Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 12 Issue 45
VISION-LIST Digest Thu Oct 07 11:18:17 PDT 93 Volume 12 : Issue 45
- ***** 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:
Contour grouping source code available
Tsai's camera calibration code using NAG library
Announcement of the DIMUND Document Information Server
Setting up a platform for active vision research
E-size scanners
Looking for Dr. Arkady Makhlin
Research Assistant in vision/robotics
Proceedings: Photogrammetric Techniques and Machine Vision
AAAI symposium call for participation
WCNN 1994 Call For Papers
----------------------------------------------------------------------
Date: Mon, 4 Oct 93 13:54:40 EDT
From: sunita@research.nj.nec.com (Sunita Hingorani)
Subject: Contour grouping source code available
Source code is available that implements a "A Bayesian Multiple
Hypothesis Approach to Edge Grouping and Contour Segmentation" as
described in the International Journal of Computer Vision, vol 11:1,
pp 5-24, (1993).
The source Code is obtainable via anonymous ftp to
ftp.nj.nec.com(138.15.10.100).
The files are in:
pub/sunita/CONTOUR/contour.tar.Z
The code is written in C++ (A 3.0 compiler is needed since the code
make extensive use of templates). A X windows interface is also
provided. An image is provided for demonstration purposes.
A Bayesian Multiple Hypothesis Approach to
Edge Grouping and Contour Segmentation
Ingemar J. Cox James M. Rehg
NEC Research Institute Dept. Of Electrical and Computer Eng.
4 Independence Way Carnegie Mellon University,
Princeton, NJ 08540 Pittsburgh, PA
Sunita L. Hingorani
NEC Research Institute
4 Independence Way
Princeton, NJ 08540
Abstract
A contour segmentation algorithm is presented that takes an edge map
and extracts continuous curves of arbitrary smoothness, correctly
handling curve intersections and capable of extrapolating over
significant measurement gaps. The algorithm incorporates noise models
of the edge detection process and limited scene statistics. It is
based on an explicit contour model and employs a statistical distance
measure to quantify the likelihood of each segmentation hypothesis. A
Bayesian multiple hypothesis tree organizes possible segmentations,
making it possible to postpone grouping decisions until a sufficient
amount of information is available. We have demonstrated its
performance on real and synthetic images.
Sunita L. Hingorani
NEC Research Institute
4 Independence Way
Princeton
NJ 08540
phone: 609 951 2729
fax: 609 951 2482
email: sunita@research.nj.nec.com (Inet)
------------------------------
Date: Tue, 5 Oct 93 13:42:43+010
From: Mark Robinson <mark-r@spec0.ee.man.ac.uk>
Subject: Tsai's camera calibration code using NAG library
Hi.
I have uploaded my modified version of Reg Willson's implementation of
Tsai's camera calibration code (Phew :-) ) to the Vision List Archive
at ftp.teleos.com. Check the SHAREWARE/CODE/CALIBRATION subdirectory.
The change is that the code now uses the NAG numerical analysis library
rather than the IMSL library.
The file is Tsai_NAG.tar.Z and the README file is included below.
---------README---------
This code implements the co-planer and non-coplanar calibration
algorithms described by Tsai in:
@ARTICLE{ca:tsai,
author = "Roger Y. Tsai",
title = "A Versatile Camera Calibration Technique for High
Accuracy {3D} Machine Vision Metrology Using Off-the-Shelf
TV Cameras and Lenses",
journal = "IEEE Journal of Robotics and Automation",
volume = "RA-3",
number = "4",
month = "August",
year = "1987",
pages = "323-344"}
using the optimisation routines E04FCF and E04LBF from the NAG Fortran
Library (a popular suite of numerical software routines written by the
Numerical Analysis Group. Note that this software is *not* in the public
domain, but is available at many sites).
99% of the code was written by Reg Willson, I modified it to use NAG
rather than IMSL optimisation routines. No other non-standard libraries
are required.
See the files README.IMSL and README.NAG for more implementation details.
Mark Robinson (October 1993)
(mark-r@spec0.ee.man.ac.uk)
------------------------------
Date: Mon, 4 Oct 93 22:33:36 EDT
From: "Dr. David Doermann" <doermann@parmenides.UMD.EDU>
Subject: Announcement of the DIMUND Document Information Server
ANNOUNCING
The DIMUND Document Information Server
Gopher Server and Mailing List
This system is under development as a repository for Document Understanding
information and resources. The site is housed with the Document Processing
Group at the University of Maryland and available via internet at the node
dimund.umd.edu, port 70.
Please take a moment to subscribe to the mailing list and explore the core
resources on the server.
