Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 12 Issue 14
VISION-LIST Digest Wed Mar 31 14:40:19 PDT 93 Volume 12 : Issue 14
- ***** The Vision List has changed hosts to TELEOS.COM *****
- Send submissions to Vision-List@TELEOS.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@TELEOS.COM
- Access Vision List Archives via anonymous ftp to FTP.TELEOS.COM
Today's Topics:
Database of handwritten digits, words, and ZIP Codes
Matching simple images
VEIL/MERLIN: Programming Interface for MaxVideo 20
Image Segmentation as an Optimization Problem.
Image database quary
Wanted Help: Integrating Neural nets with Linear Programming
Raytracers
Preprint available: Some Solutions to the Missing Feature Problem in Vision
Summer job on parallel vision processing
PhD Program in Computer Science, Univ. of Central Florida
2nd CFP: Neural networks on shape analysis
CVPR information
Vision Interface Meeting Announcemnet
First International Summer Institute in Cognitive Science
2nd CFP: Neural networks on shape analysis
CFP: ASIS SIG/Classification Research Workshop - Call for Papers
CFP: Int'l Conf. on Signal Proc. Applics. & Technology
CFP: The 5th UNB AI Symposium
Hough Transforms - a colloquium
Meeting: International Conference on Binocular Stereopsis and Optic Flow
CFP: Digital Video Compression and Processing on Personal Computers
List of references for non-rigid motion (LONG)
----------------------------------------------------------------------
Date: Sun, 21 Mar 93 22:01:19 EST
From: hull@cs.buffalo.edu (Jonathan Hull)
Subject: database of handwritten digits, words, and ZIP Codes
The Center Of Excellence for
Document Analysis and Recognition (CEDAR)
State University of New York at Buffalo
announces the availability of
CEDAR CDROM 1:
USPS Office of Advanced Technology Database of Handwritten
Cities, States, ZIP Codes, Digits, and Alphabetic Characters
CEDAR is pleased to announce the availability of a CDROM
database that contains handwritten words and ZIP Codes in high
resolution grayscale (300 ppi 8-bit) as well as binary handwrit-
ten digits and alphabetic characters (300 ppi 1-bit). This data-
base is intended to encourage research in off-line handwriting
recognition by providing access to handwriting samples digitized
from envelopes in a post office.
Specifications of the database include:
+ 300 ppi 8-bit grayscale handwritten words (cities,
states, ZIP Codes)
o 5632 city words
o 4938 state words
o 9454 ZIP Codes
+ 300 ppi binary handwritten characters and digits:
o 27,837 mixed alphas and numerics segmented from
address blocks
o 21,179 digits segmented from ZIP Codes
+ every image supplied with a manually determined truth
value
+ all data digitized on an Eikonix EC850 CCD scanner
+ extracted from live mail in a working U.S. Post Office
+ simulates a "real" recognition environment:
o unrestricted for author
o unrestricted for writing style
o unrestricted for writing implement (pen, pencil,
...)
o authors had no knowledge their samples were to be
used
+ divided into explicit training and test sets (90%
training and 10% testing)
+ performance comparison between researchers possible on
the same data sets.
+ word images in the test set supplied with dictionaries
of postal words that simulate partial recognition of
the corresponding ZIP Code.
+ digit images included in test set that simulate
automatic ZIP Code segmentation. Results on these data
can be projected to overall ZIP Code recognition per-
formance.
+ image format documentation and software included
Suitable for handwriting recognition research, the database
can be used for:
o algorithm development
o system training and testing
The database is a valuable tool for developing the range of
techniques needed for high performance handwritten word recogni-
tion including preprocessing, segmentation, feature extraction,
and classification. The system requirements are a 5.25" CD-ROM
drive with software to read ISO-9660 format.
For any further information, including how to order the
database, please contact:
Dr. Jonathan J. Hull
Associate Director, CEDAR
226 Bell Hall
State University of New York at Buffalo
Buffalo, NY 14260
716-645-6164 x109 (voice)
716-645-6176 (fax)
hull@cs.buffalo.edu (email)
Please note: email contact is preferred and is most efficient
------------------------------
Date: Tue, 30 Mar 1993 08:58:47 +0100
From: Jocelyn Paine <popx@vax.ox.ac.uk>
Organization: Oxford University VAX 6620
Subject: Matching simple images
I'm looking for advice on image-matching for an agent living in a simple
microworld. The problem is a lot simpler than anything encountered in
real robot vision, but I think methods well-known to vision researchers
would apply. I'd be grateful for suggestions.
As an aid to teaching AI to beginners, I'm working on a simple agent
which inhabits a 2-d cellular microworld. Each cell in this microworld
can be either empty or contain one or more objects. The agent "sees" an
image of the region around it, this being a rectangle of pixels, each
pixel corresponding to one cell in the microworld. A pixel is either 1
or 0. To simplify things, there are no hidden regions, so every image is
an exact rectangular chunk out of the agent's surroundings. The size of
an image is user-settable, but will normally be about 20x20.
For navigation and mapping, I want to be able to compare one image with
a set of others, finding the best match. If there is a good match, I
would also like to get a measure of "optic flow", specifying how one
image must be moved to superimpose it as well as possible over the
other. Matching must be efficient (well, as efficient as one can
achieve on a serial machine), since it may be done several times in each
perceive-think-act cycle.
Problems:
1) The world may have changed between taking two images of the same
region, so there may not be an exact match.
2) The agent can face in one of four orientations, so rotation has to be
taken into account.
3) So does translation, as the images may not have been taken at exactly
the same location.
4) Strictly, each cell contains not only a 1 or 0, but also bytes
representing the contents of the corresponding microworld cell. I'm
prepared either to use these or to ignore them, depending on what's most
efficient. Because of the problems above, they can't be used reliably for
determining point-for-point correspondance between images.
I have found some methods which should be able to help. However, I
haven't tackled this kind of problem before, and I'm not sure how fast
they'd be, or how difficult to get working. Any advice would be very
welcome.
Jocelyn Paine
Experimental Psychology
Oxford
------------------------------
Date: Wed, 31 Mar 93 12:46:50 EST
From: jrt2q@redwood.cs.virginia.edu
Subject: VEIL/MERLIN: Programming Interface for MaxVideo 20
We happily anounce the beta release of VEIL/MERLIN.
VEIL (Virginia's Extensible Imaging Library) is a C++ library
designed to simplify programming Datacube's MaxVideo20. VEIL uses a
dataflow model of computation where the nodes of a graph represent
image transformations and the arcs image paths. Users can either
build graphs interactively using MERLIN (a graphical user interface)
or call VEIL from arbitrary C++ code.
The smallest schedulable and executable entity in VEIL is the
Graph. Graphs consist of functions and their interconnections.
Functions are C++ classes that group the image processing elements of
the MV20, their interconnections, and their attributes into higher
level image processing primitives. For example, the elements of the
linear section of the AU device are grouped into an Add function
class, an instance of which can add anywhere from two for four images
together. The various attributes of the processing elements of the
Add can be specified either through Add's constructor or other public
methods.
Once built, users can schedule and then cycle or run multiple
graphs. Graphs are scheduled as Pipe Altering Threads (PAT's) that
group deferrable actions in the host's kernel for maximum speed. All
processing that cannot occur inside of PAT's is performed while they
run synchronized to the relevant image processing elements.
Other synchronization with the host cpu is handled through
callbacks and other methods. Users can attach callbacks to a few of
the function classes that will be called as often as possible
synchronized to the Pipe Altering Thread of their graph. In these
callbacks, the actual pixel or other data of the MV20 can be
processed. A VEIL program that adaptively adjusts the threshold of an
image with a callback is listed at the end of this notice.
VEIL is easily extended to include new function classes. To
extend VEIL and MERLIN, one has only to write a derived C++ class. A
function class defines its processing task by overriding the virtual
methods of the base class.
MERLIN (My Extensible Real-time Library Interactive iNterface) is
a graphical user interface to VEIL. Users can interactively create
graphs that can be later loaded and run by arbitrary C++ programs.
VEIL and MERLIN are the result of our second serious attempt at
creating a programming interface to Imageflow. Its predecessor
(accidentally named PRISM -- apologies, Keith!) was described at SPIE
Machine Vision and Applications last December. Unfortunately it
proved too difficult to extend to warrant continued use. Currently,
we use VEIL/MERLIN exclusively in our day to day MV-20 work. It has
proved a valuable and stable tool and has greatly reduced our need
to write in raw ImageFlow.
VEIL runs on Sun SPARC 2 workstations using the Performance
Technologies Sbus-to-VME adapter, as per DataCube's recommendations;
changes would be necessary to make it run with other configurations.
Compiling MERLIN requires both VEIL and SUIT (Simple User Interface
Toolkit), a product of the UVA human-computer interface group. VEIL
and MERLIN can be obtained via anonymous ftp from
uvacs.cs.virginia.edu. Simply cd to pub/veil, set mode to binary, and
'mget *.Z'. If you intend to use MERLIN you will also need to get
SUIT from pub/suit/distribution/sparc.
We hope that you will find VEIL useful, and eagerly await your
comments, suggestions and extensions.
John Taylor (jrt2q@virginia.edu)
Sample VEIL program that adaptively adjust the threshold of the
input image:
#include <stdio.h>
#include "veil.h"
int thresh = -100;
/* Constructor with attributes */
Threshold threshold (thresh, -128, 127);
void AdaptiveThresh (int rows, int cols, char *data)
{
int i, j, count = 0;
for (i = 0; i < rows; i++)
for (j = 0; j < cols; j++)
if (*data++ > 0)
count++;
if (count < rows * cols / 2)
threshold.SetThreshold (++thresh);
}
main ()
{
Graph graph;
Camera camera;
Monitor monitor;
Host host;
host.AttachCallback (AdaptiveThresh);
graph.Insert (camera);
graph.Insert (monitor);
graph.Insert (host);
graph.Insert (threshold);
graph.Connect (camera, 0, threshold, 0);
graph.Connect (threshold, 0, host, 0);
graph.Connect (threshold, 0, monitor, 0);
VEIL_Init ();
graph.Schedule ();
graph.Cycle ();
while (1)
/* Calls callbacks and performs other processing */
graph.Update ();
graph.Teardown ();
VEIL_Terminate ();
}
------------------------------
Date: Sun, 21 Mar 1993 01:58:43 GMT
From: prabhu@cs.tulane.edu (Prabhu)
Organization: Computer Science Dept., Tulane Univ., New Orleans, LA
Subject: Image Segmentation as an Optimization Problem
Keywords: image segmentation, optimization, texture
Hi,
I am looking for papers that treat the problem of image segmentaion
as a form of optimization problem. In other words, can segmentation process
be considered equivalent to optimizing some local/global measurements/features
of the image? I am especially interested in region-based and texture based
approaches.
I'd appreciate any reference/pointers/suggestions. Pl email to
prabhu@rex.cs.tulane.edu. I`ll summarize if there is enough interest.
Regards - prabhu
Devaraya Prabhu prabhu@rex.cs.tulane.edu
Dept of Comp Science
Tulane University
New Orleans
------------------------------
Date: Mon, 29 Mar 93 17:48:35 +0200
From: narciso@gti.upm.es (Narciso Garcia Santos )
Subject: Image database quary
Having worked in computer vision applications for several years, we have not
found any "standard image database for industrial parts". I am considering,
at least, side top-down and side views of: bolts, nuts, tools, pieces, keys,
..., as well as more complex scenes. So:
1 - Does anybody know any well accepted standard set?
2 - If the answer was "no",
does anybody know a good/complete set?
Thanking in advance,
Narciso Garcia E-mail: narciso@gti.upm.es
E.T.S. Ingenieros Telecomunicacion
Universidad Politecnica de Madrid
E-28040 Madrid, Spain
------------------------------
Date: 18 Mar 93 05:37:18 GMT
From: chen@kuri.ces.kyutech.ac.jp (Chen Ke)
Organization: Kyushu Institute of Technology, Iizuka, JAPAN.
Subject: Wanted Help: Integrating Neural nets with Linear Programming
Hi, everybody,
I would appreciate it if anyone can supply me with materials or
information about dealing with linear programming problems by
means of neural networks techniques and their applications to
constriant-satisfaction problems in computer vision, such as
optimal labelling problems etc.
