First image
Previous image

Next image
Last image
Show double pages

Use the mouse to select the image area you want to share.

Please select which information should be copied to the clipboard by clicking on the link:

Link to the viewer page with highlighted frame
Link to IIIF image fragment

XVIIIth Congress (Part B2)

Access restriction

There is no access restriction for this record.

Copyright

CC BY: Attribution 4.0 International. You can find more information here.

Search in

Bibliographic data

fullscreen: XVIIIth Congress (Part B2)

Multivolume work

Persistent identifier:: 1667435949

Title:: XVIIIth Congress

Sub title:: Vienna, Austria 1996

Year of publication:: 1996

Place of publication:: Vienna

Publisher of the original:: Austrian Society of Surveying and Geoinformation

Identifier (digital):: 1667435949

Language:: English

Editor:: Kraus, Karl; Waldhäusl, Peter

Corporations:: International Society for Photogrammetry and Remote Sensing, Congress, 18., 1996, Wien; International Society for Photogrammetry and Remote Sensing

Adapter:: International Society for Photogrammetry and Remote Sensing, Congress, 18., 1996, Wien; International Society for Photogrammetry and Remote Sensing

Founder of work:: International Society for Photogrammetry and Remote Sensing, Congress, 18., 1996, Wien; International Society for Photogrammetry and Remote Sensing

Other corporate:: International Society for Photogrammetry and Remote Sensing, Congress, 18., 1996, Wien; International Society for Photogrammetry and Remote Sensing

Document type:: Multivolume work

Volume

Persistent identifier:: 1667438379

Title:: XVIIIth Congress

Scope:: 449 Seiten

Year of publication:: 1996

Place of publication:: Vienna

Publisher of the original:: Austrian Society of Surveying and Geoinformation

Identifier (digital):: 1667438379

Illustration:: Illustrationen, Diagramme

Signature of the source:: ZS 312(31,B2)

Language:: English

Additional Notes:: Erscheinungsdatum des Originals ist anhand des Copyrightjahrs ermittelt.

Usage licence:: Attribution 4.0 International (CC BY 4.0)

Editor:: Kraus, Karl; Waldhäusl, Peter

Corporations:: International Society for Photogrammetry and Remote Sensing, Congress, 18., 1996, Wien; International Society for Photogrammetry and Remote Sensing; International Society for Photogrammetry and Remote Sensing, Commission Instrumentation for Data Reduction and Analysis

Adapter:: International Society for Photogrammetry and Remote Sensing, Congress, 18., 1996, Wien; International Society for Photogrammetry and Remote Sensing; International Society for Photogrammetry and Remote Sensing, Commission Instrumentation for Data Reduction and Analysis

Founder of work:: International Society for Photogrammetry and Remote Sensing, Congress, 18., 1996, Wien; International Society for Photogrammetry and Remote Sensing; International Society for Photogrammetry and Remote Sensing, Commission Instrumentation for Data Reduction and Analysis

Other corporate:: International Society for Photogrammetry and Remote Sensing, Congress, 18., 1996, Wien; International Society for Photogrammetry and Remote Sensing; International Society for Photogrammetry and Remote Sensing, Commission Instrumentation for Data Reduction and Analysis

Publisher of the digital copy:: Technische Informationsbibliothek Hannover

Place of publication of the digital copy:: Hannover

Year of publication of the original:: 2019

Document type:: Volume

Collection:: Earth sciences

Chapter

Title:: A MODULAR NEURAL ARCHITECTURE FOR IMAGE CLASSIFICATION USING KOHONEN FEATURE EXTRACTION Márcio L. Goncalves, Márcio L. de Andrade Netto, Jurandir Zullo Júnior

