Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 13 Issue 20
VISION-LIST Digest Mon May 02 11:34:04 PDT 94 Volume 13 : Issue 20
- ***** The Vision List host is 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:
A 2D HVS array....
Hand-shape recognition
Frame grabers
Book information
Forged Bank Notes
Research Positions - Computer Vision, AI
RA vacancy
New book on Geometry-Driven Diffusion
12ICPR - Acceptance Decisions
Workshop on Visual Behaviors
Computer-Based Medical Systems
Morphology Digest
----------------------------------------------------------------------
Date: Thu, 28 Apr 1994 22:30:34 +0000 (GMT)
From: eepnkl@midge.bath.ac.uk (N K Laurance)
Organization: School of Electrical Engineering, University of Bath, UK
Subject: A 2D HVS array....
I was wondering if anyone could point me in the right direction:
I wish to convolute an image with a HVS spatial frquency response, so
I intend to use an FFT/Chirp-Z-Transform to take the image (greyscale
only for the moment) into the frequency domain, then multiply this
2D-array by an HVS 2D-array. I would like to know if there is a 2D HVS
array anywhere for CCIR recommended viewing distances (hence this
array will correspond to the correct spatial frequencies)
ANY help would be appreciated
* Neil Laurance *
* School Of Electronic Engineering *
* University of Bath, U.K. *
* tel: + 44 225 826066 *
* email: neil@ee.bath.ac.uk *
------------------------------
Date: Wed, 27 Apr 1994 10:14:00 +0200
From: alistair@hdl.ie (Alistair Sutherland)
Subject: Hand-shape recognition
I would appreciate any references on recognising human hand-shapes and
gestures from images and video sequences, especially with reference to
Sign language for the Deaf.
Thank you.
Alistair Sutherland
Hitachi Dublin Laboratory
O'Reilly Institute
Trinity College
Dublin 2
Ireland
------------------------------
Date: 29 Apr 1994 18:50:31 GMT
From: spragals@uncc.edu (Satish Pragalsingh)
Organization: University of NC at Charlotte
Subject: Frame grabers
Hi,
I dont know if this is the right place to post this. Well here goes.
I have a camera that has a resolution of ~ 700x500 but my framegraber
has a 640x480 pixel resolution. I need to know how exactly this is
being mapped by the frame graber. I need some litrature on this. Can
some one send info on this
Thanking in advance,
Satish
------------------------------
Date: Thu, 28 Apr 94 23:52:51 NZS
From: ldc@daedalus.otago.ac.nz (Li_Dong Cai)
Subject: Book information
Dear Colleagues,
Could you help me to find the author(s), publisher and the ISBN number of
the book entitled "Inverse Problems in Computer Vision"?
Thank you in advance.
Li-Dong Cai
Email: ldc@daedalus.otago.ac.nz
------------------------------
Date: 28 Apr 1994 14:45:49 GMT
From: brian@daimi.aau.dk (Brian H. Mayoh)
Organization: DAIMI, Computer Science Dept. at Aarhus University
Subject: Forged Bank Notes
We are starting a Neurl net project to detect forged bank notes. We
would be grateful for any info on previous work on money forgery
detection, particularly from those working on similar projects. You
can send info to brian@daimi.aau.dk and mention if you would like me
to reply with a list of references......
------------------------------
Date: Sun, 1 May 1994 19:20:02 +0200
From: Vision User <vision@cast.uni-linz.ac.at>
Subject: Research Positions - Computer Vision, AI
Two research positions in Computer Vision will become available
in autumn 1994 at the Department of Systems Science at Johannes
Kepler University (JKU) in Linz, Austria. Applicants should have a
strong background in image processing, vision, and AI techniques,
and should be willing to pursue independent research in a small,
dedicated young group. For further information please inquire by
email to "vision@cast.uni-linz.ac.at".
------------------------------
Date: 29 Apr 94 10:46:30 GMT
From: MBHSOJP@fs2.ee.man.ac.uk
Subject: RA vacancy
Research Vacancy
Multimedia Information Systems Laboratory
Department of Electrical Engineering
University of Manchester
Research Fellow (RA II) 1 year appointment
"Real-time enhancement of images"
Applications are invited for the above post from persons with
significant experience in image/vision algorithms. The project is
concerned with a specific class of algorithms for enhancement of
images from an airborne camera. The aim of this specific post will be
to develop algorithms for real-time implementation using dedicated
hardware.
Experience in general computing algorithms (eg. sorting and indexing),
computational geometry and/or hardware will be an advantage.
The appointment will be made on the RA II scale, currently stlg18,855 -
stlg25,107, for a period of 12 months from 1/7/94 (or possibly sooner).
Extension for a further two years may be possible.
To apply please send a full CV, including the names of two referees,
by post to :
Dr J P Oakley
Electrical Engineering Department
University of Manchester
Oxford Road
Manchester
M13 9PL
Informal enquiries may be addressed to me at (J.Oakley@man.ac.uk)
------------------------------
Date: Fri, 29 Apr 1994 12:25:06 GMT
From: bart@cv.ruu.nl (Bart M. ter Haar Romeny)
Organization: University of Utrecht, 3D Computer Vision Research Group
Subject: New book on Geometry-Driven Diffusion
Keywords: Scale-Space, anisotropic diffusion
Recently there was an inquiry to the source of anisotropic diffusion.
This field, where the process of evolution of the image in a multiscale
'stack' is a function of the image information itself, is rather new.