Email is prefered for any response.
regards,
Ke Chen
Dr. Ke Chen
Masumi-Ishikawa Research Group
Dept. of Control Engineering and Science
Kyushu Institute of Technology
Iizuka, Fukuoka 820, Japan
Phone +81-948-29-7738(office)
Fax +81-948-29-7709
Email chen@kuri.ces.kyutech.ac.jp
------------------------------
Date: Mon, 29 MAR 93 16:27 N
From: ROBERTO@uduniv.cineca.it
Subject: Raytracers
Dear Sir(s),
I refer to a recent request of mine (march 11), to acquire information
about raytracers and related material.
I collected many interesting answers, which I briefly summarize
here below.
The present message is to thank you very much for
the invaluable help I received by your service.
1. Corresponding: Mark Maimone MARK.MAIMONE@A.GP.CS.CMU.EDU
Suggested products: Rayshade4.0.6 Rayshade44.0.6enh
Utah Raster Toolkit
2. Corresponding: Thomas M. Breuel TMB@IDIAP.CH
Suggested products: Rayshade4.0.6
3. Corresponding: Jiri Martinek MARTINEK@VISION.FELK.CVUT.CS
Suggested products: Rayshade4.0.6
4. Corresponding: Isaac Ng H.NG@EE.SURREY.AC.UK
Suggested products: RayShade PoV ART DKBtrace RTrace VIVID2
RAY4 MTV,QRT,DBW XDART Inetray prt
VM_pRAY VREND
5. Corresponding: Thomas TR@FCT.UNL.PT
Suggested Products: Rayshade ;
others in the FAQ in newsgroup comp.graphics.
6. Corresponding: Yang Chen YANGCHEN@ANTIGONE.USC.EDU
Suggested Products: VORT, to be searched at echidna@munnari.oz.au
Faculty of Engineering, Univ. of Melbourne, Australia
------------------------------
Date: Wed, 31 Mar 93 10:01:05 +0200
From: ahmad@bsun11.zfe.siemens.de (Subutai Ahmad)
Subject: Preprint available: Some Solutions to the Missing Feature Problem in Vision
The following paper is available for anonymous ftp on
archive.cis.ohio-state.edu (128.146.8.52), in directory
pub/neuroprose, as file "ahmad.missing.ps.Z":
Some Solutions to the Missing Feature Problem in Vision
Subutai Ahmad and Volker Tresp
Siemens Central Research and Development
Abstract
In visual processing the ability to deal with missing and noisy
information is crucial. Occlusions and unreliable feature detectors
often lead to situations where little or no direct information about
features is available. However the available information is usually
sufficient to highly constrain the outputs. We discuss Bayesian
techniques for extracting class probabilities given partial data. The
optimal solution involves integrating over the missing dimensions
weighted by the local probability densities. We show how to obtain
closed-form approximations to the Bayesian solution using Gaussian
basis function networks. The framework extends naturally to the case
of noisy features. Simulations on a complex task (3D hand gesture
recognition) validate the theory. When both integration and weighting
by input densities are used, performance decreases gracefully with the
number of missing or noisy features. Performance is substantially
degraded if either step is omitted.
To appear in:
S. J. Hanson, J. D. Cowan, and C. L. Giles (Eds.), Advances in Neural
Information Processing Systems 5. San Mateo CA: Morgan Kaufmann.
Subutai Ahmad
Siemens AG, ZFE ST SN61, Phone: +49 89 636-3532
Otto-Hahn-Ring 6, FAX: +49 89 636-2393
W-8000 Munich 83, Germany E-mail: ahmad@zfe.siemens.de
------------------------------
Date: Fri, 19 Mar 93 15:51:23 -0600
From: Chiun-Hong Chien <chien@superman.jsc.nasa.gov>
Subject: Summer job on parallel vision processing
Lockheed Engineering and Sciences Company has an opening for summer
job. We are looking for a graduate student to work on real time
vision processing for the Extra-vehicular Activities Helper and
Retriver (EVAHR) project; vision-guiding grasping in particular. The
student will be involved in the design and implementation of parallel
algorithms for pose estimation on a Mercury computing system. The
Mercury computing system consists of four i860 processors
interconnected via a 6-way cross bar, and supports physically
distributed shared memory.
The student is expected to have knowledge about computer vision
(including pose-estimation/object-recognition), and strong programming
skill in (MIMD) parallel and distributed processing. Experience with
the Mercury computing system is a plus.
If you are interested in this position, please send your resume
including the names of three references, to
chien@superman.jsc.nasa.gov (preferably in postscript)
or
Dr. C. H. Chien
Intelligent System Dept. C-19
Lockheed Engineering and Sciences
2400 NASA Road 1
Houston, TX 77058
------------------------------
Date: Mon, 22 Mar 1993 23:20:54 GMT
From: gradprog@osceola.cs.ucf.edu (Gradprog Dutton)
Organization: University of Central Florida
Subject: PhD Program in Computer Science, Univ. of Central Florida
INFO ABOUT THE PHD PROGRAM IN COMPUTER SCIENCE, UNIV. OF CENTRAL FLORIDA.
The Department of Computer Science at the University of Central Florida
(Orlando) has several unique opportunities for students interested in a
PhD program. These opportunities are in areas of active research that
include: parallel computation, VLSI, artificial intelligence, computer
vision, graphics, virtual environments and simulation, databases,
computer networks, and design and analysis of algorithms.
The department has 25 full-time faculty members including an endowed chair,
and about 200 graduate students. The department offers a full range of
degree programs and has offered the PhD since 1979. There are several
well-funded labs including a Center for Parallel Computation, a vision lab,
a graphics lab, an AI lab, a VLSI lab, a database lab, and a networking lab.
The department will be housed in state of the art facilities in two years.
In addition to being the nation's center for entertainment technology,
the Orlando area is one of the most advanced high-tech areas in the
South-East, and includes industries such as Martin Marietta, Westinghouse,
AT&T, NCR, the Naval Training Systems Center, NASA Kennedy Space Center,
Harris Corp., and IBM. The department is affiliated with the Central Florida
Research Park. This environment provides graduate students many opportunities
for financial support, in addition to the numerous supported positions
offered by the department through teaching-assistantships and research-
assistantships. A limited number of fellowships are also available to
outstanding students.
For an application or for further information about the PhD program, contact:
e-mail: gradprog@cs.ucf.edu
or TEL: (407)823-2341,
or FAX: (407)823-5419,
or write: The Graduate Chair,
Dept of Computer Science,
University of Central Florida,
Orlando FL 32816
U.S.A.
------------------------------
Date: 29 Mar 1993 20:00:04 GMT
From: sull@uirvli.csl.uiuc.edu (Sanghoon Sull)
Subject: 2nd CFP: Neural networks on shape analysis
Organization: Center for Reliable and High-Performance Computing, University of Illinois at Urbana-Champaign
CALL FOR PAPERS
Progress In Neural Networks
Special Volume on Shape Analysis
Omid M. Omidvar Minsoo Suk
Series Editor Volume Editor
Significant progress has been made recently in shape analysis using
neural networks and the energy minimization concept. Ablex Publishing
Corporation is planning a special volume on "Shape Analysis", scheduled
for this year.
This volume will be a part of "Progress in Neural Networks," an annual
book series reviewing research in modelling, analysis, design and
application of neural networks. The primary aim of this volume is to
present, in a single volume, the most important achievements made on
this important topic, which are otherwise scattered in diverse literature.
Authors are invited to submit original manuscripts detailing recent
progress. Suggested topics include, but are not limited to: shape modelling,
shape estimation, shape recovery, shape representation, shape matching,
surface reconstruction and surface decomposition. Research work utilizing
neural networks directly or based on energy minimization techniques such as
Markov random field, mean field annealing, simulated annealing, graduated
non-convexity algorithms and resistive networks are most welcome.
The paper should be tutorial in nature, self contained and preferably,
but not necessarily, about fifty double spaced pages in length. Please send
electronically (if you prefer, you can send a hardcopy to the address below)
an abstract and an outline to
msuk@ima.enst.fr
by May 30, 1993. The full paper must be submitted by July 31, 1993 to:
Europe USA
Professor Minsoo Suk Professor Omid M. Omidvar
Department IMAGES Computer Science Department
Ecole Nationale Superieure University of District of Columbia
des Telecommunications 4200 Connecticut Ave. N.W.
46, rue Barrault Washington D.C. 20008
75634 PARIS CEDEX 13 Phone: (202)282-7345
FRANCE Fax: (202)282-3677
Fax:33-1-45-81-37-94 email: oomidvar@udcvax.bitnet
email:msuk@ima.enst.fr
------------------------------
Date: Thu, 18 Mar 93 18:20:35 EST
From: Terrance Boult <tboult@division.cs.columbia.edu>
Subject: CVPR information
The IEEE Conference on Computer Vision & Pattern Recognition
Park Central Hotel, 56th St and 7th Ave, New York City, NY
June 15 -- June 17, 1993
Here is some information for CVPR93. You can obtain the full advance program
and registration material (as postscript files) via ftp from cs.columbia.edu
in the /pub/vision/CVPR93 directory (it will be coming in the mail too). This
year's CVPR, offers an exciting array of papers and presentations on topics
including:
- Motion-Based Recognition
- Discontinuity preserving visual recovery
- Capabilities of Active Vision Systems
- Modeling of Shape and Form
- Model-Based Recognition
- Real-Time Systems and Hardware
- Approaches to Recognition
- Stability of Visual Reconstruction
- Navigation
- Scene Recovery
- Range Image Analysis
- Segmentation
- Statistical Approaches to Recovery
- Recognition and Classification of Patterns
- Characteristics of Recognition Strategies
- Inspection, Mapping, Coding and Monitoring
- Determining Parameters of Active Visual Systems
- Low-Level Vision
- Capabilities of Partially Calibrated Systems
- Modeling of Reflectance and Texture
- Recognition: Template \& Image-Model Matching
- Edge Detection
- Motion
- Stereo
- Color
The social side of things will also be exciting. The conference hotel is in
the heart of one of the finest areas of Manhattan -- right across the street
from Carnegie Hall. It is just 3 blocks from Central Park an easy stroll to
any of the major theaters or stores. We have planned activities to make
seeing the Big Apple easy and enjoyable for everyone, including your
significant other and the kids. The banquet will be a combination buffet
dinner and sightseeing cruise around Manhattan. Kosher and vegetarian foods
are included too; it's New York after all. There will also be a dance band
aboard. On the weekend before the meeting there will be organized excursions
in mid-town, possibly including visits to Macy's, Sak's, Tiffany's and
Gucci's; the Metropolitan Museum of Art, Museum of Modern Art and the Natural
Science Museum; the Empire State Building, etc. (Send suggestions/requests to
cvpr_nyc_trips@cs.columbia.edu and we will see what we can do) If there are
other things you want to see, call the information desk at the hotel. Look
for more details elsewhere in this advance program, and for the latest
information check out the files in /pub/vision/CVPR93 which are available from
cs.columbia.edu via anonymous ftp.
Obtain the advance registration from via ftp from cs.columbia.edu
Here are the rates:
Advanced Onsite
Before 5/21/93 (after 5/21/93)
Tutorials (each) member $130 $155
Tutorials (each) nonmember $160 $195
Conference Member $330 $415
Conference Nonmember $430 $535
Conference Student $180 $250
Student Volunteer$^*$ $130 Not available
Extra Banquet Tickets $50
Tutorial registration includes coffee breaks and notes. Conference
registration includes the proceedings, coffee breaks and social functions.
All students will be required to show valid IEEE membership and university
student picture id at the meeting.
$^*$ Student Volunteers do not receive banquet ticket, regular students do.
Student volunteers are required to help out at the meeting and must contact
cvpr@cs.columbia.edu before the meeting. There are a limited number of
student volunteers slots.
HOTEL INFORMATION
Again, ftp the registration form if you like, it has forms for both
the conference and the hotel.
The hotel is:
Park Central Hotel
870 Seventh Avenue
56th and Seventh
New York, NY 10019
(800) 346-1359 or (212) 484-3300
Fax: (212) 484-3374
Reserved rooms will be held until 6pm unless payment is guaranteed by first
night's deposit or an accepted credit card number and signature. All CVPR
reservations must me in by 5pm Friday May 21. Reservations will be accepted
after this date based on availability of accommodations and will be confirmed
at the convention rate.