Document type:: Multivolume work

Structure type:: Chapter

Contents

Table of contents

XVIIIth Congress
XVIIIth Congress (Part B2)
Cover
Title page
ISPRS Council 1992 - 1996
International Archives of Photogrammetry and Remote Sensing (IAPRS)
Volume XXXI, Part B2
Technical Commission II Systems for Data Processing, Analysis and Representation
Editorial Team
Copyright 1996
For Sale after the Congress
Foreword
Table of Contents
FEDERATED MULTI-DATABASE INFRASTRUCTURE FOR GIS INTEROPERABILITY - THE DELTA-X PROJECT Mosaad Allam, Cherian Chaly [...] Ekow Otoo [...]
CARTOGRAPHIC ALTERNATIVES IN THE AMAZON CARTOGRAPHIC Engineer: Eliane Alves da SILVA, MSc.
GIS TECHNIQUES AND HYBRID PARAMETRIC/NON-PARAMETRIC IMAGE CLASSIFICATION: A CASE STUDY SHOWING THE POTENTIAL FOR SIGNATURE TRAINING AND ACCURACY ASSESSMENT Thomas Blaschke
SAR SPECKLE SIMULATION Regine Bolter, Margrit Gelautz, Franz Leberl
EXTRACTING SPATIAL INFORMATION FROM DIGITAL VIDEO IMAGES USING MULTIPLE STEREO FRAMES Martin Braess, [...]
PHODIS AT - An Automated System for Aerotriangulation Josef Braun, Liang Tang and Rasmus Debitsch
THE FUTURE OF SOFTCOPY IN PHOTOGRAMMETRIC MAPPING FIRMS Gary G. Brown, President, Aerial Services, Inc.
SISCAM softcopy photogrammetric workstation G. Capanni, F. Flamigni
PERFORMANCE IMPROVEMENT FOR THE TRIANGULATION PROCESS ON LEICA ANALYTICAL WORKSTATIONS BY SEQUENTIAL ADJUSTMENT USED FOR CONTINUOUS QUALITY CONTROL AND DIGITAL POINT TRANSFER Alain Chapuis
Defining and Representing Temporal Objects for Describing the Spatio-Temporal Process of Land Subdivision Jun CHEN, Yanfen LE
ANALOGICAL EQUIPMENT - ASSISTED DIGITAL DATA EDITING Dr. eng. Gh. CORCODEL, [...]
DETERMINING AN INTERCHANGE STANDARD FOR THE NATIONAL SPATIAL DATA INFRASTRUCTURE OF TURKEY Çetin CÖMERT, Gürol BANGER
RECENT DEVELOPMENTS IN DIGITAL PHOTOGRAMMETRIC SYSTEMS FROM LEICA-HELAVA DSW 1 Alex Dam [...] A. Stewart Walker [...]
Processing and Display of Three-Line Imagery at a Digital Photogrammetric Workstation Christoph Dörstel [...] Timm Ohlhof [...]
VGIS - a Graphical Front-End for User-Oriented Analytical GIS Operations Jochen Albrecht, Hartmut Brösamle and Manfred Ehlers
Network Distribution Techniques of the Global 1-km AVHRR Data Set Jeffery C. Eidenshink and Lyndon R. Oleson
A MOBILE MULTI-SENSOR SYSTEM FOR GIS APPLICATIONS IN URBAN CENTERS Naser El-Sheimy
STEREO-IMAGE REGISTRATION BASED ON UNIFORM PATCHES M. Abbasi-Dezfouli [...] T. G. Freeman [...]
ANALYSIS OF THE GEOMETRIC PARAMETERS OF SAR INTERFEROMETRY FOR SPACEBORNE SYSTEMS Rüdiger Gens and John L. van Genderen
TOWARDS AN OPERATIONAL DIGITAL VIDEO PHOTOGRAMMETRIC SYSTEM FOR 3-D MEASUREMENTS E. Tournas, [...] Dr. A. Georgopoulos, [...]
A MODULAR NEURAL ARCHITECTURE FOR IMAGE CLASSIFICATION USING KOHONEN FEATURE EXTRACTION Márcio L. Goncalves, Márcio L. de Andrade Netto, Jurandir Zullo Júnior
Integrated Photogrammetric Systems at Science Applications International Corporation Clifford W. Greve, Ph.D., Scott E. Webster
DIGITAL PHOTOGRAMMETRIC STATIONS REVISITED Armin Gruen
THE EPOS SPECKLE FILTER: A COMPARISON WITH SOME WELL-KNOWN SPECKLE REDUCTION TECHNIQUES Wilhelm Hagg, Manfred Sties
THE DPA-SENSOR SYSTEM FOR TOPOGRAPHIC AND THEMATIC MAPPING Michael Hahn, Dirk Stallmann, Christian Stätter [...] Franz Müller [...]