I am currently in the final phase of the editing of a book titled
"Geometry-Driven Diffusion in Computer Vision", which is the first
tutorial book in this field. The contributions are from the leading
researchers in this area. The final draft will be on display on the
ECCV conference in Stockholm. The book will be published by Kluwer, and
will be available later this summer (August 1994?).
For your information I include the table of contents and the synopsis:
"GEOMETRY-DRIVEN DIFFUSION IN COMPUTER VISION"
Editor: Bart M. ter Haar Romeny - Utrecht University NL
Contents:
*Foreword by Jan Koenderink - Utrecht University
*Introduction
*1. Linear Scale-Space
Tony Lindeberg - University of Stockholm
Bart M. ter Haar Romeny - Utrecht University
*2. Anisotropic Diffusion
Pietro Perona - California Institute of Technology
Taka Shiota - Kyoto University
Jitendra Malik - University of California at Berkeley
*3. Vector-Valued Diffusion
Ross Whitaker - University of North Carolina Chapel Hill
Guido Gerig - Technical University ETH Zurich
*4. The Bayesian Rationale for Energy Functionals
David Mumford - Harvard University
*5. Minimization of Energy Functional with Curve-Represented Edges
Niklas Nordstrom - Stockholm University
*6. Approximation, Formulation, and Distortion in the Variational
Formulation
Thomas J. Richardson - AT&T Bell Laboratories
Sanjoy K. Mitter - Massachusetts Institute of Technology
*7. Coupled Geometry-Driven Diffusion Equations for Low-Level Vision.
Marc Proesmans, Eric Pauwels, Luc van Gool * Leuven University
*8. Morphological Approach to Multiscale Analysis
Luis Alvarez - Las Palmas University
Jean Michel Morel - Paris University IX Dauphine
*9. Differential Invariant Signatures and Flows in Computer Vision: A
Symmetry Group Approach
Peter J. Olver - University of Minnesota
Guillermo Sapiro - Massachusetts Institute of Technology
Allen Tannenbaum - University of Minnesota
*10. On Optimal Control Methods in Computer Vision and Image Processing
Benjamin Kimia - Brown University
Allen Tannanbaum - University of Minnesota
Steven Zucker - McGill University
*11. Non-Linear Scale-Space
Luc M. J. Florack, Alfons H. Salden, Bart M. ter Haar Romeny,
Jan J. Koenderink, Max A. Viergever - Utrecht University
*12. A Differential Geometric Approach to Anisotropic Diffusion
David Eberly - University of North Carolina Chapel Hill
*13. Numerical Analysis and Applications of Geometry-Driven Diffusion
Wiro J. Niessen - Utrecht University
Bart M. ter Haar Romeny - Utrecht University
*full bibliography (370 references)
*full index (> 750 entries)
FOREWORD
The notion of scale, now widely recognized in computer vision, is
fundamentally related to the physics of observation and the process of
differentiation of discrete data. The stack of images at different
resolutions is known as a scale-space and is traditionally generated by
the linear diffusion equation. Linearity expresses the bottom-up nature
of linear scale-space: a multiresolution representation ignorant of what
is actually in the image. It is a universal ``front-end vision''
representation, without any a priori preferred scales.
Non-linear scale-space constitutes a natural extension of linear
scale-space for situations where additional a priori information is
available, and this knowledge is to be used in the front-end.
Segmentation, a very important ``medium-level'' task, i.e. defining a
hierarchy of meaningful structures in the image, is notoriously
difficult for a linear scale-space, the reason being precisely its
image-unbiased nature. A nonlinear scale-space, being tuned to the
particular image data and incorporating the notion of what should be
meant by ``meaningful'', provides a natural vehicle to incorporate
additional knowledge about the scene and the task.
This seminal book is a primer on geometry-driven, non-linear diffusion
as a promising new paradigm for vision, with emphasis on being tutorial.
The state-of-the-art robust mathematics opens a new direction in
computer vision, reflected in the rapid expansion of this field. All
authors of the carefully tuned chapters are known experts in the field.
They were requested to use a clear presentation style, while in the
editing process many crossreferences could be added. A common
bibliography for the chapters makes up for a state-of-the-art and rather
complete overview of current work. An extensive index, covering the
book as a whole, makes this book more than a textbook, a reference guide
into geometry-driven diffusion and its approaches.
The book presents a mathematically broad treatment of nonlinear (and
linear) scale-spaces: non-linear diffusion equations, axiomatic
approaches from morphology and group theory, energy minimising
functionals, curve and shape evolution, invariant signatures from
symmetry groups, the covariant formalism on image induced non-linear
metric, both in the spatial as scale domain, and more. Emphasis is
placed on the relation between the different approaches. All chapters
can be read individually, but the order in this book is chosen
carefully. As mentioned by Jan Koenderink: it is too early for a course
text (which undoubtedly will come), but the time is ripe for a thorough
analysis of the impact of the image data on the processing machinery in
a scale-space setting. This book explains why.
The book is meant for computer vision scientists and students, with a
computer science, mathematics or physics background. Appendices explain
the terminology in more detail. Many illustrated applications are given
for medical imaging, vector valued (or coupled) diffusion, general image
enhancement (e.g. edge preserving noise suppression, deblurring) and
modeling of the human front-end visual system.
This timely book is the fruit of a European-American transatlantic
collaboration, funded by the EC and NSF over 1993-1996. The book brings
together, in a unique and complete sense, the important groups active in
this field, many of which have an outstanding record of achievements.