Rates:
$109 --- Single
$119 --- Double 1 bed
$119 --- Double 2 bed
call --- Suites
No charge for children under 17 years when sharing room with parents.
STUDENT HOUSING
There is a limited amount of student housing available on Columbia's campus.
Columbia is located on the #1 subway line making it a short ride to the
conference hotel. More information and directions are available via ftp.
Student housing must be paid in advance. A non-refundable 15% deposit is
DUE BY APRIL 15, AND FULL PAYMENT BY MAY 15. There is, no ``block'' of rooms,
so their is no guarantee of a room until the deposit is received. There are
two types of rooms: type-1 which are air conditioned suites with 2 or 4
(separate) bedrooms sharing a a living/dining room with TV, a kitchen and
bathroom/shower), and type-2 which are NOT air conditioned and which have a
bathroom/shower and TV lounge shared by 15-20 rooms. All student housing is
co-ed.
The earlier you book the room the better the chance of getting type 1 rooms.
``Grouping" of rooms can be arranged ONLY IF THE REQUESTS are send in the same
package. If you request type one housing and none is left you should let us
know if you want a type 2 instead (with a refund of the difference) or a full
refund.
This ``student'' housing is available as follows:
From -- To Plan Type-1 | Plan Type-2
3pm -- 10am Code Cost | Code Cost
Sat 6/12 -- Sat 6/19 A-t1 $208 | E-t2 $160
Sat 6/12 -- Fri 6/18 B-t1 $178 | F-t2 $137
Sun 6/12 -- Fri 6/18 C-t1 $148 | G-t2 $115
Mon 6/12 -- Fri 6/18 D-t1 $118 | H-t2 $90
Send email to cvpr_student_housing@cs.columbia.edu as soon as possible with
your requests. We reiterate there is no ``block'' of rooms, so their is no
guarantee of a room until the 15% deposit is processed. Send plan choice and a
check, payable in US dollars to Columbia University, to:
CVPR Student Housing c/o T. Boult
450 Comp. Sci Building
Department of Computer Science
Columbia University, NYC NY 10027.
The number of ``student" rooms is rather limited; if you are interested do not
delay, send email today.
TRAVEL, MISC INFO
There is no ``special'' airline, call your travel agent for best prices. NYC
is one of the cheapest airline destinations, and it may pay to shop around a
little. NYC is served by 3 airports: JFK, LaGuardia and Newark (NJ).
There is a shuttle bus (Grayline, Inc.) between the hotel and the area airports
at a cost of $15 (JFK), $12 (LaGuardia) and $17 (Newark). Book your shuttle
by calling 1-800-451-0455 or (212)315-3006 or calling the hotel and asking for
extension 175. If you plan to arrive as a group, a discount can be
prearranged. You can also take a cab, the cost between $25 and $35, can also
be split. For the really budget conscious, there are bus/subway combinations
which only cost 1-3 dollars, get details via ftp.
There is a garage right next to the hotel. A car is not very useful in NYC,
parking is a hassel or is expensive ($\approx$ $10 a day). Consider using
public transportation if you can, otherwise ftp driving_directions.
If you are coming from the east coast, don't forget the train, which is
generally cheaper and sometimes more convenient. Amtrak trains will take you
to 34th st Penn Station NY. From there take a cab to the hotel or take the #1
or A or C line subway's to 59th street and walk (get a local map via ftp if
you like).
For those with children, the hotel does not, unfortunately, have a day care
center. They suggest contacting the Babysitting Guild (212)682-0227, who will
do in-hotel sitting.
If you are interested in theater tickets to a play, a musical, or an opera,
consider booking them now. Popular times for some shows, e.g Les Miserables
and Phantom of the Opera, are nearly sold-out 3-6 months in advance. Call the
hotel and ask for the theater desk (x175). They also book a variety of NYC
sightseeing tours including ones to Liberty and/or Ellis islands.
NOTE: some of the files, described as ftp-able will not exist until closer to
the conference. Sending mail to cvpr@cs.columbia.edu will get a listing of
files the currently available via ftp.
------------------------------
Date: Mon, 29 Mar 1993 20:32:35 -0500
From: "Minas Spetsakis" <minas@cs.yorku.ca>
Subject: Vision Interface Meeting Announcemnet
V I S I O N I N T E R F A C E 9 3
ANNOUNCEMENT
18-21 May 93
York University
Toronto, Ontario
Vision Interface is part of the Graphics Interface/Vision Interface
Conference which is a unique event combining two conferences that present
the latest results in the above two fields. Each conference offers three
days of invited and submitted papers. Participants can attend
presentations in both for a single fee. A banquet and an electronic
theater (90 minutes of the latest in video animation and visualisation)
provide additional opportunities to meet speakers and other attendees for
informal discussion in a social setting.
The conference is being held at York University at the Keele Campus,
4700 Keele str, North York, Ontario. North York is a suburb of Toronto
within the metropolitan area a short ride from downtown Toronto by bus and
subway. Toronto, located on the North Shore of Lake Ontario, is the
biggest city of Canada, renowned for its cosmopolitan atmosphere, its
variety in food, entertainment and shopping. A large array of tourist
attractions can keep you busy for weeks: Royal Ontario Museum,
Kleinburg Museum, Black Creek Pioneer Village, CN tower, Sky Dome,
Canada's Wonderland to name just a few.
Attendees will receive a ticket for the Electronic theater and a ticket
for the banquet in the Black Creek Pioneer Village. Guests may purchase
additional tickets either in advance or at registration desk.
All technical sessions will be held in Vari Hall on the Keele Campus.
There are three invited talks on selected topics of high interest. The
invited talks from VI and GI do not overlap to give the chance to
everybody to attend if they choose.
For more information contact:
Program: brault@vlsi.polymtl.ca or minas@cs.yorku.ca
Registration: davis@cs.ualberta.ca
Accommodation: amana@@cs.yorku.ca
Latest announcements: gi-vi-93@cs.yorku.ca
Registration information and the preliminary program follow.
REGISTRATION INFORMATION
To register in advance (i.e. prior to May 7 1993), complete a printout
of the following form and mail it with your check or money order in
Canadian Funds, to:
GI/VI '93 Registration
Box 1098
Summerland, B.C. V0H 1Z0
Phone (604) 494-9056
Fax (604) 494-4033
e-mail davis@cs.ualberta.ca
CONFERENCE REGISTRATION FORM
Name_____________________________________
Affiliation______________________________
Address__________________________________
City_______________Province_______________
Country_______________Postal Code_______________
Membership Number_______________Society_______________
Conference Registration includes one of the proceedings, one banquet
ticket and one film show ticket.
Early Late Amount
Before Apr. 19 After Apr. 19
Members $240.00 $290.00 ______
Non-Members $280.00 $330.00 ______
Students $110.00 $140.00 ______
Extra Proceedings $40.00 ______
Extra Film show ticket $10.00 ______
Extra Banquet Ticket $40.00 ______
Total Enclosed ______
Proceedings Selected: Graphics_____Vision:_____
If paid in US dollars, fees are reduced by 15%. Withdrawals and
cancellations must be made in writing by May 3 1993 and will be
subject to a cancellation fee of $25.00. After this date no refunds
will be available.
Mail to: GI/VI '93 Registration
BOX 1098
Summerland, B.C. V0H 1Z0
ON-CAMPUS ACCOMMODATION
Name__________________________________________________
Address______________________________________________
______________________________________________
Telephone______________________________________________
Arrival Date___________________ Departure Date__________
Please indicate the number of nights accommodation required______________
Please indicate the name of second person for double occupancy__________
Total number of nights ____x ($45 single or $68 double) = ______________
(taxes included)
Note: All payments must be in CANADIAN FUNDS ONLY
Please indicate the method of payment:
__Visa __Master Card___American Express __Cheque (Payable to York University)
Credit Card Number ___________________________ Expiry Date_______________
Signature_____________________________________
Return with payment in full to:
Hospitality York
York University
4700 Keele St.
North York, Ontario M3J 1P3
Telephone: (416) 736-5020 Fax: (416) 736-5648
OFF-CAMPUS ACCOMMODATION
Rooms have been booked for Graphics/Vision Interface '93 at the
Western Strata Hotel (located approximately 10 minutes drive from
York University. Please contact the hotel directly to make reservations.
The single room rate is $49.95.
Telephone: (416) 665-3500 FAX (416) 665-0807
Toll Free: 1-800-528-1234
PRELIMINARY CONFERENCE PROGRAM
Wednesday 19 May 1993
VISION INTERFACE '93
Time Paper
Session: Modeling
8:30 V. Wu and E. E. Milios, "Color and Shape based tracking".
9:00 B. A. McArthur and A. K. C. Wong, "Optimal common subgraph
isomorphism for model synthesis".
9:30 R. Houde, J. Tremblay, D. Laurendeau and M. Pelletier, "Estimating
the pose of 2D objects using potential functions and quadtrees".
10:00 P. Hebert, D. Laurendeau and D. Poussart, "Surface profile
description: invariant stable extraction of straight line segments".
10:30 Break
11:00 Invited talk: Yiannis Aloimonos, University of Maryland
"Behavioural Visual Motion Analysis".
12:00 Lunch
Session: Image Processing
1:30 D. Milun and D. B. Sher, "Training double neighborhood
Markov random fields by sampling - how much data is required."
2:00 A. Aguado, M. E. Montiel, J. Alarcon and M. Garza-Jinich, "A
pyramidal architecture based on a quadtree storage scheme"
2:30 R. I. Campeanu, "Sampling techniques in the Wiener image
restoration".
3:00 Break
3:30 A. Basu, M. Jain and X. Li, "Variable-resolution techniques for
thinning and boundary detection".
4:00 M. Kamel and L. Guan, "Tree-structured encoder for
vector quantization of image data".
4:30 M. Kamel and Q. Tang, "On improving the performance of
JPEG image compression at low encoding bitrates".
Thursday 20 May 1993
VISION INTERFACE '93
Time Paper
Session: Modeling and Representation
8:30 X. Yuan, "LSP: A view insensitive 3D representing method".
9:00 T. McInerney and D. Terzopoulos, "Finite element
techniques for fitting a deformable model to 3D Data".
9:30 I. Sekita and P. Boulanger, "Simple object extraction and
approximation by rational Bezier surface".
10:00 Break
Session: Robotics
10:30 Y. Liu and D. Laurendeau, "Building a multi-scale surface
model of the workspace of a robot manipulator".
11:00 G. Dudek, M. R. M. Jenkin, E. E. Milios and D. Wilkes.,
"Organizational characteristics for multi-agent robotic systems".
11:30 G. Dudek and P. MacKenzie, "Model-based map construction for robot
localization".
12:00 Lunch
1:30 Invited Talk: Bruce Nickerson, Ontario Hydro
"ARK: Autonomous Robot for a Known Environment"
2:30 Break
Session: Motion and Stereo
3:00 P. Lacourse and P. Pochec, "Stereo matching based on fixed point
theorem".
3:30 J. -F. Methot and D. Poussart, "Fusion of registered 2D intensity
and 3D range data: Application to the differential light
absorption technique".
4:00 D. J. Fleet and K. Langley, "Real-Time Gradient-Based Optical Flow"
4:30 S. D. Blostein and R. M. Chann, "Hybrid feature/flow-based 3D
trajectory estimation".
5:15 Annual meeting of CIPPRS. (Open to all attendees).
Friday 21 May 1993
VISION INTERFACE '93
Time Paper
Session: Pattern Recognition
9:00 M. Kamel and A. Zhao, "Extraction of character/graphics images
from document images with background pictures".
9:30 M. Lalonde and J.-J. Brault, "A neural network approach
to handwritten curve partitioning".
10:00 D. Boulanger and D. Poussart, "Unsupervised neural net
classifier for semantic graphs".
10:30 Break
11:00 Invited talk: Ching Y. Suen, Concordia University
"Pattern Recognition and Expert Systems"
12:00 Lunch
Session: Pattern Recognition
1:30 G. Chow and X. Li, "An automatic facial feature detection
system".
2:00 A. Yoshida and Y. Hongo, "Handprinted Kanji character recognition
by the background feature pattern method using a non-linear
normalization"
2:30 Q. Xiao and H. Raafat, "On a Combined Strategy to Pattern
Recognition".
3:00 X. Yuan, "Mass vector controlled view estimation for automatic 3D
object modeling".
