======================================================================
Advance Information - ECAI92 - Advance Information - ECAI92 - VIENNA
=======================================================================
10th European Conference on Artificial Intelligence (ECAI 92)
August 3-7, 1992, Vienna, Austria
Programme Chairperson
Bernd Neumann, University of Hamburg, Germany
Local Arrangements Chairperson
Werner Horn, Austrian Research Institute for AI, Vienna
The European Conference on Artificial Intelligence (ECAI) is the
European forum for scientific exchange and presentation of AI research.
The aim of the conference is to cover all aspects of AI research and to
bring together basic research and applied research. The Technical
Programme will include paper presentations, invited talks, survey
sessions, workshops, and tutorials. The conference is designed to
cover all subfields of AI, including non-symbolic methods.
ECAIs are held in alternate years and are organized by the European
Coordinating Committee for Artificial Intelligence (ECCAI). The 10th
ECAI in 1992 will be hosted by the Austrian Society for Artificial
Intelligence (OGAI). The conference will take place at the Vienna
University of Economics and Business Administration.
PROGRAMME STRUCTURE
Mon-Tue (Aug 3-4): Tutorials and Workshops
Wed-Fri (Aug 5-7): Invited Talks, Paper Presentations, Survey Sessions
Tue-Fri (Aug 4-7): Industrial Exhibition
======================== INVITED LECTURES ==============================
Stanley J.Rosenschein (Teleos Research, Palo Alto, Calif., USA):
Perception and Action in Autonomous Systems
Oliviero Stock (IRST, Trento, Italy):
A Third Modality of Natural Language?
Promising Trends in Applied Natural Language Processing
Peter Struss (Siemens AG, Muenchen, Germany):
Knowledge-Based Diagnosis - An Important Challenge and Touchstone
for AI
=================== TECHNICAL PAPERS PROGRAMME =========================
This will consist of papers selected from the 681 that were submitted.
These papers will be given in parallel sessions held from August 5
to 7, 1992. The topics of the papers include:
* Automated Reasoning
* Cognitive Modeling
* Connectionist and PDP Models for AI
* Distributed AI and Multiagent Systems
* Enabling Technology and Systems
* Integrated Systems
* Knowledge Representation
* Machine Learning
* Natural Language
* Philosophical Foundations
* Planning, Scheduling, and Reasoning about Actions
* Principles of AI Applications
* Reasoning about Physical Systems
* Robotics
* Social, Economic, Legal, and Artistic Implications
* User Interfaces
* Verification, Validation & Test of Knowledge-Based Systems
* Vision and Signal Understanding
============================ TUTORIALS =================================
TUTORIALS ----- Mon, August 3, 9:00-13:00
Applied Qualitative Reasoning
Robert Milne, Intelligent Applications Ltd, Scotland, and
Louise Trave-Massuyes, LAAS, Toulouse, France
In Search of a New Planning Paradigm - Steps Beyond Classical Planning
Joachim Hertzberg, GMD, Germany, and
Sam Steel, Essex University, Cholchester, UK
Machine Learning: Reality and Perspectives
Lorenza Saitta, Universita di Torino, Italy
TUTORIALS ----- Mon, August 3, 14:00-18:00
AI in Service and Support
Anil Rewari, Digital Equipment Corp., Marlboro, Mass.
Case-Based Reasoning
Katia P. Sycara, Carnegie Mellon University, Pittsburgh, Penn.
Computer Vision, Seeing Systems, and Their Applications
Jan-Olof Eklundh, Royal Institute of Technology, Stockholm, Sweden
Nonmonotonic Reasoning
Gerhard Brewka, ICSI, Berkeley, Calif., and
Kurt Konolige, SRI, Menlo Park, Calif.