DEVELOPMENT OF A DIGITAL-IMAGE-BASED-PLOTTER AND ITS APPLICATION TO GROUND DISPLACEMENT MEASUREMENT IN THE KOBE EARTHQUAKE Susumu Hattori, [...] Atsushi Okamoto, [...] Tetsu Ono, [...] Hiroyuki Hasegawa [...]
Design of a Mobile Mapping System for GIS Data Collection Guangping He
SOFTWARE FOR MANAGING COUNTRY-WIDE DIGITAL ELEVATION DATA Franz Hochstöger [...]
Evaluation of Several Speckle Filtering Techniques for ERS-1&2 Imagery Yonghong Huang and J. L. van Genderen
THEMATIC INFORMATION EXTRACTION IN A NEURAL NETWORK CLASSIFICATION OF MULTI-SENSOR DATA INCLUDING MICROWAVE PHASE INFORMATION. Gerrit Huurneman, Rüdiger Gens, Lucas Broekema
AUTONOMOUS AND CONTINUOUS GEORECTIFICATION OF MULTI-ANGLE IMAGING SPECTRO-RADIOMETER (MISR) IMAGERY Veljko M. Jovanovic, Michael M. Smyth, and Jia Zong
CONTROLLING AND UPDATING OF 3D - URBAN DATA WITHIN A DIGITAL PHOTOGRAMMETRIC WORKSTATION Peter Kempa, Eckhard Siebe
PROJECT SWISSPHOTO - DIGITAL ORTHOPHOTOS FOR THE ENTIRE AREA OF SWITZERLAND Thomas Kersten, William O’Sullivan
IMAGE NAVIGATION FOR EMERGENCY RESPONSE (INFER) Loey Knapp, Senior Systems Analyst, [...] John Turek, Research Staff Member, [...] Patricia Andrews, Project Leader, [...] Christopher Elvidge, [...]
A DATABASE FOR A 3D GIS FOR URBAN ENVIRONMENTS SUPPORTING PHOTO-REALISTIC VISUALIZATION Michael Kofler, Herwig Rehatschek, Michael Gruber
EXPERIMENTAL STUDY OF OPTIMAL DIGITAL MAPPING PARAMETERS Kurt Kubik, Director, [...] Peter Harvey, Director, [...]
EARTH OBSERVATION FOR IDENTIFICATION OF NATURAL DISASTERS EOFIND Dr. Steffen Kuntz, Claudia Streck [...] Claudia Kessler [...] Carlo Lavalle [...]
3-D MODELLING OF BUILDINGS FROM DIGITAL AERIAL IMAGERY Jussi Lammi
3D-WIREFRAME MODELS AS GROUND CONTROL POINTS FOR THE AUTOMATIC EXTERIOR ORIENTATION Thomas Läbe, Karl Heiko Ellenbeck
Building a Production System to Support the National Digital Orthophoto Program: An Integration Challenge George Y. G. Lee and David C. Hooper
Describing Spatial Relation based on Voronoi Diagram in Discrete Space Chengming LI, Jun CHEN
MOBILE MAPPING FOR 3D GIS DATA ACQUISITION R. Li, M. A. Chapman, L. Qian, Y. Xin and C. Tao
DIGITAL PHOTOGRAMMETRIC STATION "DELTA" Malov V. [...] Oleynik S. [...] Gajda V. [...] Zotov G. [...]
A PC - BASED SOLUTION FOR COMPUTER AIDED PHOTOGRAMMETRIC MAPPING ON ANALOG STEREOPLOTTERS Dragan Mihajlovié, Zeljko Cvijetinovic
AUTOMATION IN DIGITAL PHOTOGRAMMETRIC SYSTEMS Scott B. Miller [...] Fidel C. Paderes Jr. [...] A. Stewart Walker [...]
DESIGN OF AN AIRBORNE INTERFEROMETRIC SAR FOR HIGH PRECISION DEM GENERATION Joáo Moreira
SPECKLE FILTERING FOR JERS-1/SAR IMAGERY Masatoshi MORI, Tomonori YOKOYAMA, and Noboru YAMAMOTO [...]
STEREOSCOPIC IMAGE PROCESSING USING A DIGITAL PHOTOGRAMMETRIC SYSTEM Nobuhiko Mori : [...] Shunji Murai : [...]
ERRORS AND TOLERANCES IN THE MAPPING, PHOTOGRAMMETRY, RS AND GIS INTEGRATION Prof, dr. Nitu Constantin, [...] Dipl. eng. Nitu Calin Daniel, [...]
A MOBILE OFFICE FOR SURVEYORS. Martin J. Nix, M. Surv.
A CORRELATIVE TECHNIQUE FOR CORRECTION OF SHADING EFFECTS IN DIGITAL MULTISPECTRAL VIDEO IMAGERY. Cindy Ong
SEMI-AUTOMATIC DIGITAL PHOTOGRAMMETRIC SYSTEM ON PC OYAMA Yoichi
SYSTEMS FOR INTEGRATED GEOINFORMATION: stages of evolution Morakot Pilouk