------------------------------
Date: Tue, 30 Mar 1993 14:55:33 GMT
From: rapaport@cs.buffalo.edu (William J. Rapaport)
Organization: State University of New York at Buffalo/Comp Sci
Subject: First International Summer Institute in Cognitive Science
SECOND ANNOUNCEMENT
State University of New York at Buffalo
CENTER FOR COGNITIVE SCIENCE
announces the
FIRST INTERNATIONAL SUMMER INSTITUTE IN COGNITIVE SCIENCE:
Multidisciplinary Foundations of Cognitive Science
to be held at the Amherst Campus of SUNY Buffalo, Buffalo, NY, USA
JULY 5-30, 1994
Robert Van Valin & Barry Smith, Institute Co-Directors
Leonard Talmy, Director of the Center for Cognitive Science
HONORARY SCIENTIFIC COMMITTEE:
Margaret Boden University of Sussex, UK
Charles Fillmore University of California, Berkeley, USA
Charles Frake SUNY Buffalo, USA
Elmar Holenstein ETH Zurich, Switzerland
Philip Johnson-Laird Princeton University, USA
Kevin Mulligan University of Geneva, Switzerland
Dan Slobin University of California, Berkeley, USA
Dan Sperber CREA, Paris, France
David Waltz Thinking Machines, Cambridge, MA, USA
Sandra Witelson McMaster University, Canada
ENDORSING ORGANIZATIONS INCLUDE:
American Association for Artificial Intelligence
Cognitive Science Society
Linguistic Society of America
Society for Machines and Mentality
The Center for Cognitive Science of the State University of New York at
Buffalo will present a four-week summer institute, July 5-30, 1994.
This project represents an important innovation in the Cognitive
Science field; no venture of this type has been attempted before.
The first three weeks of the Institute will be comprised of courses at
basic and advanced levels in constituent disciplines of Cognitive
Science. Courses will be taught by both SUNY Buffalo faculty and
faculty invited from other institutions. The fourth week will then be
devoted to workshops and special conferences. Running through the four
weeks, there will also be a special speaker series of prominent invited
scholars. The Institute will provide an opportunity for many faculty
and students to get an introduction to the field of cognitive science
and to complement courses in their own disciplines at their home
institutions.
It is anticipated that participants will include undergraduate and
graduate students, faculty associates, and researchers from industry
and government. A special effort will be made to recruit students and
participants from outside the United States, where systematic courses
across the range of Cognitive Science disciplines are rarely offered.
Participants may enroll in the courses for academic credit, if desired.
Each course will meet for a total of 15 hours over the three weeks and
will carry 1 semester unit of credit.
TENTATIVE LIST OF COURSES (as of March 1993):
Foundations of Cognitive Science
Introduction to the Anthropological Study of Cognition
Introduction to Artificial Intelligence
Introduction to Cognitive Psychology
Introduction to Cognitive Neuroscience
Introduction to Linguistics in Cognitive Science
Introduction to Philosophy for Cognitive Science
Anthropology of Knowledge Systems
Knowledge Representation
Epistemology
Mental Models
Knowledge of Language: Syntax
Knowledge of Language: Semantics
Natural-Language Understanding
Language Disorders
Cognitive Development
Neurological Development
Linguistic Development
Geographic Organization of Space
Artificial Intelligence and Categorization
Language and Conceptual Structure
Philosophy and Categorization
Psychology of Problem Solving
Reasoning and Artificial Intelligence
Logic
Inference in Conversation, Discourse, and Narrative
Artificial Intelligence Approaches to Perception
Language and Speech Perception
Neuropsychology of Vision
Philosophy and Psychology of Perception
TENTATIVE LIST OF WORKSHOPS, SEMINARS, AND SYMPOSIA (as of March 1993):
Workshop on Connectionism
Evolution of Cognition
The SNePS Knowledge Representation and Reasoning System
Applied Cognitive Science: Cognitive Science in the Work-Place
Narrative and Deixis
Ontology and the Cognition of Space and Time
Bilingualism and Cognition
INVITED SPEAKERS (as of March 1993)
Thomas G. Bever Psychology, Univ. of Rochester
Antonio Damasio (tentative) Neuroscience, Univ. of Iowa
Gilles Fauconnier Linguistics, Univ. of California, San Diego
Jerry Feldman Computer Science, Univ. of California, Berkeley
Janet Dean Fodor Linguistics, CUNY Graduate Center
Jerry Fodor Philosophy, Rutgers Univ. & CUNY Graduate Center
Dedre Gentner Psychology, Northwestern Univ.
Geoff Hinton Computer Science, Univ. of Toronto
Ed Hutchins Anthropology, Univ. of California, San Diego
Ray Jackendoff Linguistics, Brandeis Univ.
Michael Jordan Artificial Intelligence, MIT
Annette Karmiloff-Smith Psychology, Univ. of London, UK
Stephen M. Kosslyn Psychology/Neuroscience, Harvard Univ.
John Searle (tentative) Philosophy, Univ. of California, Berkeley
Michael Silverstein Linguistics/Anthropology, Univ. of Chicago
Brian Cantwell Smith Computer Science, Xerox PARC
Paul Smolensky Computer Science, Univ. of Colorado, Boulder
David Waltz Computer Science, Thinking Machines Corp.
Sandra Witelson Neuroscience, McMaster Univ.
Detailed information on the Institute, including course offerings,
speaker series, workshops, fees, living accommodations, and scholarship
and travel support for students, will be available in summer 1993.
If you wish to receive the Institute brochure, please send your name
and *postal* address (and e-mail address, if available) to either:
Bitnet: cogsci94@ubvms
Internet: cogsci94@ubvms.cc.buffalo.edu
or
1994 Cognitive Science Summer Institute
Center for Cognitive Science
652 Baldy Hall
SUNY Buffalo
Buffalo, NY 14260
USA
(716) 645-3794
(716) 645-3825 (fax)
------------------------------
Date: Thu, 25 Mar 93 06:42:31 GMT
From: schwartz@.LOCAL.nlm.nih.gov (Ray Schwartz)
Organization: National Library of Medicine
Subject: CFP: ASIS SIG/Classification Research Workshop
CALL FOR PARTICIPATION
The American Society for Information Science Special Interest Group on
Classification Research (ASIS SIG/CR) invites submissions for the 4th ASIS
Classification Research Workshop, to be held at the 56th Annual Meeting of
ASIS in Columbus, Ohio. The workshop will take place Sunday, October 24th,
1993, 8:30 a.m. -5:00 p.m. ASIS '93 continues through Thursday, October
28th.
The CR Workshop is designed to be an exchange of ideas among active
researchers with interests in the creation, development, management,
representation, display, comparison, compatibility, theory, and application
of classification schemes. Emphasis will be on semantic classification, in
contrast to statistically based schemes. Topics include, but are not
limited to:
* Warrant for concepts in classification schemes * Concept acquisition *
Basis for semantic classes * Automated techniques to assist in creating
classification schemes * Statistical techniques used for developing
explicit semantic classes * Relations and their properties * Inheritance
and subsumption * Knowledge representation schemes * Classification
algorithms * Procedural knowledge in classification schemes * Reasoning
with classification schemes * Software for management of classification
schemes * Interfaces for displaying classification schemes * Data
structures and programming languages for classification schemes * Image
classification * Comparison and compatibility between classification
schemes * Applications such as subject analysis, natural language
understanding, information retrieval, expert systems *
The CR Workshop welcomes submissions from various disciplines. Those
interested in participating are invited to submit a short (1-2 page single-
spaced) position paper summarizing substantive work that has been conducted
in the above areas or other areas related to semantic classification
schemes, and a statement briefly outlining the reason for wanting to
participate in the workshop. Submissions may include background papers as
attachments. Participation will be of two kinds: presenter and regular
participant. Those selected as presenters will be invited to submit
expanded versions of their position papers and to speak to those papers in
brief presentations during the workshop. All position papers (both expanded
and short papers) will be published in proceedings to be distributed prior
to the workshop. The workshop registration fee is $35.00.
Submissions should be made by email, or diskette accompanied by paper copy,
or paper copy only (fax or postal), to arrive by May 15, 1993, to:
Phil Smith, 210 Baker Systems, 1971 Neil Avenue, Cognitive Systems
Engineering Laboratory, The Ohio State University, Columbus, Ohio 43210;
Phone: 614-292-4120; Fax: 614-292-7852, Internet: Phil+@osu.edu
------------------------------
Date: Mon, 22 Mar 1993 16:05:11 GMT
From: DSPWorld@world.std.com (Amnon Aliphas)
Organization: The World Public Access UNIX, Brookline, MA
Subject: CFP: Int'l Conf. on Signal Proc. Applics. & Technology
CALL FOR PAPERS - ICSPAT '93
International Conference on Signal Processing Applications & Technology
featuring DSP World Expo.
September 28, 1993 - October 1, 1993, Santa Clara Convention Center
Santa Clara, CA
Technical Committee | Application Areas: Aerospace
| Automotive
| Audio
| Communications
Dr. J.B. Evans | Computer Architectures
Univ. of Kansas | Consumer Products
USA | DSP Machines
| DSP Software
Mr. Joel Feldman | DSP Technology
AudioFile, Inc. | Geophysics
USA | Image Processing
| Industrial Control
Dr. Jose Fonollosa | Instrumentation and Testing
ETSE Telecom. | Medical Electronics
Spain | Military Electronics
| Multimedia
Dr. Helmut Gander | Navigation
University of Tech. | Neural Networks
Austria | Parallel Processing
| Radar
Dr. Frank Gao | Speech Processing
GAO Research | Telephony
| Underwater
Mr. John Irza | Video
DSP Associates | VLSI Architectures
| Virtual Reality
Dr. Bruce Musicus |
B.B.N | and other applications
USA |
|
Dr. Tokunbo Ogunfunmi | Mail, Fax, or by send e_mail a 400 word abstract
Santa Clara Univ. | for review, no later than April 30, 1993.
|
Dr. Robert Owen |
Mentor Graphics | to: DSP Associates
USA | 18 Peregrine Road
| Newton, MA 02159
Dr. A. M. Peterson |
Stanford University | Tel: (617) 964-3817 or (617) 964-3195
USA | Fax: (617) 969-6689
|
Dr. Tomo Taniguchi | e_mail: DSPWorld@world.std.com
Fujitsu Lab. |
USA |
Sponsored by: DSP Associates -- Electronic Engineering Times
------------------------------
Date: Mon, 22 Mar 93 15:36:46 AST
From: POCHEC@unb.ca
Subject: CFP: The 5th UNB AI Symposium
Final Call for Participation
The 5th UNB AI Symposium
* Theme: *
* ARE WE MOVING AHEAD? *
August 11-14, 1993
Sheraton Inn, Fredericton
New Brunswick
Canada
ADVISORY COMMITTEE
N. Ahuja, Univ.of Illinois, Urbana
W. Bibel, ITH, Darmstadt
D. Bobrow, Xerox PARC
M. Fischler, SRI
P. Gardenfors, Lund Univ.
S. Grossberg, Boston Univ.
J. Haton, CRIN
T. Kanade, CMU
R. Michalski, George Mason Univ.
T. Poggio, MIT
Z. Pylyshyn, Univ. of Western Ontario
O. Selfridge, GTE Labs
Y. Shirai, Osaka Univ.
PROGRAM COMMITTEE
The international program committee will consist of
approximately 40 members from all main fields of AI and
from Cognitive Science.
We invite researchers from the various areas of Artificial
Intelligence, Cognitive Science and Pattern Recognition,
including Vision, Learning, Knowledge Representation and
Foundations, to submit articles which assess or review the
progress made so far in their respective areas, as well as
the relevance of that progress to the whole enterprise of
AI. Other papers which do not address the theme are also
invited.
FEATURE
Four 70 minute invited talks and five panel discussions are
devoted to the chosen topic: "Are we moving ahead: Lessons
from Computer Vision." The speakers include (in
alphabetical order)
* Lev Goldfarb
* Stephen Grossberg
* Robert Haralick
* Tomaso Poggio
Such a concentrated analysis of the area will be undertaken
for the first time. We feel that the "Lessons from Computer
Vision" are of relevance to the entire AI community.
INFORMATION FOR AUTHORS
NOW: Fill out the form below and email it.