The group formed in 1992, with a collaborating effort in the application of
a (travel and subsistence) grant proposal for the EC/NSF program. Since
then a number of succesful meetings were held: May 21-23 1993 the
kickoff meeting was held in Berlin (attracting 25 members of the group's
laboratories). Here the concept of the book was born. The joint meeting
with the Newton Mathematical Institute November 29-December 3 1993 saw
double the audience. The meeting in Stockholm, April 29-30 1994,
satellite to ECCV94, saw the first presentation of this book as first
tangible result of the collaboration.
We are grateful that Jan Koenderink, a most outspoken pioneer and well
recognised scientist of scale-space, has written a preface for this book.
Bart M. ter Haar Romeny, Utrecht April 1994
Bart M. ter Haar Romeny Ph.D. E-mail: bart@cv.ruu.nl
3D Computer Vision - Room E.02.222 Tel: (+31)-30.506695/507772
University Hospital Utrecht Fax: (+31)-30.513399
Heidelberglaan 100, 3584 CX Utrecht, The Netherlands
------------------------------
Date: Mon, 2 May 1994 13:06:42 +0300
From: Shmuel Peleg <peleg@cs.huji.ac.il>
Subject: 12ICPR - Acceptance Decisions
WELCOME TO THE 12th ICPR
You are invited to attend the 12th International Conferences on Pattern
Recognition, to be held at the Renaissance Hotel in Jerusalem, October 9-13,
1994.
The program contains 210 presentations organized in four tracks, with
a total of 56 seesions.
COMPUTER VISION AND IMAGE PROCESSING - 25 Sessions
PATTERN RECOGNITION AND NEURAL NETWORKS - 19 Sessions
SIGNAL PROCESSING - 7 Sessions
PARALLEL COMPUTING - 5 Sessions
In addition, about 210 papers will be presented in poster form.
The program committees did their best to achieve a high-quality and
balanced technical program. Combined with the inspiring location at
Jerusalem, we are certain that the 12th ICPR will be a rewarding and
memorable experience.
S. Peleg S. Ullman Y. Yeshurun
=============================================================================
12-ICPR - Jerusalem, 9-13 October 1994 : Acceptance Decisions
=============================================================================
You could see the list of accepted papers using anonymous ftp to
ftp.huji.ac.il:
cd pub/ICPR
get accept
The acceptance list can also be retrieved by E-Mail as follows:
Send E-Mail to ftpmail@cs.huji.ac.il having the following lines:
open
cd pub/ICPR
get accept
quit
More advanced options of ftpmail can be obtained by sending an E-mail to
ftpmail@cs.huji.ac.il having a single line with the work "help".
------------------------------
Date: Mon, 2 May 1994 13:24:48 GMT
From: Worthy Martin <martin@virginia.edu>
Organization: University of Virginia Computer Science Department
Subject: Workshop on Visual Behaviors
=================================================================
Note: This workshop has a separate registration from
CVPR, so please use the included form and send
it directly to W.Martin
=================================================================
IAPR / IEEE
Workshop on Visual Behaviors
The Westin Hotel --- Seattle, Washington
June 19, 1994
in conjunction with CVPR'94
Few vision researchers question the statement,
"Vision must be understood as a spatio-temporal process."
However, there is still considerable debate about the
fundamental nature of that process. One major approach
claims that vision (and any perceptual process) can only be
understood properly in the context of motivating actions or
tasks. A further pragmatic observation is that the
complexity concerns require that limited system resources be
allocated dynamically in processing only restricted spatial
and temporal regions (at restricted resolutions). The
purpose of this workshop is to foster debate and dialogue on
the fundamental issues involved in systems that tightly
couple perception and behavior to perform tasks. The
program will consist of the papers given below and
associated system demonstrations.
PROGRAM COMMITTEE:
Worthy Martin University of Virginia, General Chair
Dana Ballard University of Rochester
Ruzena Bajcsy University of Pennsylvania
Tom Olson University of Virginia
Mike Swain University of Chicago
John Tsotsos University of Toronto
Linda Shapiro University of Washington, Local Arrangements
===========================================
IAPR/IEEE
Workshop on Visual Behaviors
Registration Form - Register Today!
===========================================
To register, just send this form and a check payable in US dollars to:
Prof. W.N. Martin
Department of Computer Science
Thornton Hall
University of Virginia
Charlottesville, Virginia 22093-2442
The check should be made out to: Workshop on Visual Behaviors.
For information send email to martin@virginia.edu
or call (804) 982-2202 (sorry, no phone registrations).
****************************************************************************
please type or print
Name ________________________________________________________________
Last/Family First Middle Badge Name
Company ________________________________________________________________
Address/Mailstop __________________________________________________________
City/State/Zip/Country ___________________________________________________
Daytime Phone _____________________ FAX Number ___________________________
Email ________________________________
(special pre-workshop information will be sent via email)
IAPR or IEEE/CS
Membership Number _________________________________________________
(required for member discount)
Do you have any special needs? ____________________________________________
Workshop Registration Fee
Advance (until 5/20/94) Late (after 5/20/94)
Member $35 $50
Nonmember $50 $65
Total Enclosed (in U.S. dollars) $ __________
Payment must be enclosed. Please make checks payable to:
Workshop on Visual Behaviors
All payments must be in U.S. dollars, drawn on U.S. banks.
Method of Payment Accepted
Personal Check Company Check Traveler's Check
Registration fee includes workshop attendance and
one copy of the workshop proceedings.
=================
Hotel Information
=================
The Seattle Westin is located in downtown Seattle within easy walking
distance of many restaurants and tourist attractions.