COST-EFFECTIVE DIGITAL PHOTOGRAMMETRY Frantisek Pivnicka, Vladimir Cervenka, Karel Charvát, Ales Limpouch
INDUSTRY TRENDS FOR PC BASED GIS Gordon Plunkett [...] Y. C. Lee [...]
METADATA REQUIREMENT FOR GIS: A CANADIAN EXPERIENCE Gordon Plunkett
AUTOMATIC TIE-POINTING IN OVERLAPPING SAR IMAGES Arnold BAUER, Hannes RAGGAM, Wolfgang HUMMELBRUNNER
ELSM AND GLSR TECHNIQUES OF ARRAY ALGEBRA IN SHAPE MATCHING AND MERGE OF MULTIPLE DEMs Urho A. Rauhala
A CONCEPT FOR A NETWORK-BASED DISTRIBUTED IMAGE DATA ARCHIVE Herwig Rehatschek,[...]
AIR MASS MOTION REMOTE CONTROL SYSTEM A. L. Logutko [...] N. A. Rosental, V. N. Glazov, K. V. Obrosov, [...]
DESCTOP MAPPING AND GIS SYSTEM - DIGIMAP-GeoSET Jerzy Saczuk
INVESTIGATION OF AERIAL TRIANGULATION AND SURFACE GENERATION USING A SOFTCOPY PHOTOGRAMMETRIC SYSTEM Professor Frank L. Scarpace and Raad A. Saleh
PRODUCTION D'IMAGES SYNTHÉTIQUES DE HAUTE RÉSOLUTION POUR LA STÉRÉORESTITUTION PHOTOGRAMMÉTRIQUE par Florin Savopol, Michel Boulianne et Clément Nolette
AUTOMATED GENERATION OF COLOURED ORTHOIMAGES AND IMAGE MOSAICS USING HRSC AND WAOSS IMAGE DATA OF THE MARS96 MISSION Frank Scholten
OPERATIONAL EXPERIENCES OF DIGITAL PHOTOGRAMMETRIC SYSTEMS Martin J. Smith and Douglas G. Smith
EXPRESSION OF THREE DIMENSIONAL SPACE WITH DIGITAL CARTOGRAPHIC DATA AND COMPUTER GRAPHICS METHOD Takayasu OHTSUKA, Hidehisa TAKAHASHI, Hiroshi MASAHARU, Takashi ISAKA, Yoshikazu FUKUSHIMA
IMPLEMENTATION OF A PHOTOGRAMMETRIC RANGE SYSTEM Antonio Maria Garcia Tommaselli [...] Milton Hirokazu Shimabukuro [...] Patricia A. Paiola Scalco, Fernando M. A. Nogueira
SELF-ORGANIZING NEURAL NETWORKS IN FEATURE EXTRACTION Mr. Markus Törmä
AUTOMATIC HEIGHT EXTRACTION FROM ERS-1 SAR IMAGRY Zway-Gen Twu, I. J. Dowman
DIGITAL PHOTOGRAMMETRIC WORKSTATIONS 1992-96 A Stewart Walker [...] Gordon Petrie [...]
DYNAMIC WINDOW SIZE LEAST SQUARES MATCHING FOR AERIAL TRIANGULATION POINTS Shue-chia Wang, Sysh-Hong Chiu, Chi-Chang Tsai
A CLIENT/SERVER MAP VISUALIZATION COMPONENT FOR AN ENVIRONMENTAL INFORMATION SYSTEM BASED ON WWW J. Wiesel, W. Hagg [...] A. Koschel, R. Kramer, R. Nikolai [...]
A NEW METHOD OF PHOTOGRAPHIC IDENTIFICATION IN FIELD WORK - EPSA PHOTOGRAPHIC IDENTIFICATION SYSTEM Delin Yang Professor, [...]
STATISTICAL TEST FOR EVALUATION OF THE ACCURACY OF DIGITAL MAPS FOR GEO-SPATIAL INFORMATION SYSTEM Prof. Bock-Mo Yeu [...] Prof. Hyun Kwon [...] Researcher Seok-Kun Lee [...] Researcher Dong-Bin Shin [...]
DESIGN AND APPLICATION OF SPATIAL INFORMATION MANAGEMENT SYSTEM FOR CITY LAND ASSESSMENT Genong Yu
A PORTABLE SOFTWARE SYSTEM FOR A DIGITAL PHOTOGRAMMETRIC STATION P. Zatelli, PhD. student, [...]
VIRTUOZO DIGITAL PHOTOGRAMMETRY SYSTEM AND ITS THEORETICAL FOUNDATION AND KEY ALGORITHMS Prof. Jianging Zhang, Prof. Zuxun Zhang, Dr. Weiming Shen and Zhihong Wang
THE CONTRIBUTION OF INFORMATION THEORY TO DEVELOPMENT OF MAPPING THEORY OF DIGITIZED AIRPHOTOS (Northwest University, China, Zhang Renlin )
DIGITAL POINTS TRANSFER FOR AEROTRIANGULATION BY ANALYTICAL PLOTTER G. A. Zotov, L. B. llyin, S. S.Nekhin, [...] S. V. Oleinik, [...]
Appendix: Authors and Co-authors Index Volume XXXI, Part B2 - ISPRS Commission Il
Appendix: Keywords Index Volume XXXI, Part B2 - ISPRS Commission II
Cover