March 30, 1993:
--------------
Four copies of an extended abstract (maximum of 4 pages
including references) should be sent to the conference
chair.
May 15, 1993:
-------------
Notification of acceptance will be mailed.
July 1, 1993:
-------------
Camera-ready copy of paper is due.
Conference Chair: Lev Goldfarb
Email: goldfarb@unb.ca
Mailing address:
Faculty of Computer Science
University of New Brunswick
P. O. Box 4400
Fredericton, New Brunswick
Canada E3B 5A3
Phone: (506) 453-4566
FAX: (506) 453-3566
Symposium location
The symposium will be held in the Sheraton Inn, Fredericton
which overlooks the beautiful Saint John River.
IMMEDIATE REPLY FORM
====================
(please email to goldfarb@unb.ca)
I would like to submit a paper.
Title:
I would like to organize a session.
Title:
Name:
Department:
University/Company:
Address:
Prov/State:
Country:
Telephone:
Email:
Fax:
------------------------------
Date: Mon, 29 Mar 93 23:17:52 GMT
From: Farzin Deravi <eederavi@pyr.swan.ac.uk>
Subject: Hough Transforms - a colloquium
HOUGH TRANSFORMS
A Colloquium
Organized by
Professional Group E4 (Image Processing and Vision)
of the
Institution of Electrical Engineers
to be held at
Savoy Place, London
on
Friday, 7 May 1993
PROVISIONAL PROGRAMME
Presentations will cover research into Hough transforms and related
techniques for pattern recognition in digital images and other multi-
dimensional signals. Significant advances have been made in this area
in recent years, with the development of efficient algorithms, parallel
hardware implementations and novel applications. The Colloquium aims
to bring together researchers active in all of the above three areas
of algorithms, architecture and applications.
9.30am Registration and coffee
Chairman: Dr F Deravi (Univerity of Wales, Swansea)
REGISTRATION & Installation of Posters
10.00 "Which Hough? A Buyer's Guide to the Hough Transform?":
Violet Leavers (University of London, King's College)
10.20 "Some methods for minimising computation with the Hough transform":
E R Davies (University of London, RHBNC)
10.40 "Methods for Improving Line Parameter Accuracy in a Hough Transform
Algorithm": P L Palmer, J Kittler and M Petrou (University of Surrey)
11.00 "A Hough Transform with Integral Kalman Filter Refinement":
C Xu and S A Velastin (University of London, King's College)
11.20 "Using Phase to Represent Radius in the Coherent CircleHough Transform":
T J Atherton and D J Kerbyson (University of Warwick)
11.40 "Object Location: Hough-based schemes versus graph matching":
E R Davies, (University of London, RHBNC)
12.00 LUNCH - Available at the IEE (and poster session)
2.00pm "Recognition by Adaptive Subdivision of Transformation Space (RAST)
Practical Experiences and Comparisons with the Hough Transform":
Thomas M Breuel (IDIAP Switzerland)
2.20 "A Software Testbed for Hough-Transform Algorithms":
A R Hare and M B Sandler (University of London, King's College)
2.40 "The Hough Transform - A Fine Grain Algorithm for Mesh Connected
Processors": D Krishnaswamy, V Govindan, C Nagendra, (Syracuse
University, USA)
3.00 "Finding Axes of Symmetry in a rho-sigma Parameter Space":
T P Pridmore (Sheffield Hallam University)
3.20 TEA
3.40 "Recognition and location of shapes in the Hough parameter space":
P K Sinha, F-Y Chen, R E N Horne (University of Reading)
4.00 "Motion Estimation Based on Hough Transforms":
C Collet (Ecole Navale, Brest, France)
4.20 "A Hough Transform Based Algorithm for Motion Segmentation and
Estimation": M Bober and J Kittler (University of Surrey)
4.40 DISCUSSION
4.50 CLOSE
POSTERS
"Compressing the Parameter Space of the Generalised Hough Transform":
A D H Thomas (University of Wales, Swansea)
"Corner and Curve Detection along a Boundary Using Line Segment Triangles":
A J Pritchard, S J Sangwine, R E N Horne (University of Reading)
"A Weighted Mahalanobis Distance Hough Transform and its Application for the
Detection of Circular Segments":
C Xu and S A Velastin (University of London)
"Fast recognition on general processor using moment invarients":
P K Sinha and F-Y Chen (University of Reading)
"2D shape reconstruction from the Hough Transform":
T Hanif and M B Sandler, (University of London, King's College)
"Circle, elipse and parabola parameterisation using integral transforms":
C J Hinton and J F Boyce (University of London, King's College)
REGISTRATION
For further information and registration please contact:
Kathleen Ford
Groups Officer
Electronics Division
IEE
Savoy Place
London WC2R 0BL
United Kingdom
Tel: +44 71 240 1871
fax: +44 71 497 3633
------------------------------
Date: Wed, 24 Mar 1993 14:09:26 -0500
From: "Michael Jenkin" <jenkin@cs.yorku.ca>
Subject: International Conference on Binocular Stereopsis and Optic Flow
June 22 - June 26, 1993
York University,
Toronto, Canada
Registration:
Name:
Address:
Tel. No & E-mail:
Faculty & Others $60 CDN ($52 US) $____________
Students $30 CDN ($26 US) $____________
Banquet June 24th $35 CDN ($30 US) $____________
Total enclosed* $____________
Deduct $5 from the registration fee is paid before May 15th
College Accommodation:
I will require the following accommodation (no deposit required). In
the colleges of York University at $40 single per night with shared
facilities or $60 double with shared facilities. Prices include all
taxes.
College single College double**
Tuesday June 22nd __________ __________
Wednesday June 23rd __________ __________
Thursday June 24th __________ __________
Friday June 25th __________ __________
Saturday June 26th __________ __________
Hotel Accommodation:
Is available at the nearby Hotel Strata - $54 per night for single
room or $57 per night for a double room. Prices include all taxes and
a continental breakfast. For hotel reservations please call Chris or
Irv at (416)-665-3500 or Fax (416)-665-0807.
Posters:
Please submit a title and abstract (about 100 words) before April 30th.
Please return this form to:
Teresa Manini
103 Farquharson Building
York University
North York, Ontario M3J 1P3
Canada
Tel (416) 736 5659 Fax (416) 736 5857 E-mail manini@hpl.ists.ca
*Registration and banquet fees should be in Canadian dollars (or US
equivalent) by Check or Money Order payable to York University.
**Limited number of rooms, first come first serve basis.
Binocular Stereopsis and Optic Flow
Provisional Programme
Tuesday June 22 6:00 to 10:00 pm. Reception Buffet and Registration
Wednesday June 23
Theoretical analysis of optic flow
9:00 Invariant properties of the optic flow field
J. J. Koenderink, Univ of Utrecht
9:40 Local and global analysis of optic flow
K. Nakayama, Harvard University
10:00 Computing optic flow
S. Ullman, M.I.T.
10:20 Coffee break
Optic flow and heading
11:00 Control of walking from optic flow
W. Warren, Brown University
1140 Computational aspects of motion perception
V. Torre, University of Genoa
12:00 Recovering heading from visual motion
E. Hildreth, Wellesley College
12:20 Lunch
Structure from motion
2:00 Spatio-temporal integration in optic flow
J. Todd, Ohio State University
2:40 Perceiving shape from motion
J. Lappin, Vanderbilt University
3:00 Depth and velocity in structure from motion
M. Braunstein, Univ of Cal, Irvine
3:20 Coffee break and posters
Motion in depth
4:40 Motion in depth
D. Regan, York University
5:20 Stereoscopic motion in depth
A. Parker University of Oxford
5:40 Time-to-contact neurons in pigeon brain
B. Frost, Queens University
Thursday June 24
Eye movements and stereoscopic vision
9:00 Binocular correspondence
W. van de Grind, Univ of Utrecht
9:00 Vergence and rules of dichoptic matching
I. Howard, York University
9:40 Cyclotorsion and stereopsis
J. Enright, Scripps Institute, San Diego
10:00 Coffee break
10:20 Proximal vergence and accommodation
C. Schor, Uni of Cal,Berkeley
11:00 Eye movements and binocular stereopsis
C. Erkelens, University of Utrecht
11:20 Vergence control in machine vision
J-O. Eklundh, Stockholm University
11:40 Lunch
1:00 Poster session
Stereoscopic processing
3:00 Multiple channels in stereo processing
C. Tyler, Smith-Kettlewell Institute
3:40 Stereo matching and dichoptic masking
S. McKee, Smith-Kettlewell Institute
4:00 Stereoscopic acuity
G. Westheimer, Univ of Cal, Berkeley
6:00 Banquet
Friday June 25
Computation of disparity
9:00 Computing binocular disparity
J. Mayhew, Sheffield University
9:40 Computing 3-D shape from disparity
J. Malik, Univ of Cal, Berkeley
10:00 Computing disparities from phase
M. Jenkin, York University
10:20 Coffee break
Physiology of stereopsis and optic flow
11:00 Physiology of binocular stereopsis
R. Freeman, Univ of Cal, Berkeley
11:40 Motion and disparity-sensitive cortical cells
G. Orban, University of Leuven
12:20 Lunch
The concept of disparity
2:00 The concept of binocular disparity
B. Rogers, Oxford University
2:40 Modulation of stereo by perspective
B. Gillam, University of Sydney
3.00 Binocular vision and spatial scale
H. Wilson, University of Chicago
3:20 Coffee break
3:40 General discussion
Discussants B. Julesz and R. Gregory
5:00 Social evening
Saturday June 26
Binocular vision and rivalry
9:00 Binocular rivalry and stereopsis
R. Blake, Vanderbilt University
9:40 Binocular rivalry and interocular transfer
J. Wolfe, Harvard University
10:00 Stereopsis and visual direction
H. Ono, York University
10:20 Coffee break
Interactions between depth cues
11:00 Integrating stereopsis with perspective
K. Stevens, University of Oregon
11:40 Stereo and texture interactions
J. Frisby, Sheffield University
12:00 Specularity, texture and stereo
H. Bulthoff, University of Tubingen
Sponsored by:
NATO as an Advanced Research Workshop
The Institute for Space and Terrestrial Science, York University
------------------------------
Date: Wed, 24 Mar 1993 12:45:28 -0800
From: aar@kaleida.com
Subject: CFP: Digital Video Compression and Processing on Personal Computers
CALL FOR PAPERS
DIGITAL VIDEO COMPRESSION AND PROCESSING ON PERSONAL COMPUTERS:
ALGORITHMS AND TECHNOLOGIES
Part of IS&T/SPIE Symposium on Electronic Imaging: Science & Technology
San Jose Convention Center, San Jose, California, February 6-10, 1994
Rapid continual advances in computer technologies coupled with the
availability of high-volume data storage devices have effected the advent
of multimedia applications in desktop computers and workstations. As
emerging technologies set higher performance levels, much emphasis is being
placed on enabling low-cost computer platforms with digital video playback
capabilities. Digital video data poses many challenges due to its inherent
high bandwidth and storage requirements.
This conference brings together practitioners and researchers working in
all facets of digital video implementations on desktop computers and
low-cost workstations. The conference will serve as a forum for exchange
of video codec implementations. Presenters will be encouraged to
demonstrate their digital video solutions on any desktop computer or
low-cost workstation. Papers on video and image processing techniques
employed in video editing are also welcomed. This conference will allow
participants to appreciate the scientific concepts behind technologies that
work on desktop computers and low-cost workstations, and to understand the
compromises required with constraints on numerical resources.
Papers are solicited in all areas of digital video implementations on
desktop computers and low-cost workstations, including, but not limited to:
* Video codec algorithms amenable to software-only playback in personal
computers:
- asymmetrical compression techniques based on statistical data analysis,
image analysis, fractals, or vector quantization
- frame-differencing techniques
- decoding techniques to facilitate software-only playback
- design of video stream syntax for software-only playback
* Decoder optimization
* Frame-rate scalability techniques
* Hierarchical encoding schemes and frame resolution scalability techniques
- wavelets
- sub-band coding
- pyramids
* Model based image coding
* Displaying schemes:
- real-time dithering and error-diffusion techniques
- real-time palette-to-palette translation techniques
- real-time color space conversion techniques
* MPEG
- software or hardware implementations
- rapid block motion estimation techniques
- block matching criteria
- pre-processing and image analysis techniques to control scalar
quantization
- post-processing and image enhancement methods
* Motion JPEG implementations
* Motion JPEG to MPEG conversions
* Low bit rate video coding (less than 100 Kilobits per second)
* Very low bit rate video coding (less than 10 Kilobits per second)
* Bandwidth control techniques:
- mapping threshold adjustment to bandwidth control
* Image and video processing techniques for video editing, including morphing,
cropping, fading, scaling, and background accentuation/de-accentuation
* Scene change detection
* Studies on perceptual quality and bandwidth tradeoffs by varying color depth,
frame resolution, and frame rate
* Psychovisual studies of detection of motion JPEG and MPEG artifacts
Papers describing case studies of digital video codec algorithms and/or
technologies, and system integration issues will be also welcomed.