Some of the information available on this server includes:
- Research Announcements, Calls for Papers and Conference Programs
- Document-List Digest Archive
- On-line access to a document understanding bibliography including
feature extraction, OCR, on-line recognition, text/graphics
discrimination, signature verification and related document
problems.
- A contribution directory for Document Understanding Resources
- source code
- technical reports
- database information
- Archives of document understanding internet utilities
****** Submissions of all relevant information are strongly encouraged. ******
SYSTEM ACCESS
Access to this information is available via
Gopher:
An interactive information server available at dimund.umd.edu, port 70
To add DIMUND Gopher to and existing system, use the following link:
Name=DIMUND Document Information Server
Type=1
Port=70
Path=1/
Host=dimund.umd.edu
Telnet:
Access is available on a temporary basis via telnet to dimund.umd.edu.
Use "gopher" as a login.
Anonymous FTP:
Access to the selected files on the server by connecting to
dimund.umd.edu. Upload capabilities are also available.
EMail:
Email Access to selected files stored on the server is available
through the document server (Document-Server@dimund.umd.edu).
The DOCUMENTS mailing list is also processed by the server
Gopher access is the most complete and easiest to use. Please take time to
browse through the system. Although the core resources will be compiled by
the University of Maryland, the success of such a system depends on user
support, contributions and advertising.
For additional help getting started, send a mail message containing the
following body
HELP
to document-server@dimund.umd.edu
CONTRIBUTIONS
Contributions can be sent to documents@dimund.umd.edu in the format specified
in the Gopher file
USING_THE_SYSTEM/SUBMISSION_INSTRUCTIONS
or uploaded via anonymous FTP.
The format can also be obtained via email by sending a mail request to
Document-Server@dimund.umd.edu containing the single line
HELP SUBMISSIONS
MAILING LIST
A Document Understanding Mailing List (DOCUMENTS) is also available as part
of the document server.
Send a mail message to Document-Server@dimund.umd.edu
containing the following body
SUBSCRIBE DOCUMENTS <first name> <last name>
For additional help with the mailing list or online bibliography searchs,
send a mail message containing the following body
HELP MAIL-LIST
HELP BIBSEARCH
to Document-Server@dimund.umd.edu
QUESTIONS and COMMENTS
Direct all questions to gopher@dimund.umd.edu
Moderated by: Dr. David Doermann
| Document Processing Group
Phone: (301) 405-4526 | Center For Automation Research
Fax: (301) 314-9115 | University of Maryland
Email: gopher@dimund.umd.edu | College Park, MD 20742
| USA
------------------------------
Date: Tue, 05 Oct 1993 17:29:11 +0800
From: "Mr. W.H. WONG" <CSWONGWH@cphkvx.cphk.hk>
Organization: City Polytechnic of Hong Kong
Subject: Setting up a platform for active vision research
Hello All,
We intent to set up an active vision research platform using one single
camera mounted on a stand that allows rotations, zoom in, zoom out and
focusing under software control. Can anyone experienced in setting up
such an environment give us some idea on the budget, performance and ease
of use of some commerically available hardware/software packages? Any
suggestions and information are welcome.
Please send the replies to
him@cpcsaix01.cphk.hk
Thanks a lot in advance.
W.H. WONG,
Image computing group,
Dept. of Computer Science,
City Polytechnic of Hong Kong.
------------------------------
Date: Wed, 6 Oct 93 18:32:36 EDT
From: atul@nynexst.com (Atul Chhabra)
Subject: E-size scanners
I am looking for a good monochrome or gray level scanner that
can scan E-size (3' x 4') engineering drawings at 300 dpi or
higher. I would appreciate any information on such scanners.
Thanks in advance.
Atul K. Chhabra Phone: (914)644-2786
Member of Technical Staff Fax: (914)644-2404
NYNEX Science & Technology Internet: atul@nynexst.com
500 Westchester Avenue
White Plains, NY 10604
------------------------------
Date: Tue, 5 Oct 93 11:33:48 EDT
From: smjeff@lerc05.lerc.nasa.gov (Jeff Miller)
Subject: Looking for Dr. Arkady Makhlin
I am trying to contact Dr. Arkady Makhlin. He was working on vision
systems at DEC but I can't seem to locate him. If you know him can
you please have him call me or give me his phone number or address.
Thank you very much.
------------------------------
From: rbf@aifh.ed.ac.uk
Date: Mon, 4 Oct 93 17:39:24 BST
Subject: Research Assistant in vision/robotics
One Research Post - Computer Vision and Robotics
University of Edinburgh
Department of Artificial Intelligence
Applications are invited for one researcher to work in the
Department of Artificial Intelligence on a SERC funded project entitled
"A Feasibility Study for Visually Locating Robot Grasp Points on Irregular
Objects Using Range Data".