The workshop is being held in conjunction with CVPR in the Seattle Westin.
Transportation to the Seattle Westin from the Seattle-Tacoma Airport can be
booked through Gray Line Coach at the airport. The current price is $12 for
roundtrip transportation. A taxi from the airport to the hotel will cost
approximately $28 one way.
The CVPR conference rate for rooms at the Seattle Westin hotel will be $96
for a single and $111 for a double, plus taxes. The current tax rate is
15.2%. To obtain the conference rates at the Seattle Westin, make your
reservation by Monday May 30 at 5:00 pm Pacific time and mention that you
are attending CVPR. Reservations made after this date will be accepted by
the hotel on a "space available" basis. All major credit cards are accepted
by the hotel.
To make your reservation contact the hotel directly:
The Westin Hotel
1900 Fifth Avenue
Seattle, WA 98101
Phone: (206) 728-1000
Fax: (206) 728-2007
############################################################
# Papers to be Presented #
############################################################
Memory Use During Hand-Eye Coordination
Dana H. Ballard, Mary M. Hayhoe and Jeff B. Pelz
University of Rochester
Abstract:
The very limited capacity of short-term or working
memory is one of the most prominent features of human
cognition. Most studies have stressed delimiting the upper
bounds of this memory in memorization tasks rather than the
performance of everyday tasks. We designed a series of
experiments to test the use of short-term memory in the
course of a natural hand-eye task where subjects have the
freedom to choose their own task parameters. In this case
subjects choose not to operate at the maximum capacity of
short-term memory but instead seek to minimize its use. In
particular, reducing the instantaneous memory required to
perform the task can be done by serializing the task with
eye movements. These eye movements allow subjects to
postpone the gathering of task-relevant information until
just before it is required. The reluctance to use short-
term memory can be explained if such memory is expensive to
use with respect to the cost of the serializing strategy.
*******
Integration of Camera Motion Behaviours for Active Object Recognition
David Wilkes and John Tsotsos
University of Toronto
Abstract:
The concept of active object recognition, as introduced
in our previous work, relies on the use of image-data-driven
behaviours to drive the camera to special views. We review
the arguments for an active approach, then argue for our
particular choice of behaviours. We address the issue of
integrating the behaviours into a complete recognition
methodology, and demonstrate its effectiveness in moderately
cluttered environments. Finally, areas for further work are
identified.
*******
Vision in Man-Made Environments: Looking for Syrup in all the
Right Places
Daniel Fu and Michael Swain
University of Chicago
Abstract:
People are often able to act efficiently in places like
various grocery stores, libraries, and other man-made
domains. They do so because they have useful knowledge
about how these domains are organized. In this paper we
show that an everyday domain, a grocery store, exhibits
useful regularities an agent can use both to simplify visual
tasks and to perform efficiently. We do this by first
identifying the organizations principles around which
grocery stores are structured, identifying the visual
routines involved, and then showing how our current
implementation, SHOPPER, uses these principles and routines
to find items in GROCERY WORLD, a simulated grocery store.
*******
The Surface-Attribute Probe: A "Smart" Tool for 3-D Object Recognition
Y. Tan and H. Freeman
Rutgers University
Abstract:
This paper describes a new approach to the classical
machine vision problem of 3-D object recognition and pose
determination. The process begins by extracting contour
edges from a given patterned-light image of an unknown
object and postulates an initial object line structure.
This line structure is used to guide placement of a set of
small surface-attribute-determining windows, called
"surface-attribute probes" (SAPs), over the image to
determine whether the areas being examined show the presence
of one or more intersecting planar or curved regions. The
resulting information is used to refine the object feature
description, i.e., to determine all face intersections and
characterize each face. The process is repeated until no
further refinement in region segmentation and surface-
attribute determination appears feasible. The ultimate
objective is to obtain (1) an accurate description of the
object line structure, (2) the orientation of all planar
faces, and (3) a qualitative characterization of all curved
surfaces. The segmentation process is guided by recursively
accessing data from the object-model data base, in which the
permissible objects are stored in terms of indexed multiview
representations. Experimental results are provided, showing
the status of the work to date.
*******
Spherical Retinal Flow for a Fixating Observer
Inigo Thomas, Eero Simoncelli and Ruzena Bajcsy
University of Pennsylvania
Abstract:
When a human observer moves, the eye continually
fixates on targets in the world. Although fixation is a
common process in human vision, its role has not yet been
established for computational purposes. The main
contribution of this paper is to formalize the retinal flow
for a fixating observer. A further contribution - a
potentially more practical one - is to explore the role of
the periphery in predicting collision. Utilizing fixation
is expected to turn out to be especially fruitful in light
of recent advances in computer vision for constructing
active head/eye systems [?].
In this work we make the following assumptions: (i) the
observer moves with respect to the world and fixates on a
target; (ii) the world is rigid, with no independently
moving elements; and (iii) the possible rotation axes of the
eye lie on a plane (comparable to Listing's Plane).
Assumptions (ii) and (iii) make the problem of determining
retinal flow tractable.
We first define retinal flow for a 2D universe and then
extend it to the full 3D case; the flow in 2D turns out to
form a component of the flow in 3. The retinal flow in 3D
will be decomposed into longitudinal and latitudinal flow;
the behavior of longitudinal flow along the retinal
periphery will be further analyzed for interesting
properties. Finally the results of a simulated experiment
on retinal flow at the periphery will be presented.