Full text

dE SN adu ES
2. FEATURE EXTRACTION BY KOHONEN MAP
The objective of the feature extraction phase is to identify the
spectral classes present in the image and to define the set of
correspondent samples to be used in the classification phase
afterwards.
There is no well-developed theory for feature extraction,
mostly features are application-oriented and often found by
heuristic methods and interactive data analysis.
An important basic principle is that the features must be
independent of class membership because, by definition, at the
feature extraction phase the membership to the classes is not
yet known. This implies that any learning methods used for
feature extraction should be unsupervised in the sense that the
target class for each object is unknown (Oja et al. 1994).
One of the approaches is the use of competitive learning
resulting in data clustering. An example is Kohonen's Self-
Organizing Map (SOM) (Kohonen 1988).
It’s well known the SOM property of dividing the input space
into convex regions, where a set of reference vectors associates
vector codes with the input space. The classification of an
image may then be based on the cluster codes found to the
image by the SOM.
In our approach we generated an auxiliary visual tool from the
SOM, denominated Kohonen Clusters Map (KCM), which
enables to identify the spectral classes present in the image
through the visualization of the clusters generated by SOM.
2.1. SOM Description
The SOM belongs to the class of unsupervised neural netwoks
based on competitive learning, in which only one output
neuron , or one per local group of neurons at a time gives the
active response to the current input signal. The level of activity
indicates the similarity between the input signal vector and its
respective weight vector. A standard way of expressing
similarity is through the Euclidian distance between these
vectors.

hexagonal
900
00.00
9000©
0000 C) aere
0:0:0:0 OOO
d neurons rm
99090 ©
rectangular
OOO
00.00
OOOO
00900
e o 6 o e o
input vectors’