Conference Chair:
Arturo A. Rodriguez, Kaleida Labs
Program Committee:
Walter Bender, MIT Media Lab
Alan C. Bovik, University of Texas
Jerome R. Cox, Jr., Washington University
Edward J. Delp, Purdue University
Paul Farrelle, Optivision
Edward A. Fox, Virginia Tech
Ehud D. Karnin, IBM Haifa Scientific Center
Ken Morse, Kaleida Labs
James O. Normile, Apple Computer
P. Venkat Rangan, University of California, San Diego
K. R. Rao, University of Texas at Arlington
Lawrence A. Rowe, University of California, Berkeley
Arthur J. Stein, IBM Watson Research Center
Eric Viscito, IBM Watson Research Center
INSTRUCTIONS FOR AUTHORS
Each paper will be reviewed by members of the program committee.
The deadline for paper submissions is 12 July 1993. Please submit
four copies by mail, or one copy by email or fax, of a 500 word (or
greater) summary and other requested information to:
IS&T/SPIE EI94
Digital Video Compression and Processing on Personal Computers
P.O. Box 10
Bellingham, WA 98227-0010 USA
Shipping address: 1000 20th St., Bellingham, WA 98225
Telephone: (206) 676-3290
Telefax: (206) 647-1445
Internet abstracts@mom.spie.org
Please include the following information:
1. Title of Paper
2. Authors' full names, affiliations, address, phone, fax and email
3. Include a sentence indicating that the paper is intended for Digital
Video Compression and Processing on Personal Computers.
4. Summary text (500 words or greater)
5. Authors' Biographies
The Conference Chair and Program Committee will select the best papers of
the conference. Authors of the best papers will be invited to make journal
form submissions for a special issue of the journal, Multimedia Systems,
devoted to the theme of the conference. Multimedia Systems is an international
journal jointly published by ACM and Springer-Verlag.
Arturo A. Rodriguez, Ph.D.
Kaleida Labs, 1945 Charleston Road, Mt. View, CA 94043
internet: aar@kaleida.com ph: (415) 966-0866
------------------------------
Date: Wed, 24 Mar 93 18:00:30 -0600
From: Bikash Sabata <bsabata@zeus.ee.utexas.edu>
Subject: List of references for non-rigid motion (LONG)
Hello everyone,
Here is the final list of the references for non-rigid motion. I would like
to thank Denis Friboulet, Amir Amini and K. Chandrasekhar for helping me in
collecting the references. Please let me know if I have missed out on any
paper or if you detect any errors.
Thanks
Bikash Sabata
Computer and Vision Research Center,
The University of Texas at Austin,
e-mail: bsabata@zeus.ee.utexas.edu
*****************************************************************************
[1] A. A. Amini and J. S. Duncan,
"Pointwise tracking of left-ventricular motion in 3d," in Proceedings
of the IEEE Workshop on Visual Motion, (Princeton, NJ), pp.
294-299, Oct. 1991.
[2] A. Amini, R. Owen, P. Anandan, and J. S. Duncan,
"Non-rigid motion models for tracking the left ventricular wall," in
Lecture notes in Computer Science : Information processing in Medical
Images (A. Colchester and D. Hawkes,eds.), pp. 343-357,
Springer-Verlag, 1991.
[3] A. A. Amini and J. S. Duncan,
"Bending and stretching models for lv wall motion analysis from
curves and surfaces," Image and Vision Computing, vol. 10, pp.
418-430, July/August 1992.
[4] M. Asada, M. Yachida, and S. Tsuji,
"Understanding of 3d motion in block world," Pattern Recognition,
vol. 17, no. 1, pp. 57-84, 1984.
[5] D. H. Ballard and C. M. Brown, Computer Vision. Prentice-Hall, 1982.
[6] D. Baraff and A. Witkin,
"Dynamic simulation of non-penetrating flexible bodies," in SIGGRAPH,
pp. 303-308, 1992.
[7] A. H. Barr,
"Superquadrics and angle-preserving transformations," IEEE Computer
Graphics and Applications, vol. 18, pp. 21-30, Jan 1981.
[8] A. Barr,
"Global and local deformations of solid primitives," in SIGGRAPH, pp.
21-31, 1984.
[9] A. Barr, B. Currin, S. Gabriel, and J. Hughes,
"Smooth interpolation of orientations with angular
relocity constraints using quaternions," in SIGGRAPH, pp. 313-320,
1992.
[10] K. Bartels, A. Bovik, S. Aggarwal, and K. Diller,
"Shape change analysis of confocal microscope images using
variational techniques," in SPIE Vol. 1660: Biomedical Image
Processing and Three Dimensional Microscopy, (San Hose, CA), pp.
618-629, Feb. 1992.
[11] T. Beier and S. Neely,
"Feature-based image metamorphosis," in SIGGRAPH, pp. 35-42, 1992.
[12] B. M. Bennett and D. D. Hoffman,
"The computation of structure from fixed axis motion: non rigid
structures," Biological Cybernetics, pp. 293-300, 1985.
[13] R. M. Bolle and B. C. Vemuri,
"On three-dimensional surface reconstruction methods," IEEE Trans-
actions on Pattern Analysis and Machine Intelligence, vol. 13, no. 1,
1991.
[14] F. L. Bookstein,
deformations," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 11, pp. 567-585, June 1989.
[15] T. Boult and A. Gross,
"Recovery of superquadrics from 3-d information," in Proc. Spatial
Reasoning and Multi-Sensor Fusion Workshop, (St. Charles, IL), pp.
128-137, 1987.
[16] H. I. Bozma and J. S. Duncan,
"Model-based recognition of multiple deformable objects using a game-
theoretic framework," in Proc. of 12'th International Conference,
IPMI'91, (Wye, UK), pp. 358-372, July 1991.
[17] B. Bruno, N. Bennett, K. Bowyer, D. Goldgof, and L. Stark,
"Modeling of articulated objects for machine perception," in Proc.
of 5'th Florida AI Research Symposium, (Ft. Lauderdale, Florida),
pp. 247-251, 1992.
[18] S. Chaudhuri and S. Chatterjee,
"Estimation of motion parameters for a deformable object from range
data," in Proc. of IEEE Computer Society Conference on Computer
Vision and Pattern Recognition,
pp. 291-295, 1989.
[19] S. Chaudhuri and S. Chatterjee,
"Motion analysis of a homogeneously deformable object using subset
correspondences," Pattern Recognition, vol. 24, pp. 739-745, 1991.
[20] S. S. Chen,
"Structure-from-motion without the rigidity assumption," in
Proceedings of the Third Workshop on Computer Vision: Representation
and Control, (Bellaire, MI), pp. 105-112, 1985.
[21] S. Chen and M. Penna,
"Recognizing deformations of nonrigid bodies," in Proc. of IEEE
Computer Society Conference on Computer Vision and Pattern
Recognition, pp. 452-455, 1986.
[22] S. Chen and M. Penna,
"Shape and motion of nonrigid bodies," Computer Vision, Graphics, and
Image Processing, vol. 36, pp. 175-207, 1986.
[23] S. S. Chen and M. Penna,
"Motion analysis of deformable objects," in Advances in Computer Vision
and Image Processing (T. S. Huang, ed.), ch. 3, JAI Press, 1988.
[24] S.-S. Chen and A.-G. Zhao,
"Image representation of moving nonrigid objects," Journal of Visual
Communication and Image Representation, vol. 1, pp. 199-207, 1990.
[25] C. W. Chen and T. S. Huang,
"Analysis of left ventricle global deformation based on dynamic ct
data," in Proc. of 11th IAPR International Conference on Pattern
Recognition, (The Hague, The Netherlands), pp. 443-446, 1992.
[26] C. W. Chen and T. S. Huang,
"Nonrigid object motion and deformation estimation from
three-dimensional data," International Journal of Imaging Systems and
Technology, vol. 2, pp. 385-394,
1990.
[27] R. Cipolla and A. Zisserman,
"Qualitative surface shape from deformation of image curves," Inter-
national Journal of Computer Vision, vol. 8, pp. 53-69, 1992.
[28] R. Cipolla and A. Blake,
"Surface shape from deformation of apparent contours,"
International Journal of Computer Vision, vol. 9, pp. 83-112, 1992.
[29] R. Cipolla and A. Blake,
"Surface orientation and time to contact from image divergence and
deformation," in ECCV, pp. 187-202, 1992.
[30] I. Cohen, N. Ayache, and P. Sulger,
"Tracking points on deformable objects using curvature information,"
in Proc. of the second European Conference on Computer Vision,
(Santa Margherita Ligure, Italy), pp. 458-466, 1992.
[31] L. D. Cohen and I. Cohen,
"Deformable models for 3D medical images using finite elements and
baloons," in Proc. of IEEE Computer Society Conference on Computer
Vision and Pattern Recognition, pp. 592-598, 1992.
[32] S. Coquillart and P. Jancene,
"Animated free-form deformation: An interactive animation technique,"
in SIGGRAPH, pp. 23-26, 1991.
[33] T. E. Dietz, K. R. Diller, and J. K. Aggarwal,
"Automated computer evaluation of time-varying
cryomicroscopical images," Cryobiology, vol. 21, pp. 200-208, 1984.
[34] J. Duncan, R. Owen, L. Staib, and P. Anandan,
"Measurement of non-rigid motion using contour shape descriptors," in
Proc. of IEEE Computer Society Conference on Computer Vision and
Pattern Recognition, pp. 318-324, 1991.
[35] K. Fujimura, N. Yokoya, and K. Yamamoto,
"Motion tracking of deformable objects based on energy minimization
using multiscale dynamic programming," in
International Conference on Pattern Recognition, pp. 83-86, 1992.
Vol. A.
[36] P. Georgiades and D. Greenberg,
"Locally manipulating the geometry of curved surfaces," IEEE
Computer Graphics and Applications, vol. 12, no. 1, pp. 54-64, 1992.
[37] D. B. Goldgof, T. S. Huang, and H. Lee,
"Feature extraction and terrain matching," in Proc. of IEEE
Computer Society Conference on Computer Vision and Pattern Recognition,
pp. 899-904, May 1988.
[38] D. B. Goldgof, H. Lee, and T. S. Huang,
"Motion analysis of nonrigid surfaces," in Proc. of IEEE
Computer Society Conference on Computer Vision and Pattern Recognition,
pp. 375-380, 1988.
[39] D. B. Goldgof, H. Lee, and T. S. Huang,
"Parameter estimation of the heart motion from angiography
data," in Proc. of SPIE/SPSE Symposium on Electronic Imaging,
Conference on Biomedical Image Processing, (Santa Clara, California),
pp. 171-181, Feb. 1990.
[40] D. B. Goldgof and C. Kambhamettu,
"Application of the nonrigid shape matching algorithm to
volumetric cardiac images," in Proc. of SPIE/SPSE Symposium on
Electronic Imaging, Conference on Biomedical Image Processing, 1991.
SPIE vol. 1450.
[41] J. Gourret, N. M. Thalmann, and D. Thalmann,
"Simulation of object and human skin deformations
in a grasping task," in SIGGRAPH, pp. 21-30, 1989.
[42] W. C. Graustein, Differential Geometry. MacMillan, New York, 1935.
[43] A. Gross and T. Boult,
"Error of fit measurements for recovering parametric solids,"
in Proc. of IEEE Conference on Computer Vision, pp. 690-694, 1988.
[44] U. Gudukbay and B. Ozguc,
"Free-form solid modeling using deformations," Computers and Graph-
ics, vol. 14, pp. 491-500, 1990.
[45] A. Gupta and R. Bajcsy,
"An integrated approach for surface and volumetric segmentation of
range images using biquadrics and superquadrics," in SPIE Proc.