TUTORIALS ----- Tue, August 4, 9:00-13:00
Distributed AI
Frank von Martial, Bonn, and Donald Steiner, Siemens AG, Germany
Fuzzy Set-Based Methods for Inference and Control
Henri Prade, IRIT, Universite Paul Sabatier, Toulouse, France
Validation of Knowledge-Based Systems
Jean-Pierre Laurent, Universite de Savoie, Chambery, France
TUTORIALS ----- Tue, August 4, 14:00-18:00
Current Trends in Language Technology
Harald Trost, Austrian Research Institute for AI and University of
Vienna, Austria
KADS: Practical, Structured KBS Development
Robert Martil, Lloyd's Register of Shipping, Croydon, UK, and
Bob Wielinga, University of Amsterdam, The Netherlands
Neural Networks: From Theory to Applications
Francoise Fogelman Soulie, Mimetics, France
User Modeling and User-Adapted Interaction
Sandra Carberry, University of Delaware, Newark, Delaware,
and Alfred Kobsa, University of Konstanz, Germany
============================ WORKSHOPS =================================
Workshops are part of the ECAI92 scientific programme. They will give
participants the opportunity to discuss specific technical topics in a
small, informal environment, which encourages interaction and exchange
of ideas. Persons interested in attending a workshop should contact the
workshop organizer (addresses below), and the conference office (ADV)
for ECAI92 registration. Note that all workshops require an early
application for participation.
A full description of all workshops can be obtained by sending an email
to ecai92.ws@ai.univie.ac.at, which will automatically respond.
WORKSHOPS ----- Mon, August 3
Art and AI: Art / ificial Intelligence
Robert Trappl, Austrian Research Institute for Artificial Intelli-
gence, Schottengasse 3, A-1010 Vienna, Austria; Fax: +43-1-630652,
Email: robert@ai.univie.ac.at
Coping with Linguistic Ambiguity in Typed Feature Formalisms
Harald Trost, Austrian Research Institute for Artificial Intelli-
gence, Schottengasse 3, A-1010 Vienna, Austria; Fax: +43-1-630652,
Email: harald@ai.univie.ac.at
Formal Specification Methods for Complex Reasoning Systems
Jan Treur, AI Group, Dept.of Mathematics and Computer Science, Vrije
Universiteit Amsterdam, De Boelelaan 108-1a, NL-1081 HV Amsterdam,
The Netherlands; Fax: +31-29-6427705, Email: treur@cs.vu.nl
Knowledge Sharing and Reuse: Ways and Means
Nicolaas J.I. Mars, Dept.of Computer Science, University of Twente,
PO Box 217, NL-7500 AE Enschede, The Netherlands; Fax: +31-53-339605,
Email: mars@cs.utwente.nl
Model-Based Reasoning
Gerhard Friedrich, Franz Lackinger, Dept.Information Systems, CD-Lab
for Expert Systems, Univ.of Technology, Paniglg.16, A-1040 Vienna;
Fax: +43-1-5055304, Email: friedrich@vexpert.dbai.tuwien.ac.at
Neural Networks and a New AI
Georg Dorffner, Austrian Research Institute for Artificial Intelli-
gence, Schottengasse 3, A-1010 Vienna, Austria; Fax: +43-1-630652,
Email: georg@ai.univie.ac.at
Scheduling of Production Processes
Juergen Dorn, CD-Laboratory for Expert Systems, University of
Technology, Paniglgasse 16, A-1040 Vienna, Austria;
Fax: +43-1-5055304; Email: dorn@vexpert.dbai.tuwien.ac.at
Validation, Verification and Test of KBS
Marc Ayel, LIA, University of Savoie, BP.1104, F-73011 Chambery,
France; Fax: +33-79-963475, Email: ayel@frgren81.bitnet
WORKSHOPS ----- Tue, August 4
Advances in Real-Time Expert System Technologies
Wolfgang Nejdl, Department for Information Systems, CD-Lab for Expert
Systems, University of Technology, Paniglgasse 16, A-1040 Vienna,
Austria; Fax: +43-1-5055304, Email: nejdl@vexpert.dbai.tuwien.ac.at
Application Aspects of Distributed Artificial Intelligence
Thies Wittig, Atlas Elektronik GmbH, Abt.TEF, Sebaldsbruecker
