|
|
Working Groups
WG III/1 - Pose estimation and surface reconstruction from image and/or range data
Home Page:
www.commission3.isprs.org/wg1/
WG III/1 - Terms of Reference:
- Promote within ISPRS more or less fully automatic methods for:
- calibration and orientation without requiring markers,
- surface reconstruction.
- Current state-of-the-art methods are to be tested with respect to
general applicability, reliability, and performance. Thereby, a
further refinement and robustification of the methods is to be
fostered.
- WG III/1 will therefore provide various synthetic and real test data
sets for image calibration/orientation as well as surface
reconstruction tasks. It will invite researchers to evaluate their
algorithms against known ground truth data with respect to general
applicability and robustness.
WG III/2 - Point Cloud Processing
Home Page:
www.commission3.isprs.org/wg2/
WG III/2 - Terms of Reference:
- Information extraction from point clouds,
- Registration of point clouds,
- Classification/segmentation of natural and urban areas from point clouds,
- Analysis of full-waveform lidar data,
- Data management systems,
- Feature extraction and 3D modelling,
- Quality analysis of lidar data.
ISPRS Working group III/2 aims at promoting the developement of
new methodologies, algorithms and applications related to the
processing of point clouds acquired by airborne or satellite lidar systems,
as well as from other sensors.
To this purpose, the WG organises workshops to exchange the latest developments on
processing point clouds. Furthermore the WG provides (links to) publicly available datasets
and organises international comparative tests on the performance of algorithms
for processing point clouds for various applications.
Finally, the WG will continue to work closely with WG V/3 and WG III/4 and will
establish links with WG VII/7 and WG I/2.
WG III/3 - Image Analysis for Indexation and Image retrieval
Home Page:
www.commission3.isprs.org/wg3/
WG III/3 - Terms of Reference:
- Information mining in large satellite, aerial, and street view image archives;
- Satellite, aerial and street-view image indexing and retrieval;
- Machine learning and context aware image understanding;
- Image semantics and knowledge representation;
- Integration of heterogeneous features : textural, spectral and geometrical attributes;
- Integration of low and high level features (points, segments, regions, graphs, etc.);
- Integration of 3D information and spatial relations between the features;
- Multi-resolution image indexing;
- Image retrieval for localisation and pose estimation;
- Managing huge heterogeneous data sets.
WG III/4 - Complex scene Analysis and 3D reconstruction
Home Page:
www.commission3.isprs.org/wg4/
Chair |
Co-Chair |
Co-Chair |
Secretary |
Franz Rottensteiner |
Caroline Baillard |
Gunho Sohn |
Markus Gerke |
Institute of Photogrammetry and GeoInformation
Leibniz Universität Hannover
Nienburger Str.1
30167 Hannover
Germany
Tel: +49 511 762 3893
Fax: +49 511 762 2483
|
SIRADEL
3 allée Adolphe Bobière CS 24343
35043 Rennes
France
Tel: +33 (0)2 23 48 05 00
Fax: +33 (0)2 23 48 05 99
|
GEOICT
York University
Toronto, M3J 1P3
Canada
Tel: +1 416 650 8011
Fax: +1 416 736 5817 |
International Institute for Geo-Information Science and Earth Observation (ITC)
Hengelosestraat 99, P.O. Box 6
7500 AA Enschede
The Netherlands
Tel: +31 (0)53 4874522
Fax: +31 (0)53 4874335 |
Email:
rottensteiner(at)ipi(dot)uni-hannover(dot)de |
Email:
cbaillard(at)siradel(dot)com |
Email:
gsohn(at)yorku(dot)ca |
Email:
gerke(at)itc(dot)nl |
Web:
www.ipi.uni-hannover.de |
Web:
www.siradel.com |
Web:
www.geoict.net |
Web:
www.itc.nl |
WG III/4 - Terms of Reference:
Our working group aims at making progress in the automatic recognition and 3D reconstruction
of objects in complex scenes from images, point clouds, and other sensor data. The emphasis
is on urban scenes characterized by the occurrence of different object
classes such as vegetation, buildings, roads, street furniture and cars,
with the goal of generating high-resolution 3D
City Models. The working group is focused on but not restricted to analysis techniques that
are capable of handling multiple object classes or that exploit models of the
interconnections between different object classes for scene analysis. It is also our goal
to evaluate methods for object extraction and the suitability of different sensors for
that task.
- Models and techniques for extraction of buildings, roads, cars, vegetation, and other objects for the
generation and update of high-resolution 3D city models and road databases from aerial, spaceborne and
terrestrial image, laser, and (In)SAR data.
- Interpretation of the above sensor data possibly together with information from traditional cartographic
products, CAD models, and urban GIS.
- Development of analysis tools and models required to integrate information about multiple object classes
and their interconnections within complex scenes.
- Automatic and semi-automatic generation of urban models with level-of-detail (LOD) and inferred attribution
including analysis of the trade-off between geometry and radiometry / texture for visualization
- Assessment of efficiency and quality of techniques for these objects and their dependence on the quality
of the input data.
WG III/5 - Image Sequence Analysis
Home Page:
www.commission3.isprs.org/wg5/
WG III/5 - Terms of Reference:
Models, methods and algorithms for:
- camera and camera network calibration from image sequences
including cameras with non-standard geometry and variable framerate,
- ego-motion determination for navigation and object reconstruction,
- detection, reconstruction, classification and tracking of single
and multiple objects in image sequences,
- event reconstruction from image sequences as well as single and
multiple video streams,
- qualitiy assessment of calibration, orientation and object detection
using image sequences.
ICWG III/VII - Pattern Recognition for Remote Sensing
Home Page:
www.commission3.isprs.org/icwg3-7/
ICWG III/VII - Terms of Reference:
- Statistical and non-statistical methods,
- Pixel-based and object-based methods,
- Graphical models (random fields, Bayesian nets) and stochastic grammars,
- Scale space methods,
- Data fusion,
- Quality and uncertainty,
- Benchmarking.
|
|