Applications of AI X: Machine Vision and Robotics, (Orlando, FL),
1992. volume 1708.
[46] S. Han, D. B. Goldgof, and K. W. Bowyer,
"Using hyperquadrics for shape recovery from range data,"
in Proc. of 4th International conference on computer vision, (Berlin,
Germany), 1993. in press.
[47] A. J. Hanson,
"Hyperquadrics: Smoothly deformable shapes with convex polyhedral
bounds," Computer Vision, Graphics, and Image Processing, vol. 44,
pp. 191-210, 1988.
[48] I. L. Herlin, C. Nguyen, and C. Graffigne,
"A deformable region model using stochastic processes
applied to echocardiographic images," in Proc. of IEEE Computer Society
Conference on Computer Vision and Pattern Recognition, pp. 534-539,
1992.
[49] D. D. Hoffman and B. E. Flinchbaugh,
"The interpretation of biological motion," Biological Cybernetics,
pp. 195-204, 1982.
[50] R. Holt and A. Netravali,
"Motion of nonrigid objects from multiframe comparison,"
Journal of Visual Communication and Image Representation, vol. 3,
pp. 255-271, 1992.
[51] B. Horowitz and A. Pentland,
"Recovery of non-rigid motion and structure," in Proc. IEEE Conf.
on Computer, pp. 288-293, June 1991.
[52] B. Horowitz and A. Pentland,
"Recovery of non-rigid motion and structure," in Proc. of IEEE
Computer Society Conference on Computer Vision and Pattern Recognition,
pp. 325-330, 1991.
[53] W. Hsu, J. Hughes, and H. Kaufman,
"Direct manipulation of free-form deformations," in SIGGRAPH,
pp. 177-184, 1992.
[54] T. S. Huang,
"Motion analysis," in Encyclopedia of Artificial Intelligence, Vol. 1
(S. C. Shapiro, ed.), pp. 620-632, New York: Wiley, 1987.
[55] T. S. Huang,
"Modeling, analysis, and visualization of nonrigid object motion," in
Proceedings of 10th International Conference on Pattern Recognition
(ICPR), vol. 1, (Atlantic City, NJ), pp. 361-364, June 1990.
[56] W. Huang and D. B. Goldgof,
"Adaptive-size physically-based models for nonrigid motion analy-
sis," in Proc. of IEEE Computer Society Conference on Computer Vision
and Pattern Recognition, (Urbana, Illinois), pp. 833-835, June 1992.
[57] W.-C. Huang and D. B. Goldgof,
"Sampling and surface reconstruction with adaptive-size meshes,"
in Applications of Artificial Intelligence X: Machine Vision and
Robotics, (Orlando, Florida), April 1992.
[58] W.-C. Huang and D. B. Goldgof,
"Qualitative vision using non-linear finite element modeling,"
in Proc. of SPIE/SPSE Symposium on Electronic Imaging,
Conference on Geometric Methods in Computer Vision, (San Diego,
California), July 1993. in press.
[59] W.-C. Huang and D. B. Goldgof,
"Adaptive-size meshes for rigid and nonrigid shape analysis and
synthesis," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 15, Mar. 1993.
[60] C. J. Jacobus, R. T. Chien, and J. M. Selander,
"Motion detection and analysis of matching graphs of
intermediate-level primitives," IEEE Transactions on Pattern Analysis
and Machine Intelligence, vol. PAMI-2, pp. 495- 510, Nov. 1980.
[61] R. Jain and I. K. Sethi,
"Establishing correspondence of non-rigid objects using smoothness of
motion," in Workshop on computer vision: Representation and Control,
pp. 83-87, 1984.
[62] R. Jasinschi and A. Yuille,
"Nonrigid motion and regge calculus," Journal of the Optical Society of
America, vol. A6, pp. 1088-1095, 1989.
[63] R. Cameron-Jones,
"Visual interpretation of lambertian surface deformation," in
International Joint Conference on Artificial Intelligence, pp.
1299-1304, 1991.
[64] C. Kambhamettu and D. B. Goldgof,
"Towards finding point correspondences in non-rigid motion,"
in Proc. of the 7'th Scandinavian Conference on Image Analysis, pp.
1126-1133, 1991.
[65] C. Kambhamettu and D. B. Goldgof,
"Point correspondence recovery in nonrigid motion," in Proc. of
IEEE Computer Society Conference on Computer Vision and Pattern
Recognition, (Urbana, Illinois), pp. 222-227, 1992.
[66] K. Chandra and D. B. Goldgof,
"Estimating point correspondences in small deformations," Tech.
Rep. TR. 93-01, Department of Computer Science and Engineering,
University of South Florida, 1993.
[67] C. Kambhamettu, D. B. Goldgof, D. Terzopoulos, and T. S. Huang,
"Nonrigid motion analysis," in
Handbook of PRIP: Computer Vision (T. Young, ed.), vol. 2, Academic
Press, 1993. To be Published.
[68] M. Kass, A. Witkin, and D. Terzopoulos,
"Snakes: Active contour models," in Proc. of IEEE Conference on
Computer Vision, 1987.
[69] M. Kass, A. Witkin, and D. Terzopoulos,
"Snakes: Active contour models," International Journal of
Computer Vision, vol. 1, no. 4, pp. 321-331, 1987.
[70] A. Kaul and J. Rossignac,
"Solid-interpolating deformations: Construction and animation of
pips," Computers and Graphics, vol. 16, pp. 107-115, 1992.
[71] J. Kent, W. Carlson, and R. Parent,
"Shape transformation for polyhedral objects," in SIGGRAPH,
pp. 47-54, 1992.
[72] D. Keren, D. Cooper, and J. Subrahmonia,
"Describing complicated objects by implicit polynomials,"
Tech. Rep. TR lems-102, Division of Eng., Brown University, Feb. 1992.
[73] J. J. Koenderink and A. J. V. Doorn,
"The singularities of the visual mapping," Biological Cybernetics,
vol. 24, pp. 51-59, 1976.
[74] J. J. Koenderink and A. J. V. Doorn,
"The internal representation of solid shape with respect to
vision," Biological Cybernetics, vol. 32, pp. 211-216, 1979.
[75] J. J. Koenderink,
"Shape from motion and bending deformation," Journal of
Optical Society of America, vol. A1, pp. 1265-1266, 1984.
[76] J. J. Koenderink and A. J. van Doorn,
"Depth and shape from different perspective in the presence
of bending deformations," Journal of the Optical Society of America,
vol. 3, Feb. 1986.
[77] J. J. Koenderink and A. J. V. Doorn,
"Dynamic shape," Biological Cybernetics, vol. 53, pp. 383-396,
1986.
[78] J. J. Koenderink, Solid Shape. Cambridge, MA: MIT Press, 1990.
[79] C. Lee, O. Hasegawa, W. Wongwarawipat, H. Dohi, and M. Ishizuka,
"Realistic image synthesis of a deformable living thing based on
motion understanding," Journal of Visual Communication and
Image Representation, vol. 2, pp. 345-354, 1991.
[80] C.-W. Liao and G. Medioni,
"Representation of range data with b-spline surface patches," in Proc.
of 11th IAPR International Conference on Pattern Recognition,
(The Hague, The Netherlands), pp. 745-748, Aug. 1992.
[81] A. Matheny,
"The use of three- and four-dimensional surface harmonics for rigid
and non-rigid shape recovery and representation," Master's thesis,
University of South Florida, Department of Computer Science and
Engineering, April 1993.
[82] T. McInerney and D. Terzopoulos,
"A finite element model for 3d shape reconstruction and nonrigid
motion tracking," in Proc. Fourth International Conf. on
Computer Vision (ICCV'93), (Berlin, Germany), 1993. in press.
[83] D. Metaxas and D. Terzopoulos,
"Recursive estimation of shape and nonrigid motion," in Proc. IEEE
Workshop on Visual Motion, pp. 306-311, Oct. 1991.
[84] D. Metaxas and D. Terzopoulos,
"Shape and nonrigid motion estimation through physics-based syn-
thesis," in Proc. IEEE Computer Vision and Pattern Recognition
Conference (CVPR'91), (Hawaii), pp. 337-343, June 1991.
[85] D. Metaxas and D. Terzopoulos,
"Constrained deformable superquadrics and nonrigid motion tracking,"
in Proc. of IEEE Computer Society Conference on Computer Vision
and Pattern Recognition, pp. 337-343, 1991.
[86] D. Metaxas and D. Terzopoulos,
"Dynamic deformation of solid primitives with constraints," in
SIGGRAPH, pp. 309-312, 1992.
[87] D. Metaxas and D. Terzopoulos,
"Shape and nonrigid motion estimation through physics-based
synthesis," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 15, 1993. in press.
[88] E. Milios,
"Recovering shape deformation by an extended circular image
representation," in Proc. of IEEE Conference on Computer Vision, pp.
20-29, 1988.
[89] S. K. Mishra and D. B. Goldgof,
"Motion analysis and modeling of epicardial surfaces from point
and line correspondences," in Proc. IEEE Workshop on Visual Motion,
(Princeton, NJ), pp. 300-305,
Oct. 1991.
[90] S. K. Mishra, D. B. Goldgof, and T. S. Huang,
"Non-rigid motion analysis and epicardial deformation
estimation from angiography data," in Proc. of IEEE Computer Society
Conference on Computer Vision and Pattern Recognition, (Maui,
Hawaii), pp. 331-336, June 1991.
[91] S. K. Mishra, D. B. Goldgof, T. S. Huang, and C. Kambhamettu,
"Curvature-based non-rigid motion analysis from 3d point
correspondences." To appear in International Journal of Imaging
Systems and Technology, 1993.
[92] S. K. Mishra, D. B. Goldgof, and C. Kambhamettu,
"Estimating non-rigid motion from point and line correspondences." To
appear Pattern Recognition Letters, 1993.
[93] F. Mokhtarian and A. Mackwoth,
"Scale-based description and recognition of planar curves and
two-dimensional shapes," IEEE Transactions on Pattern Analysis and
Machine Intelligence, vol. 8, pp. 34-43, Jan. 1986.
[94] F. Mokhtarian,
"Multi-scale description of space curves and three-dimensional
objects," in Proceedings of Compter Vision and Pattern Recognition,
pp. 298-303, 1988.
[95] J. O'Rourke and N. Badler,
"Model-based image analysis of human motion using constraint prop-
agation," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 2, pp. 522-536, 1980.
[96] B. Payne and A. Toga,
"Distance field manipulation of surface models," IEEE Computer Graphics
and Applications, vol. 12, no. 1, pp. 65-71, 1992.
[97] M. Penna,
"Non-rigid motion analysis: Isometric motion," Computer Vision,
Graphics, and Image Processing: Image Inderstanding, vol. 56, pp.
366-380, Nov. 1992.
[98] A. Pentland,
"Towards an ideal CAD system," in Proc. SPIE Conf. on Machine Vision
and Man Machine Interface, SPIE, Jan. 1986. order No.75820.
[99] A. Pentland,
"Perceptual organization and the representation of natural form,"
Artificial Intelligence, vol. 28, no. 2, pp. 293-331, 1986.
[100] A. Pentland,
"Parts: structured descriptions of shape," in National Conference on
Artificial Intelligence, (Philadelphia, PA), pp. 695-701, 1986.
[101] A. Pentland,
"Recognition by parts," in Proc. of IEEE Conference on Computer
Vision, (London), pp. 612-620, 1987.
[102] A. Pentland and J. Williams,
"Perception of non-rigid motion: inference of shape, material
and force," in International Joint Conference on Artificial
Intelligence, pp. 1565-1570, 1989.
[103] A. Pentland,
"Automatic extraction of deformable part models," International
Journal of Computer Vision, vol. 4, pp. 107-126, 1990.
[104] A. Pentland,
"Extraction of deformable part models," in ECCV, pp. 397-401, 1990.
[105] A. Pentland, B. Horowitz, and S. Sclaroff,
"Non-rigid motion and structure from contour," in Proc.
IEEE Workshop on Visual Motion, pp. 288-293, Oct. 1991.
[106] A. Pentland and B. Horowitz,
"Recovery of nonrigid motion and structure," IEEE Transactions on
Pattern Analysis and Machine Intelligence, vol. 13, pp. 730-742,
1991.