Heerstrasse 235, D-W-2800 Bremen 44, Germany; Fax: +49-421-4573756,
Email: t_wittig@eurokom.ie
Applications of Reason Maintenance Systems
Francois Charpillet, Jean-Paul Haton, CRIN/INRIA-Lorraine, B.P. 239,
F-54506 Vandoeuvre-Les-Nancy Cedex, France; Fax: +33-93-413079,
Email: charp@loria.crin.fr
Artificial Intelligence and Music
Gerhard Widmer, Austrian Research Institute for Artificial Intelli-
gence, Schottengasse 3, A-1010 Vienna, Austria; Fax: +43-1-630652,
Email: gerhard@ai.univie.ac.at
Beyond Sequential Planning
Gerd Grosse, FG Intellektik, TH Darmstadt, Alexanderstr.10, D-6100
Darmstadt, Germany; Fax: +49-6151-165326,
Email: grosse@intellektik.informatik.th-darmstadt.de
Concurrent Engineering: Requirements for Knowledge-Based Design Support
Nel Wognum, Dept. of Computer Science, University of Twente, P.O.Box
217, NL-7500 AE Enschede, The Netherlands; Fax: +31-53-339605, Email:
wognum@cs.utwente.nl
Improving the Use of Knowledge-Based Systems with Explanations
Patrick Brezillon, CNRS-LAFORIA, Box 169, University of Paris VI,
2 Place Jussieu, F-75252 Paris Cedex 05, France; Fax: +33-1-44277000,
Email: brezil@laforia.ibp.fr
The Theoretical Foundations of Knowledge Representation and Reasoning
Gerhard Lakemeyer, Institut f.Informatik III, Universitaet Bonn,
Roemerstr.164, D-W-5300 Bonn 1, Germany; Fax: +49-228-550382,
Email: gerhard@uran.informatik.uni-bonn.de
WORKSHOPS ----- Mon and Tue, August 3-4
Expert Judgement, Human Error, and Intelligent Systems
Barry Silverman, Institute for AI, George Washington University, 2021
K St. NW, Suite 710, Washington, DC 20006, USA; Fax: (202)785-3382,
Email: barry@gwusun.gwu.edu
Logical Approaches to Machine Learning
Celine Rouveirol, Universite Paris-Sud, LRI, Bat 490, F-91405 Orsay,
France; Fax: +33-1-69416586, Email: celine@lri.lri.fr
Spatial Concepts: Connecting Cognitive Theories with Formal
Representations
Simone Pribbenow, Email: pribbeno@informatik.uni-hamburg.de, and
Christoph Schlieder, Institut f.Informatik und Gesellschaft,
Friedrichstr.50, D-7800 Freiburg, Germany; Fax: +49-761-2034653,
Email: cs@cognition.iig.uni-freiburg.de
======================== GENERAL INFORMATION ===========================
DELEGATE'S FEE
(in Austrian Schillings, approx. 14 AS = 1 ECU, 12 AS = 1 US$)
early late on-site
(rec.before) (Jun 1) (Jul 15)
Members of ECCAI member organizations 4.500,- 5.000,- 6.000,-
Non-Members 5.000,- 6.000,- 7.000,-
Students 1.500,- 2.000,- 2.500,-
The delegate's fee covers attendance at the scientific programme
(invited talks, paper presentations, survey sessions, and workshops),
conference documentation including the conference proceedings, admission
to the industrial exhibition, and participation in selected evening
events.
TUTORIAL FEE (per tutorial)
early late on-site
(rec.before) (Jun 1) (Jul 15)
Members of ECCAI member organizations 3.000,- 3.500,- 4.000,-
Non-Members 3.500,- 4.000,- 4.500,-
Students 1.500,- 2.000,- 2.500,-
Tutorial Registration entitles to admission to that tutorial, admission
to the exhibition, a copy of the course material, and refreshments
during the tutorial.
ACCOMODATION
Hotels of different price categories, ranging from DeLuxe to the very
cheap student hostel (available for non-students too), are available for
the first week of August. The price ranges (in AS) are given below.
Hotel Category single room double room
with bath without bath with bath without bath
DeLuxe ***** 1690,-/2375,- 2400,-/3200,-
A **** 990,-/1300,- 1400,-/1790,-
B *** 750,-/980,- 1100,-/1350,-
Season Hotel 480,-/660,- 335,-/450,- 780,-/900,- 580,-/730,-
Student Hostel 220,- 380,-
The conference venue is located in a central district of Vienna. It can
be reached easily by public transport.