*******
Integration and Control of Reactive Visual Processes
James L Crowley and Jean Marc Bedrune
IMAG-LIFIA
Abstract:
This paper describes a new approach to the integration
and control of continuously operating visual processes.
Visual processes are expressed as transformations which map
signals from virtual sensors into commands for robotic
devices. These transformations define reactive processes
which tightly couple perception and action. Such
transformations may be used to control robotic devices, and
may also be used to control the fixation and optical
parameters of an active binocular head and the visual
processes which interpret visual data.
Our approach takes inspiration from so-called
"behavioural" approaches to mobility and manipulation.
However, unlike most previous work, we define reactive
transformations at the level of virtual sensors and device
controllers. This permits a system to integrate a large
number of perceptual processes and to dynamically compose
sequences of such processes to perform visual tasks. The
transition between visual processes is mediated by signals
from a supervisory controller as well as signals obtained
from perception. This method offers the possibility of
constructing vision systems with large numbers of visual
abilities in a manner which is both salable and learnable.
After a review of related work in mobility and
manipulation, we adapt the reactive process framework to
computer vision. We define reactive visual processes which
map information from virtual sensors to device commands. We
discuss the selection and control of reactive visual
processes to accomplish visual tasks. We then illustrate
this approach with a system which detects and fixates on
moving objects and on human faces.
*******
Representational Frames in Dynamic Scene Annotation
Aaron F. Bobick
MIT Media Lab
Abstract:
One of the tenets of machine vision is that the choice
of representation is critical in describing a scene;
representations are selected that make important information
explicit and that allow domain constraints to be brought to
bear. For describing dynamics scenes, however, there may be
no single representation appropriate for analysis; the
imagery is changing and the choice of best representation
may vary over time. We present two examples of where the
selection of representation frame - the coordinate system in
which the representation describes the scene - determined by
the dynamics of the scene. In the first example, we use
multiple, concurrent representations to describe some
action. These representations are self-validating, meaning
that they can test for their own applicability. The final
description of the action is a composite where part of the
action is described using one system, and the remainder
using another, as determined by the validity measures. The
second example is a simple demonstration of how the
transformation of imagery into the natural coordinate system
of the domain makes the application of domain knowledge
simple. Though this has always been the case, it is
particularly important in video annotation where
transforming domain knowledge into the imagery is more
difficult since the reference frame of the imagery may be
constantly changing.
*******
Perception and Action in a Dynamic Three-Dimensional World
Frank Z. Brill III
University of Virginia
Abstract:
Part of the artificial intelligence community has
broken away from the traditional approach and founded the
sub-discipline known as reactive planning. Reactive systems
do not maintain a world model; instead, they perform actions
reflexively, based primarily on immediate sensory
information obtained directly from the environment. There
are, however, fundamental limits on the capabilities of
systems that do not retain some information about the world.
In particular, a representation of the local space, i.e.,
spatial memory, is required to efficiently perform search
and avoidance tasks in a realistic environment. Given that
it is intractable to maintain a completely current and
accurate model of a dynamic world, research will investigate
the extent to which a world model is necessary for
accomplishing particular tasks in a dynamic three-
dimensional world, and the form of that model. These issues
are addressed by augmenting a reactive agent with a minimal
retention of spatial information necessary to achieve
competence in specific search and avoidance tasks in a
dynamic three-dimensional environment. Visual routines
(top-down, goal-directed visual computations) will be used
to implement the perceptual strategy, which will produce
deictic (agent-centered, activity-oriented) representations
of the world. The principal research in this area will
address the application of visual routines to three-
dimensional environments, the introduction of spatial memory
to deictic representations, and architectural techniques for
building autonomous agents which support these concepts.
*******
A Novel Environment for Situated Vision and Behavior
Trevor Darrell, Pattie Maes, Bruce Blumberg, Alex P. Pentland
MIT Media Lab
Abstract:
In this paper we present a new environment for the
development of situated vision and behavior algorithms. We
demonstrate a system which allows wireless full-body
interaction between a human participant and a graphical
world inhabited by autonomous agents. An image of the
participant is composited together with the graphical world
and projected onto a large screen in from of the
participant. No goggles, gloves, or wires are needed for
interaction with the world: agents and objects in the
graphical world can be acted upon by the human participant
through the use of domain-specific computer vision
techniques that analyze the silhouette and gestures of the
person. The agents inhabiting the world are modeled as
autonomous behaving entities which have their own sensors
and goals and which can interpret the actions of the
participant and react to them in real-time. We have
demonstrated and tested our system with two prototypical
worlds and describe the results obtained and lessons
learned.
*******
Task and Environment-Sensitive Tracking
Peter N. Prokopowicz, Michael J. Swain and Roger E. Kahn
University of Chicago
Abstract:
In a mobile robot, visual tracking, like other visual
behaviors, takes place in a context that includes aspects of
the task, the object being tracked, and the background. In
this work, prior knowledge of those task and target
characteristics that either enable or hinder different
real-time image-tracking algorithms, together with run-time
evaluation of the robot's environment, are used to select an
algorithm appropriate to the context.
*******
Directing Attention to Onset and Offset of Image - Events for
Eye-Head Movement Control
Winky Y. K. Wai and John K. Tsotsos
University of Toronto
Abstract:
This paper proposes a model that investigates a new
avenue for attention control based on dynamic scenes. We
have derived a computational model to detect abrupt changes
and have examined how the most prominent change can be
determined. With such a model, we explore the possibility
of an attentional mechanism, in part guided by abrupt
changes, for gaze control.