The researcher will investigate how to use range data for
extraction of gripping contact points, how to organise the potential gripping
points into sets consistent with the kinematics of various grippers
and physical dynamics of grasping, and other related topics.
Applicants for the post should have a PhD (or a MSc with comparable experience)
in an appropriate area, such as computer vision, robot manipulation,
image processing and should have experience with the C or C++ programming
languages.
The salary is on the AR1A/B scale in the range 12828-15186 pounds, and the
job is for 18 months starting after Nov 1st, 1993.
Placement for the post is according to age, experience and qualifications.
Applications should include a curriculum vitae (3 copies) and the names and
addresses of two referees, and should be sent to
Ms. Alison Fleming, Department of Artificial Intelligence, University
of Edinburgh, 5 Forrest Hill, Edinburgh, EH1 2QL
by October 22, 1993, from whom further particulars can be obtained.
In your application letter, please quote reference number 930417.
Please note that EEC employment regulations require consideration of
EEC citizens first in filling this post.
------------------------------
Date: Tuesday, 5 October 1993 14:38:54 EDT
From: Dave.McKeown@MAPS.CS.CMU.EDU
Subject: Proceedings: Photogrammetric Techniques and Machine Vision
Conference Proceedings Now Available from SPIE.
The following volume is now available from SPIE. Order information
follows at the end of this message. If you ordered a copy at the
conference you should be receiving it shortly. -Dave McKeown
Integrating Photogrammetric Techniques with Scene Analysis and Machine Vision
E. Barrett and D. McKeown, Eds.
SPIE Vol. 1944
Table of Contents
v Conference Committee
vii Introduction
SESSION 1 PHOTOGRAMMETRY AND COMPUTER VISION
2 Integration of photogrammetric cues into cartographic feature
extraction [1944-01]
D. M. McKeown, Jr., J. C. McGlone, Carnegie Mellon Univ.
16 Linear features for photogrammetric restitution and object
completion [1944-02]
E. M. Mikhail, Purdue Univ.
31 Comparison of two terrain extraction algorithms: hierarchical
relaxation correlation and global least squares matching [1944-03]
G. Hermanson, J. H. Hinchman, U. A. Rauhala, W. J. Mueller, GDE
Systems, Inc.
44 Global image matching and surface reconstruction in object space
using aerial images [1944-04]
H. Ebner, C. Heipke, Technical Univ./Munich (FRG); M. Holm,
Technical Univ./Munich (FRG) and Technical Research Ctr. of
Finland
58 Use of object space matching for feature extraction in multiple
aerial images [1944-05]
T. F. Schenk, C. Toth, The Ohio State Univ.
68 Fast autonomous registration of Landsat, SPOT, and digital map
imagery [1944-07]
A. J. Lee, N. H. Carender, D. J. Knowlton, D. M. Bell, J. K.
Bryan, Harris Information Systems Div.
SESSION 2 PROJECTIVE INVARIANTS AND CAMERA MODELING
82 Photogrammetry and projective geometry: an historical survey
[1944-08]
T. Buchanan, Eberstadt (FRG)
92 Relationship between photogrammmetry and computer vision [1944-09]
R. I. Hartley, J. L. Mundy, GE Corporate Research and Development
Ctr.
106 Extension of three-dimensional invariant methods to
noncentral-projection imaging systems [1944-11]
E. B. Barrett, P. M. Payton, Lockheed Missiles & Space Co., Inc.
120 Absolute orientation of photo pairs using GPS and laser profiles
[1944-12]
J. Kilian, D. Fritsch, Univ. Stuttgart (FRG)
127 Photogrammetric techniques for panoramic cameras [1944-13]
R. I. Hartley, GE Corporate Research and Development Ctr.
140 Quality and performance analysis of automatic relative orientation
[1944-14]
B. Haala, M. Hahn, D. Schmidt, Univ. Stuttgart (FRG)
SESSION 3 STEREO AND MULTISPECTRAL ANALYSIS
152 SPOT stereo matching for DTM generation [1944-16]
E. P. Baltsavias, D. Stallmann, Swiss Federal Institute of
Technology Zurich (Switzerland)
164 Some DEM applications in SAR imagery [1944-17]
F. P. Perlant, ISTAR (France)
176 Alternatives to hierarchical techniques in stereo correlation
[1944-18]
F. R. Norvelle, U.S. Army Topographic Engineering Ctr.
185 Automatic recognition of USGS land use/cover categories using
statistical and neural network classifiers [1944-19]
R. R. Bailey, E. J. Pettit, R. T. Borochoff, E-Systems; M. T.
Manry, X. Jiang, Univ. of Texas/Arlington
196 Effect of on-board compression on stereo and classification
[1944-20]
R. Gupta, J. J. Bloomer, A. Abdel-Malek, R. Zinser, GE Corporate
Research and Development Ctr.; D. B. Hogan, GE Astro-Space Div.