Figure 2: Geometrical representations of neurons
for SOM.
Since the distance between the weight vector of a given neuron
and the input data vector is minimal to all neurons in the
network, this neuron together with a predefined set of
neighbour neurons will have their weights automatically
updated by the learning algorithm. The neighbourhood for each
neuron may be defined accordingly to the geometrical form,
over which the neurons are arranged. Figure 2 depicts two
examples of representation proposed by (Kohonen 1989): a
rectangular grid and an hexagonal grid.
A short description of the learning algorithm of SOM is given
bellow:
Step I: Select a training pattern X — (x4, X»,..., xw) and present
it as an input to the network.
Step 2: Compute distances di between the input vector, and
each j neuron's weight vector, acording to:
N
d;=S &0-w,07 (D)
j
where x;(t) is the j-th input in a given iteraction and
Wi ;(t) is the weight of neuron j from the input layer connected
to neuron i from the output layer.
*
Step 3: Select neuron i with the smallest distance among all
.* .
other neurons, and update the weight vector of 1 and its
neighbours using the following expression:
Wi (t1) & wi ;(0 + (t) * (x; (0 = wi, ; (0)
for i€ N.«,j- L2... N (2)
*
where N. is a set that contains 1 and its neighbours, and
oft) is the learning rate, usually smaller than 1. This
procedure repeats until the the weight update is no longer
significant.
By the end of the learning process each neuron or group of
neighbour neurons will represent a distinct pattern among the
set of patterns presented as input to the network.
2.2. Kohonen Clusters Map (KCM)
In this approach, 3x3 pixel windows taken from the original
image were used as training patterns for the SOM. These
patterns were randomly and uniformly obtained from all over
the image and presented as input vectors to the SOM. Since the
SOM has the property of arranging its weight vectors in
rectangular or hexagonal grids and considering that both input
data vectors and weight vectors have the same dimension, this
enables to generate an image of the weight grid of the SOM.
The resulting grid image, after the unsupervised learning by
the SOM, was denominated Kohonen Clusters Map (KCM).
Figure 5 shows an example of a rectangular KCM generated
from the test image (Fig. 8).
The KCM produces a visual auxiliary tool for the task of
identifying and selecting the spectral classes present in the
image and their correspondent training samples, which will be
used afterwards in the module of neural classification. The
118
International Archives of Photogrammetry and Remote Sensing. Vol. XXXI, Part B2. Vienna 1996
KCM
tasks:
e As
it's p
origir
e The
amon
of p
obtaii
close
posse
e The
founc
highe
mapp
There
used
and n
2,3: P
The
parall
and ii
In
imple
imprc
SOM
Labo
PVM
heter
conct
may
super
work:
netwe
User
throu
comn
For S
was
proce
to red
A cor
the p:
Havir
samp
propc
imag:

Cite and reuse

Cite and reuse

Here you will find download options and citation links to the record and current image.

Volume

METS METS (entire work) MARC XML Dublin Core RIS Mirador ALTO TEI Full text PDF DFG-Viewer OPAC

TOC

Chapter

Image

PDF ALTO TEI Full text

Preview 114×150 jpg

Small 780×1024 jpg

Medium 1559×2048 jpg

Master 3873×5087 MASTER

Image fragment

Link to the viewer page with highlighted frame Link to IIIF image fragment

Citation links

Citation links

Volume

To quote this record the following variants are available:

Here you can copy a Goobi viewer own URL:

Chapter

To quote this structural element, the following variants are available:

Here you can copy a Goobi viewer own URL:

Image

To quote this image the following variants are available:

Here you can copy a Goobi viewer own URL:

Citation recommendation

Kraus, Karl, and Peter Waldhäusl. XVIIIth Congress. Austrian Society of Surveying and Geoinformation, 1996.

Please check the citation before using it.

Image manipulation tools

Tools not available

Share image region

Use the mouse to select the image area you want to share.

Please select which information should be copied to the clipboard by clicking on the link:

Link to the viewer page with highlighted frame
Link to IIIF image fragment

Contact

Have you found an error? Do you have any suggestions for making our service even better or any other questions about this page? Please write to us and we'll make sure we get back to you.

Name: (Required)

Last name:

E-mail: (Required)

Message: (Required)

Security question:

What is the fifth month of the year?:

I hereby confirm the use of my personal data within the context of the enquiry made.

Accept:

No Yes