The computational model is derived from the difference
of Gaussian (DOG) model and it examines the change in the
response of the DOG operator over time to determine if
changes have occurred. On and off-DOG operators are used to
detect "on" and "off" events respectively. The response of
these operators is examined over various temporal window
sizes so that changes at different rates can be found. The
most salient "on" and "off" events are determined from the
corresponding winner-take=all (WTA) network. The model has
been tested with image sequences which have changes caused
by brightness or motion and the results are satisfactory.
*******
An Active Visual Attention System to "Play Where's Waldo"
W. E. L. Grimson, A. Lakshmi Ratan, P. A. O'Donnell and G. Klanderman
MIT AI Lab
Abstract:
We present an attentive active vision system, which
integrates visual cues to attentively fixate candidate
regions in which to recognize a target object. The system
uses a combination of color and stereo cues to perform
figure/ground separation, yielding candidates regions in
which to focus attention. Within each image region, we use
stereo to extract features that lie within a narrow
disparity range about the fixation position. These features
are used as input to an Alignment recognition system. We
demonstrate significant reductions in the complexity of
recognition using such methods. Our system can successfully
scan a large room, fixating and recognizing specified
targets. We also argue that cues such as stereo can be used
for figure/ground separation without needing accurate camera
calibration.
*******
Color Object Tracking with Adaptive Modeling
Rolf Schuster
Technical University, Munich and Siemens
Abstract:
The color representation of an object viewed with a
color camera is influenced by many parameters (ambient
light, object movement, camera characteristics, etc.). In
that context we address the problem of tracking an object
over time using adaptive color and adaptive shape modeling.
We develop two color models (Ellipsoid- and Mixture
Density Model) to describe the color of an object in two-
and three-dimensional color histogram space. For shape
modeling we suggest a simple moment based modeling scheme.
Finally, we propose an object tracking algorithm that
compensates for object color variations by adaptively
changing both, color and shape models (adaptive modeling).
The procedure has been tested on image sequences of the
human hand with changing ambient light, object movement and
relatively crowded background. The results show that
adaptive modeling performs reliable and fast object
tracking.
*******
Using Multiple Cues for Controlling an Agile Camera Head
Claus Siggaard Andersen and Henrik Iskov Christensen
Aalborg University
Abstract:
The interest in camera heads has been ever increasing
through the past years, and more and more places have them.
The interest in agile sensor systems seems promising for
guiding the vision research in new directions, one of these
being how to direct cameras to obtain a given goal. At
Aalborg University, we have implemented the second and much
improved version of a camera head, which has lead to
research in how to control the system, using visual
information. We propose using a combination of multiple
cues for controlling the camera head, enabling it to cope
with less restricted scenarios than otherwise possible. By
integrating accommodation and disparity cues we are able to
control the vergence of the camera head separated from the
version mechanism, which allows for a simple and yet
reliable method for doing smooth pursuit and base shift, a
central problem of camera head control, and focus of
attention.
*******
Visual Servoing Using Image Motion Information
V. Sundareswaran, F. Chaumette and P. Bouthemy
IRISA/INRIA
Abstract:
Visual servoing is a framework for achieving the tight
coupling of a camera's movements and information from
images. We consider a typical visual servoing approach that
uses geometric information about image features for
controlling the position and attitude of a camera. We claim
that image motion information can be used as well. We
substantiate this claim by presenting two different
approaches to visual tasks that use motion information. The
first one uses motion data which manifests as positional
information; in particular, we use the focus of expansion.
The second one incorporates the parameters of the affine
motion model in the control equations. We illustrate both
these approaches by means of a task to align the optical
axis of the camera with the translational direction, and
present results of experiments done with a six DOF robot.
The contribution of this work is in showing that a tight
coupling between the camera behavior and image motion is
possible.
*******
A $1000 Active Stereo Vision System
Ian Horswill
MIT AI Lab
Abstract:
We describe a simple disparity-based vergence algorithm
running on an ultra-low-cost stereo vision system built from
off-the-shelf components, and present performance data on
the complete system. The system includes a 68020-class
processor, two low-resolution b/w cameras and a 4 degree of
freedom active head. The system runs at up to 16Hz, costs
less than $1000US, and weights less than half a kilogram,
consumes only 3W of power, and is suitable for mounting on a
low cost mobile robot.
We argue that sophisticated vision systems suitable for
mobile robotics are feasible, and that active head systems
need not be as complicated or expensive as was once thought.
*******
Vision-Based Behavior Acquisition For A Shooting Robot By Using
A Reinforcement Learning
Minoru Asada, Shoichi Noda, Sukoya Tawaratsumita and Koh Hosoda
Osaka University
Abstract:
We propose a method which acquires a purposive behavior
for a mobile robot to shoot a ball into the goal by using
the Q-learning, one of the reinforcement learning methods.
A mobile robot (an agent) does not need to know any
parameters of the 3_d environment or its
kinematics/dynamics. Information about the changes of the
environment is only the image captured from a single TV
camera mounted on the robot. Only two parameters, the
velocity and orientation are control commands to be learned.
Image positions of the ball and the goal are used as state
variables which evaluate the effect of an action taken
during the learning process. After the learning process,
the robot tries to carry a ball near the goal and to shoot
it. Both computer simulation and real robot experiments are
shown, and we discuss on the role of vision in the context
of the vision-based reinforcement learning.