SESSION 4 DIGITAL PHOTOGRAMMETRIC WORKSTATIONS
210 State-of-the-art digital photogrammetric workstations for
topographic applications [1944-21]
C. Heipke, Technical Univ./Munich (FRG)
223 Low-cost soft-copy mapping [1944-22]
E. E. Derenyi, Univ. of New Brunswick (Canada)
231 Restitution of digital stereo data using a digital video plotter
[1944-23]
T. Toutin, Canada Ctr. for Remote Sensing; M. Beaudoin, ESRI
Canada
SESSION 5 AUTOMATED CONSTRUCTION OF CARTOGRAPHIC DATABASES
242 Conceptual design for a model-supported exploitation workstation
for imagery analysts [1944-24]
S. J. Gee, A. M. Newman, Hughes Aircraft Co.
254 Rapid generation and use of 3D site models to aid imagery
analysts/systems performing image exploitation [1944-25]
M. E. Murphy, Computing Devices International
263 Model-based feature extraction [1944-26]
W. J. Mueller, J. A. Olson, GDE Systems, Inc.
273 Incorporating vanishing-point geometry in building extraction
techniques [1944-27]
J. C. McGlone, J. A. Shufelt, Carnegie Mellon Univ.
285 Addendum
286 Author Index
Volume 1944 is $42/members, $50/working group members, and $56/nonmembers.
Member price is extended to anyone who attended this Workshop or the
Orlando Conference. Please add 5% for shipping & handling within the U.S.,
Canada and Mexico. Please add 10% for S&H outside the U.S. SPIE requires
prepayment.
Mailing address: SPIE, P.O. Box 10, Bellingham, WA 98227-0010
Method of Payment: Payment in US dollars drawn on a US bank or int'l
money orders. Credit cards accepted are: Visa, Mastercard, American
Express and Diners. Bank wire transfers must include a copy of the
transfer order. Bank details: Key Bank
Fairhaven Branch
1200 12th Street
Bellingham, WA 98225
Acct. No. 0354 804 957
A credit card order can be phoned or faxed. Phone 206/676-3290,
Fax 206/647-1445.
------------------------------
From: sw@ai.mit.edu (William M. Wells)
Date: Wed, 6 Oct 93 09:54:06 EDT
Subject: AAAI symposium call for participation
Dear Vision List Moderator --
I am interested in (re) advertising a call for participation for a
aaai symposium on the vision list. This is intended as a reminder.
The materials from potential participants are due Oct. 15.
The call for participation appears below.
ANNOUNCEMENT
AAAI 1994 Spring Symposium Series
APPLICATIONS OF COMPUTER VISION IN MEDICAL IMAGE PROCESSING
March 21-23, 1994
Stanford University
Significant interest and activity in medical image processing has
developed among computer vision researchers in the last several years.
This interdisciplinary activity is still in a relatively early stage
of development, in terms of applied technology, and the size of the
research efforts.
This symposium is intended to serve several purposes:
* To bring together vision and robotics researchers
who are currently applying computer vision to medical
image processing problems.
* To increase communication between established researchers
in medical image processing and computer vision researchers.
* To provide information to researchers that are
interested in the field.
The symposium will consist of short presentations of papers and work
in progress, and discussions. Working notes will be produced and
distributed to the participants.
Specific areas of interest include (but are not limited to) the following:
* image guided medical procedures / robotics
* image processing applied to laparoscopic and other endoscopic procedures
* change detection in medical images
* recognition in medical images
* multimodal registration of medical images
* elastic registration of medical images
* motion analysis in medical images
* anatomical atlases
* applications of computer vision in segmentation of medical imagery
Prospective participants are invited to submit one of the following to
the symposium chair by October 15, 1993: an abstract of a paper to be
presented, a description of research in progress, or a statement
describing what you hope to contribute to and gain from the symposium.