============================ REGISTRATION ==============================
For detailed information and registration material please contact the
conference office:
ADV
c/o ECAI92
Trattnerhof 2
A-1010 Vienna, Austria
Tel: +43-1-5330913-74, Fax: +43-1-5330913-77, Telex: 75311178 adv a
or send your postal address via email to: ecai92@ai.univie.ac.at
------------------------------
Date: Wed, 1 Apr 92 18:44:29 BST
From: J.Illingworth@ee.surrey.ac.uk
Subject: SPECIAL OFFER
***********************
SPECIAL OFFER PRICE
***********************
Proceedings of
Alvey Vision Club Conferences
The Alvey Vision Club Conferences established themselves as the major forum
for the presentation of UK work in Machine Vision, Image Processing and Pattern
Recognition during the eighties. A small number of residual copies of the
proceedings of two of these conferences are still available and are on offer at
the special price of 5 English pounds + postage and packing (2 pounds within
the U.K., 3:50 for overseas postage) for each volume.
The two conferences which are available are
AVC88, held in Manchester
AVC89, held in Reading
Each volume is about 300 pages and contains about 40-50 wide ranging papers
describing work in machine vision and pattern recognition.
Sessions at the conferences included work on
* model-based vision,
* shape representation,
* tracking and AGVs,
* image features,
* texture,
* Hough transforms,
* shape from ...
* shape from motion.
* + much, much more
Requests for copies of these proceedings and should be sent to:
Dr J. Illingworth,
BMVA Secretary,
Dept of Electronics,
University of Surrey,
Guildford GU2 5XH.
United Kingdom
email: J.Illingworth@uk.ac.surrey.ee.
Payment must be included with any request. All cheques or payment
orders are to be in pounds STERLING and should be made payeable to
``The British Machine Vision Association''.
Enquiries will be dealt with on a first come, first served basis.
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Proceedings of
British Machine Vision Conference
----------------------------------
In addition to the above special offer, copies are available of the more recent
British Machine Vision Conferences, which are organised by the British Machine
Vision Association (a merger of the Alvey Vision Club and the British Pattern
Recognition Association). The proceedings which are available are:
BMVC90, held in Oxford
BMVC91, held in Glasgow
The cost of BMVC91 proceedings is 25 English pounds while BMVC92 cost
33 English pounds. It is also necessary to add costs of package and posting
(2 pounds within the U.K. and 3:50 for overseas orders). As above all orders
must include payment in full and all cheques or payment orders must be in
pounds STERLING and made payeable to
``The British Machine Vision Association''.
Dr. J. Illingworth, | Phone: (0483) 300-800 Ext. 2299
V.S.S.P. Group, | Fax : (0483) 34139
Dept of Electronic and Electrical Eng, | Email: J.Illingworth@ee.surrey.ac.uk
University of Surrey, |
Guildford, |
Surrey GU2 5XH |
United Kingdom |
------------------------------
Date: Thu, 2 Apr 1992 14:14:56 GMT
From: oh@roquefort.auc.dk (Ole Hansen )
Organization: LBA/AUC/DK
Subject: Post-Doc position wanted (long)
Keywords: image processing.
I am a newly graduated Ph.D from the Laboratory of Image Analysis at
Aalborg University, and I am now looking for new challenges in a postdoc
position at a European computer vision laboratory. If you or somebody you
know is interested in my qualifications, I would be happy to provide
further details.
A brief CV and a thesis abstract is enclosed this email.
Yours Sincerely,
Ole Hansen, Ms. Sci. E.E. , Ph. D.
Laboratory of Image Analysis, Aalborg University, Denmark.
Email: oh@vision.auc.dk
Brief Curriculum Vitae for
Ole Hansen
==========================
Born: 17. February 1957.
Nationality: Danish
Sex: Male
Marital Status: Single
Affiliation:
Laboratory of Image Analysis, Institute of Electronic Systems
Aalborg University (AUC)
Fredrik Bajers Vej 7-D, DK-9210 Aalborg East, Denmark
phone: +45 98 158522 ext. 4985.
email: oh@vision.auc.dk
fax: +45 98 154008
1984: M.Sc.EE. - Aalborg University (AUC), Denmark
1984-1985: Research Assistant at the University by
Speech Processing Group.