*******
Localizing Un-Calibrated, Reactive Camera Motion in an Object
Centered Coordinate System
Claus Brondgaard Madsen and Henrik Iskov Christensen
Aalborg University
Abstract:
We present elements of an analytic framework for an
approach to determining the angle between legs of junctions
in a polyhedral domain. From geometrical analyses we define
a set of qualitative visual events induced by moving the
camera in a reactive manner. These events provide means of
determining the position of the camera in relation to an
object centered coordinate system. The sole assumption
being an ability to perform fixation, the approach is
completely free of calibration, matching and absolute
motion.
An expression is derived relating the apparent angle
(viewed angle) to the true angle and the view point
specified in an object centered coordinate system. We show
that this relation has saddle surface characteristics. We
then define two camera motion strategies based on the
direction of the bisecting line in the image. Resulting
general trajectories are computed. Using the trajectories
we analyze the rate-of-change in apparent angle and the
orientation of the bisecting line. From these analyses we
define a set of visual events and relate them to what
knowledge about view point can be deduced from them.
Experiments are presented to illustrate the effect of
the motion strategies and to exemplify positional knowledge
obtained from sequences of visual events.
------------------------------
Date: 29 Apr 1994 15:02:08 GMT
From: wes@eos.ncsu.edu (WESLEY E SNYDER)
Organization: North Carolina State University
Subject: Computer-Based Medical Systems
EMAIL ADVANCE PROGRAM
The 7th IEEE Symposium on
Computer-Based Medical Systems
Adam's Mark Hotel
Winston-Salem, North Carolina
June 10-12, 1994
Sponsors:
IEEE Engineering in Medicine & Biology Society
IEEE Computer Society
IEEE Winston-Salem Chapter
and in cooperation with the Bowman Gray School of Medicine,
Wake Forest University
*************************************************************
CBMS will be held in coordination with S/CAR:12th Conference*
for Computer Applications in Radiology June 12-15 *
*************************************************************
For a copy of the complete CBMS advance program,
contact Ms. Carla Muller, Tel (910)716-6890;
Fax (910)716-2870; email carla@relito.medeng.wfu.edu
Email Advance Program
FRIDAY, JUNE 10
FM1:10:00 AM --12 Noon
Expert Systems-1 (Martha Evens)
FM2 10:00 AM --12 Noon
Image Processing - 1 (Wesley Snyder)
FM3: 10:00 AM --12 Noon
Drug Roundtable (Margaret Peterson)
12:00: LUNCH
Speaker: Design News Magazine's "Engineer of the Year", Dean Kamen
FA1 1:00-3:00 PM
Prosthetic Valve Sounds 1 (Rebecca Inderbitzen)
FA2 1:00-3:00 PM
Signal Processing-1 (Paul Kizakevich)
FA3 1:00-3:00 PM
Methods 1
3:00 COFFEE
FA4 3:30-5:30 PM
Prosthetic Valve Sounds 2 (Rebecca Inderbitzen)
FA5 3:30-5:30 PM
Image Processing 2 (Nelson Corby)
FA6 3:30-5:30 PM
Methods 2
6:00 Social at the Workshop, Old Salem: Join us for food, music, and Moravian
crafts demonstrations
SATURDAY, JUNE 11, 1994
SM1 8:30-9:30 AM
Expert Systems 2 (Martha Evens)
SM2 8:30-9:30 AM
Signal Processing-2 (Paul Kizakevich)
SM3 10:00AM-12:00 Noon
Neural Networks-1 (Russ Eberhart)
9:30 COFFEE
SM 4 10:00 AM-12:00 Noon
Signal Processing-3 (Richard Fries)
SM5 10:00 AM-12:00 Noon
Medical Software Safety (Lon Gowen)
12:00 LUNCH
SA1 1:00-3:00 PM
Medical Information (Harry Burke)
SA 2 1:00-3:00 PM
Image Processing 3 (Wes Snyder)
SA3 1:00-3:00 PM
Ambulatory Blood Pressure Monitoring (Tom Smith)
SA4: 1:00-3:00 PM
Neural Networks-2 (Russ Eberhart)
3:00 COFFEE
SA5 3:30-5:30 PM
Image Processing 4 (Nassrin Tavakoli)
SA6 3:30-5:30 PM
Software Safety Roundtable (Lon Gowen)
Open Discussion
REGISTRATION
Conference Registration Fees Advance (Prior to 5/20/94) Late and onsite
IEEE Member $295 $355
Non Member $370 $445
IEEE Full-time Student Member $125
Registration includes Proceedings, Coffee Breaks, Lunches, and Friday Social
at Old Salem.
**************************************************************************
*Special S/CAR -CBMS Joint Registration: With full registration at either*
*CBMS or S/CAR, participants may attend the other meeting for $150 *
*(proceedings not included) *
**************************************************************************
Send Registration form along with check or money order payable on a U.S.
bank to: CBMS, Attn: Ms. Carla Muller, Department of Radiology, Bowman Gray
School of Medicine, Medical Center Boulevard, Winston-Salem NC 27157
Tel (910)716-6890; Fax (910)716-2870; email carla@relito.medeng.wfu.edu.
We regret that CBMS can not accept credit cards.
Cancellation policy: Registration will be refunded less a $50 processing fee
if cancellations are made in writing prior to May 23.