[107] N. P. de la Blanca and J. Fdez-Valdivia,
"Building up templates for non-rigid plane outlines," in
International Conference on Pattern Recognition, pp. 575-578, 1992.
Vol. A.
[108] J. Platt,
"A generalization of dynamic constraints," Graphical Models and Image
Processing, vol. 54, pp. 516-525, 1992.
[109] J. M. Rehg and A. Witkin,
"Visual tracking with deformation models," Tech. Rep. CMU-CS-90-156,
Carnegie Mellon University, School of Computer Science, Aug. 1990.
[110] J. W. Roach and J. K. Aggarwal,
"Determining the movement of objects from a sequence of images,"
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.
2, no. 6, pp. 554-562, 1980.
[111] B. Sabata and J. K. Aggarwal,
"Estimation of motion from a pair of range images: A review,"
Computer Vision, Graphics, and Image Processing: Image
Inderstanding, vol. 54, pp. 309-324, Nov. 1991.
[112] M. Sallam and K. Bowyer,
"Generalizing the aspect graph concept to include articulated
assemblies," Pattern Recognition Letters, vol. 12, pp. 171-176,
March 1991.
[113] A. Sanfeliu,
"A distance measure based on tree-graph-grammars: a way of
recognizing hidden and deformed 3d complex objects," in
International Conference on Pattern Recognition, pp. 739-741,
1984.
[114] A. Sanfeliu,
"Structural similarity measures for classifying 2d and 3d partially
hidden, occluded and deformed objects," in International Conference
on Pattern Recognition, pp. 1294-1296, 1986.
[115] E. Saund,
"Representation and the dimensions of shape deformation," in Proc. of
IEEE Conference on Computer Vision, pp. 684-689, 1990.
[116] S. Sclaroff and A. Pentland,
"Generalized implicit functions for computer graphics," in SIGGRAPH,
pp. 247-250, 1991.
[117] T. Sederberg and S. Parry,
"Free-form deformation of solid geometric models," in SIGGRAPH,
pp. 151-160, 1986.
[118] T. Sederberg and E. Greenwood,
"A physically based approach to 2-d shape blending," in SIG-
GRAPH, pp. 25-34, 1992.
[119] J. Segen,
"Model learning and recognition of nonrigid objects," in Proc. of
IEEE Computer Society Conference on Computer Vision and Pattern
Recognition, pp. 597-602, 1989.
[120] J. Segen and K. Dana,
"Parallel symbolic recognition of deformable shapes," in From
Pixels to Features II (H. Burkhardt, Y. Neuvo, and J. Simon, eds.),
Elsevier Science Publishers B.V. (North-Holland), 1991.
[121] J. Segman, J. Rubinstein, and Y. Zeevi,
"The canonical coordinates method for pattern deformation:
Theoretical and computational considerations," IEEE Transactions on
Pattern Analysis and Machine Intelligence, vol. 14, pp. 1171-1183,
1992.
[122] R. B. Shudy and D. H. Ballard,
"Towards an anatomical model of heart motion as seen in 4-d cardiac
ultrasound data," in Proc., 6th Conf. on Computer Applications in
Radiology and Computer-Aided Analysis of Radiological Images, 1979.
[123] D. Shulman and J. Aloimonos,
"Nonrigid motion interpretation: A regularized approach," Proceed-
ings Roy. Soc. London, vol. B233, pp. 217-234, 1988.
[124] W. E. Snyder (Guest Ed.),
"Special issue on motion and timevarying imagery," Computer Vision,
Graphics, and Image Processing, vol. 21, Jan. 1983.
[125] F. Solina and R. Bajcsy,
"Recovery of parametric models from range images: The case
for superquadrics with global deformations," IEEE Transactions on
Pattern Analysis and Machine Intelligence, vol. 12, Feb. 1990.
[126] R. M. L. S. M. Song,
"Computation of 3d velocity fields from 3d cine-ct images of a human
heart," IEEE Trans. on Medical Imaging, vol. 10, pp. 295-306, Sept.
1991.
[127] L. Staib and J. Duncan,
"Parametrically deformable contour models," in Proc. of IEEE Computer
Society Conference on Computer Vision and Pattern Recognition, pp.
98-103, 1989.
[128] R. Strickland and Z. Mao,
"Computing correspondences in a sequence of non-rigid shapes," Pattern
Recognition, vol. 25, no. 9, pp. 901-912, 1992.
[129] J. Subrahmonia, D. B. Cooper, and D. Keren,
"Practical reliable bayesian recognition of 2d and 3d
objects using implicit polynomials and algebraic invariants," Tech.
Rep. TR lems-107, Division of Eng., Brown University, 1992.
[130] R. Szeliski and D. Terzopoulos,
"Physically-based and probabilistic modeling for computer vision,"
in Proc. SPIE 1570, Geometric Methods in Computer Vision (B. C.
Vemuri, ed.), (San Diego, CA), pp. 140-152, July 1991.
[131] R. Szeliski and D. Tonnesen,
"Surface modeling with oriented particle systems," in SIGGRAPH,
pp. 185-194, 1992.
[132] M. Takahata, M. Imai, and S. Tsuji,
"Determining motion of non-rigid objects by active tubes," in
International Conference on Pattern Recognition, pp. 647-650, 1992.
Vol. A.
[133] G. Taubin, R. M. Bolle, and D. B. Cooper,
"Representing and comparing shapes using shape polyno-
mials," in Proc. of IEEE Computer Society Conference on Computer
Vision and Pattern Recognition, pp. 510-516, June 1989.
[134] G. Taubin,
"Estimation of planar curves, surfaces, and nonplanar curves defined
by implicit equations with applications to edge and range image
segmentation," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 13, no. 11, 1991.
[135] D. Terzopoulos,
"Regularization of inverse visual problems involving
discontinuities," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 8, no. 4, pp. 413-424, 1986.
[136] D. Terzopoulos, A. Witkin, and M. Kass,
"Energy constraints on deformable models: recovering
shape and non-rigid motion," in National Conference on Artificial
Intelligence, pp. 755-760, 1987.
[137] D. Terzopoulos, J. Platt, A. Barr, and K. Fleischer,
"Elastically deformable models," in Computer
Graphics (SIGGRAPH-87), vol. 21, pp. 205-214, 1987.
[138] D. Terzopoulos, A. Witkin, and M. Kass,
"Symmetry-seeking models and 3-D object reconstruction,"
International Journal of Computer Vision, vol. 1, pp. 211-221, 1987.
[139] D. Terzopoulos and A. Witkin,
"Physically based models with rigid and deformable components,"
IEEE Computer Graphics and Applications, vol. 8, no. 6, pp. 41-51,
1988.
[140] D. Terzopoulos,
"The computation of visible-surface representations," IEEE
Transactions on Pattern Analysis and Machine Intelligence, vol. 10,
no. 4, pp. 417-438, 1988.
[141] D. Terzopoulos, A. Witkin, and M. Kass,
"Constraints on deformable models: Recovering 3d shape
and nonrigid motion," Artificial Intelligence, vol. 36, no. 1, pp.
91-123, 1988.
[142] D. Terzopoulos and K. Fleischer,
"Modeling inelastic deformation: viscoelasticity, plasticity,
fracture," in Proc. of SIGGRAPH, pp. 269-278, 1988.
[143] D. Terzopoulos and D. Metaxas,
"Dynamic 3d models with local and global deformations: Deformable
superquadrics," in Proceedings of International Conference on
Computer Vision, (Osaka, Japan), pp. 606-615, Dec 1990.
[144] D. Terzopoulos and K. Waters,
"Analysis and synthesis of facial image sequences using physical and
anatomical models," in Proc. Third International Conf. on
Computer Vision (ICCV'90), (Osaka, Japan), pp. 727-732, December
1990.
[145] D. Terzopoulos and M. Vasilescu,
"Sampling and reconstruction with adaptive meshes," in Proc. of
IEEE Computer Society Conference on Computer Vision and Pattern
Recognition, (Miami), pp. 70-75, June 1991.
[146] D. Terzopoulos and D. Metaxas,
"Dynamic 3d models with local and global deformations: Deformable
superquadrics," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 13, pp. 703-714, July 1991.
[147] D. Terzopoulos and R. Szeliski,
"Tracking with kalman snakes," in Active Vision (A. Blake and
A. Yuille, eds.), pp. 3-20, Cambridge, MA: MIT Press, 1992.
[148] D. Terzopoulos and D. Metaxas,
"Tracking nonrigid 3d objects," in Active Vision (A. Blake and
A. Yuille, eds.), pp. 75-89, Cambridge, MA: MIT Press, 1992.
[149] D. Terzopoulos and K. Waters,
"Analysis and synthesis of facial image sequences using physical and
anatomical models," IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 15, 1993.
[150] N. Ueda and K. Mase,
"Tracking moving contours using energy-minimizing elastic contour
models," in Lecture Notes in Computer Science, Vol. 588,
Computer Vision - ECCV'92 (G. Sandini, ed.),
(Berlin Heidelberg), pp. 453-457, Springer-Verlag, 1992.
[151] S. Ullman,
"Maximizing rigidity: the incremental recovery of 3-d structure from
rigid and nonrigid motion," Perception, vol. 13, pp. 255-274, 1984.
[152] B. Vemuri, K. R. Diller, L. S. Davis, and J. K. Aggarwal,
"Image analysis of solid-liquid interface
morphology in freezing solutions," Pattern Recognition, vol. 16, no.
1, pp. 51-61, 1983.
[153] B. C. Vemuri, K. R. Diller, and J. K. Aggarwal,
"A model for characterizing the motion of the
solid-liquid interface in freezing solutions," Pattern Recognition,
vol. 17, no. 3, pp. 313-319, 1984.
[154] F. Verbeek,
"Deformation correction using euclidean contour distance maps," in
International Conference on Pattern Recognition, pp. 347-351, 1992.
[155] N. da Vitoria Lobo and J. Tsotsos,
"Using collinear points to compute egomotion and detect nonrigid-
ity," in Proc. of IEEE Computer Society Conference on Computer Vision
and Pattern Recognition, (Maui, Hawaii), pp. 344-350, June 1991.
[156] Y. Wang and J. Wang,
"Surface reconstruction using deformable models with interior and
boundary constraints," in Proc. of IEEE Conference on Computer
Vision, pp. 300-303, 1990.
[157] J. A. Webb and J. K. Aggarwal,
"Visually interpreting the motion of objects in space," IEEE
Computer, pp. 40-46, Aug. 1981.
[158] J. A. Webb and J. K. Aggarwal,
"Structure from motion of rigid and jointed objects,"
Artificial Intelligence, vol. 19, pp. 107-130, Jan. 1983.
[159] A. Witkin and W. Welch,
"Fast animation and control of nonrigid structures," in
SIGGRAPH, pp. 243-252, 1990.
[160] J. Woodfill and R. Zabih,
"An algorithm for real-time tracking of non-rigid objects," in AAAI-91,
Proceedings of Ninth National Conference on Artificial Intelligence:
Vision and Sensor Interpretation,
pp. 718-723, 1991.
[161] J. Wu and K. Wohn,
"On the deformation of image intensity and zero-crossing
contours under motion," Computer Vision, Graphics, and Image
Processing: Image Inderstanding, vol. 53, pp. 66-75, 1991.
[162] M. Yamamoto, P. Boulanger, J. A. Beraldin, M. Rioux, and J.Domey,
"Direct estimation of deformable motion parameters from range image
sequence," in Proc. of IEEE Conference on Computer
Vision, pp. 460-464, 1990.
[163] M. Yamamoto, P. Boulanger, J. A. Beraldin, and M. Rioux,
"Direct estimation of range flow on
deformable shape from a video rate range camera," IEEE
Transactions on Pattern Analysis and
Machine Intelligence, vol. 15, pp. 82-89, Jan. 1993.
[164] A. Young and L. Axel,
"Non-rigid heart wall motion using MR tagging," in Proc. of IEEE
Computer Society Conference on Computer Vision and Pattern Recognition,
(Urbana, Illinois), pp. 399-404, 1992.
[165] L. A. A. A. Young,
"Three-dimensional motion and deformation of the heart wall :
Extimation with spatial modulation of magnetization - a model-based
approach," Radiology, vol. 185, pp. 241-247, 1992.
------------------------------
End of VISION-LIST digest 12.14
************************