Organizing Committee:
William M. Wells III (symposium chair)
Department of Radiology
Harvard Medical School and Brigham and Women's Hospital
75 Francis St, Boston, MA 02115, USA
tel (617) 278-0622 fax (617) 732-7963
sw@ai.mit.edu
Eric Grimson, Massachusetts Institute of Technology,
Ron Kikinis, Harvard Medical School,
Takeo Kanade, Carnegie Mellon University,
Nicholas Ayache, INRIA,
------------------------------
Date: 6 Oct 1993 17:09:42 GMT
From: hrb@se.houston.geoquest.slb.com (Horacio Bouzas)
Organization: GeoQuest Systems Inc. Houston
Subject: WCNN 1994 Call For Papers
WORLD CONGRESS ON NEURAL NETWORKS
SAN DIEGO
1994 INTERNATIONAL NEURAL NETWORK SOCIETY
ANNUAL MEETING
Town & Country Hotel
San Diego, California
June 4-9, 1994
C A L L F O R P A P E R S
SESSION TOPICS SESSION CHAIRS
1. Biological Vision S. Grossberg, V.S. Ramachandran
2. Machine Vision K. Fukushima, R. Hecht-Nielson
3. Speech and Language D. Rumelhart, R. Peterson
4. Biological Neural Networks T. McKenna, J. Davis
5. Neurocontrol and Robotics A. Barto, K. Ashenayi
6. Supervised Learning G. Lendaris, S.Y. Lee
7. Unsupervised Learning G. Carpenter
8. Pattern Recognition T. Kohonen, B. Telfer
9. NEW! Prediction and System Identification P. Werbos, G. Deboeck
10. Cognitive Neuroscience D. Alkon, D. Fong
11. NEW! Links to Cognitive Science and
Artificial Intelligence J. Anderson, L. Medsker
12. Neural Fuzzy Systems L. Zadeh, B Kosko
13. Signal Processing B. Widrow, H. Bouzas
14. NEW! Nurodynamics and Chaos H. Szu, M. Zaghoul
15. Hardware Implementations C. Lau, R. Castain, M. Sayeh
16. Associative Memory J. Taylor, S. Usui
17. Applications D. Casasent, R. Pap, D. Sobajic
18. NEW! Neuroprocessing and Virtual Reality L. Giles, H. Hawkins
19. Circuits & Systems Neuroscience J. Dayhoff, C. Koch
20. NEW! Mathematical Foundations S-I. Amari, D. Levine
Papers must be received by December 10, 1993. The deadline WILL NOT be extended.
Authors must submit registration payment with papers to be eligible for early
registration fee. Six (6) copies (1 original, 5 copies) are required for
submission. Do not fold or staple originals. Six page limit, in English. $20
per page for papers exceeding six (6) pages (do not number pages). Checks for
over length charges should be made to INNS and MUST be included with submitted
paper. Papers must be: camera-ready on 8 1/2" x 11" white paper with 1" margins
on all sides, on column format, single spaced, in Times or similar type style
of 10 points or larger, one side of paper only. FAX is not acceptable. By submi-
tting a previously unpublished paper, author agrees to the transfer of the
copyright to INNS for the conference proceedings.Centered at top of first page
should be complete title, author name(s), affiliation(s) and mailing address(es)
followed by blank space, abstract (up to 15 lines), and text. The following
information MUST be included in an accompanying cover letter in order for the
paper to be reviewed: Full title of paper, corresponding author(s) and presenting
author name, address, telephone and fax numbers, Technical Session
(see session topics) 1st and 2nd choices, oral or poster presentation preferred,
audio visual requirements (for oral presentations only) and INNS member number.
Papers to be sent to the following address:
WCNN San Diego
INNS
1250 24th Street NW, Ste 300
Washington, DC 20037
Attn: Program Chairs
INNS members will be allowed a chance for revision. In order to be elegible for
revision, your cover letter MUST include your INNS member number.
All members of INNS up to the paper deadline may designate up to one paper with
themselves as an author for automatic acceptance. This guarantees only a poster
presentation and abstract publication for that paper.
INNS members and others may submit papers already accepted by journals, or
publicly accessible Tech reports. In lieu of a paper, for considerations as the
basis of an oral presentation. In such a case, the member must submit at least
three copies of the relevant paper, along with an abstract of the talk which
clearly cites the paper well enough to permit easy access to it. When such talk
are accepted, then only the abstracts will be published.
If you have any questions you may contact the INNS at:
Phone: 202-466-4667
Fax : 202-466-2888
\_ \_ \_\_\_ \_\_\_ Horacio Bouzas - Schlumberger GeoQuest
\_ \_ \_ \_ \_ \_ 5858 Westheimer, Ste 800 - Houston, Tx 77057
\_\_\_\_ \_\_\_ \_\_\_ V: 01 713 952-2100
\_ \_ \_ \_ \_ \_ F : 01 713 952-2420
------------------------------
End of VISION-LIST digest 12.45
************************