TUTORIALS
Saturday Evening, June 11
Sunday Morning, June 12
T1: Grantsmanship in Biomedical Engineering Research
T2: Surfing the Internet: Mosaic and Other Tools
T3: Integrated Neuro-fuzzy Models in Pattern Recognition
T4: Programming in Motif
T5: Medical Imaging
For complete details on tutorials, including speaker resumes and
tutorial descriptions, contact Ms. Carla Muller, Tel (910)716-6890;
Fax (910)716-2870; email carla@relito.medeng.wfu.edu
Tutorials
IEEE Member Non-member
Advance Registration $125 $155
Late/onsite $175 $220
Travel to Winston-Salem: Winston-Salem is located in the beautiful western
piedmont region of North Carolina, about 80 miles north of Charlotte,
30 miles west of Greensboro, and less than an hour's drive from the Blue
Ridge Parkway. The Piedmont Triad International Airport, which is midway
between Winston-Salem and Greensboro, is served by USAir, Delta, Continental,
United, and American Air Lines.
Accommodations: Adam's Mark Hotel, 425 N. Cherry St., Winston-Salem NC 27101;
Tel(910)725-3500 or (800)444-2326; Fax(910)721-2235. Please state that you
are attending the IEEE-CBMS Symposium. The Symposium rate is $85.00/night.
**************************************************************************
FOLLOWING CBMS: *
S/CAR94 *
Symposium for Computer Assisted Radiology *
June 12-15, 1994 Winston-Salem, North Carolina *
Sunday, June 12 - Tutorials/Technical Exhibits (1:00-5:15 PM) *
Monday, June 13 *
Wide Area PACS Image Processing *
3D-Imaging RIS/HIS/PACS *
PACS Assessment Expert Systems *
MDIS *
*
Tuesday, June 14 *
PACS Software Information Systems *
Artificial Intelligence Public Health *
Teleradiology DICOM/LAN *
Workstations Computed Radiography *
Wednesday, June 1 *
PACS Integration, Teaching, Research, Focus session:Current State of *
Virtual Reality *
Demonstrations, Poster Sessions, and Technical Exhibits on Mon. & Tues. *
Tutorials *
o Basics of Computers *
o Basics of Digital Imaging *
o A Transition to Filmless Imaging Department *
o Introduction to DICOM *
o Asynchronous Transfer Mode (ATM) and its Applicability to Telemedicine*
Fees: Register for either S/CAR or CBMS and attend the other conference *
for only an additional $150. *
Program and Registration Information: Contact Pat Rice, Department of *
Radiology, The Bowman Gray School of Medicine, Medical Center Boulevard, *
Winston-Salem, North Carolina USA. 27157-1088, Tel: (910)716-2470, *
Fax(910) 716-2029. *
**************************************************************************
Conference Committee
General Chair
Wesley E. Snyder
North Carolina State University and Bowman Gray School of Medicine
Local Arrangements Chair
Craig Hamilton, Bowman Gray School of Medicine
Program Co-Chairs
Paul Kizakevich Nassrin Tavakoli
Research Triangle Institute Motorola Info Systems
Finance Chair Tutorials Chair
Meena Banerjee Thomas K. Miller
AT&T North Carolina State University
Exhibits Chair
Richard Riddle
Riddle and Associates
------------------------------
Date: Thu, 28 Apr 94 12:38:42 EDT
From: sharilee@aol.com
Subject: Morphology Digest
Below you find the announcement of this newsletter. The archive is located at
ftp.cwi.nl (directory /pub/morphology), and can also be reached via the
HTTP server at CWI (www.cwi.nl).
MAILING LIST: morpho@cwi.nl
Electronic newsletter on mathematical morphology, image algebra, stochastic
geometry, and related subjects.
Subscribe: email to morpho@cwi.nl with "subscribe" as subject
and empty message body.
Unsubscribe: email to morpho@cwi.nl with "unsubscribe" followed by email
address
as subject and empty message body.
Submissions: email to morpho@cwi.nl with "submit" as subject.
FTP Archives
ftp.cwi.nl , directory /pub/morphology for old issues of Morphology Digest,
CWI report, PhD theses, and bibTeX database on mathematical morphology
Yours,
Henk Heijmans
CWI email: henkh@cwi.nl
Kruislaan 413 tel: +31 20 5924057
NL 1098 SJ Amsterdam fax: +31 20 5924199
The Netherlands
*******************************
Announcement: MORPHOLOGY DIGEST
*******************************
We are happy to announce the "Morphology Digest".
This digest is intended as a forum between workers in the field of
Mathematical Morphology and related fields (stochastic geometry, random
set theory, image algebra, etc.).
The Morphology Digest intends to provide fast and up-to-date information on:
1. Conferences, workshops, courses
2. Books, articles, reports, PhD theses
3. Algorithms, software, hardware
4. Available research positions
5. Bibliographical data
relevant to anyone interested in mathematical morphology.
The Morphology Digest also seeks to disperse informal contributions
ranging from elementary questions about specific morphological algorithms
to critical essays on the nature of mathematical morphology.
The frequency of the digest depends on the number of submissions.
Our estimate is to have an issue once every month.
Subscribe: email to morpho@cwi.nl with "subscribe" as subject
and empty message body.
Unsubscribe: email to morpho@cwi.nl with "unsubscribe" followed by email
address
as subject and empty message body.
Submissions: email to morpho@cwi.nl with "submit" as subject.
Archive site: anonymous ftp to ftp.cwi.nl; directory /pub/morphology/digest
The email addresses will only be used for sending the digest and not for
other
purposes.
Henk Heijmans
Centre for Mathematics and Computer Science (CWI)
Kruislaan 413
NL 1098 SJ Amsterdam, The Netherlands
------------------------------
End of VISION-LIST digest 13.20
************************