Topics: Word Recognition (Markov Model based) and Speech Coding.
- in that period working with Intel 8086 family
1985-1987: R&D Engineer at the Danish company Bruel & Kjaer designing
man-machine interface to acoustic measuring instruments.
1987-1991: Research ass. and Ph-D student at the AUC,
Laboratory of Image Analysis: Motion Estimation (Optic Flow),
Multi-dimensional Image Processing, Scale Space Methods,
Depth-Estimation, Group Theory in Image Analysis.
Experience with Unix-programming and system administration on
Uniplus, Sys-V (Motorola), Sun3/Sun4.
Programming experience in Pascal,cc,c++, Motif, X-windows.
1992 Ph.D., Thesis: "On the Use of Local Symmetries in Image
Processing and Computer Vision", defended 6 March 1992.
Teaching Experience: Partly as supervisor and partly as lecturer at
Graduate and post-graduate level. Topics: Pattern Recognition,
Motion Analysis, Tomographics Reconstruction Techniques, Basic
Image Processing.
Languages: Danish, English, German, and Russian.
Scientific interests:
Signal Processing, Pattern Recognition, Texture Analysis,
Motion Analysis, Scale Space Methods, Image Coding, Machine
Vision, Visual Perception.
Selected Publications :
On modeling active movements of camera used for depth-perception
NOBIM Conference, Oslo 1988.
Detection of local symmetries in multi-dimensional images,
5ICIAP, Positano, Italy 1989
Multidimensional Symmetry Modelling,
Pattern Recognition Letters, April 1992.
Estimation of Optic Flow in Multi-Dimensional Image-sequences,
7th Scandinavian Conference on Image Aanalysis, 1991.
Ph.D. Thesis Alert
==================
On the Use of Local Symmetries in Image Analysis and Computer Vision
Ole Hansen
Laboratory of Image Analysis, Aalborg University, Denmark
6 March 1992.
This thesis describes modeling of local image patterns, with an
analytic description, and methods for detection of the patterns. The
detection methods involves mainly pipelined operations like
convolutions, and they can be implemented cost-effectively on
signal-processors. The information, which describes the individual
pattern-classes and is used for the detection process, is encoded in a
set of convolution kernels.
The thesis develops a theoretical description of the symmetry modeling
and detection methods, and applications of the symmetry concept are
presented.
The work covers three main issues.
The first issue concerns symmetry modeling in 2-dimensional
complex-valued images. The symmetries are modeled by a set of complex
valued transformation functions, which makes it pos- sible to describe
symmetries by transformation functions with 4 variable parameters. The
complex symmetry model enables a rotation-invariant modeling of
an-isotropic real-valued pattern, by using the complex phase to
describe the orientation of the pattern. The elliptic symmetry is
presented as an application.
The second issue concerns a multi-dimensional symmetry model. The
model describes patterns, which are homogeneous solutions to a subclass
of first-order partial differential equations. A detection algorithm
is introduced and implemented for 3- dimensional images. A set of
3-dimensional symmetries are presented and used to test the algorithm.
The third issue concerns a method for the detection of the optical flow
in multi-resolutional image-sequences by mea- suring spatio-temporal
displacement. The algorithm estimates the apparent optical flow and
"true" optical flow. Confidence values, which indicates the robustness
of the two estimated values, are calculated. Pyramids are constructed
for each of such confidence images, and they are used in a
"coarse-to-fine" approach to direct the computation to areas with a
robust estimation of the optical flow. The algorithm is tested both on
synthetic and natural image-sequences. It is shown that the
"coarse-to-fine" approach can result in a substantial reduction of the
computational load.
Thesis Advisors:
Prof. Erik Granum, Aalborg University,
Dr. Josef Bigun, Swiss Federal Institute of Technology, Lausanne
Thesis Promoters:
Prof. J. J. Koenderink, Utrecht State University,
Prof. K. Conradsen, Technical University, Copenhagen.
Copies available from LIA/AUC, Aalborg University,
Fredrik Bajersvej 7, Bldg. D-1, DK-9220 Aalborg East
Denmark (email: eg@vision.auc.dk).
------------------------------
End of VISION-LIST digest 11.12
************************
