ISPRS WG II/6

Large-scale Machine Learning for Geospatial Data Analysis

Introducing a new benchmark dataset: Semcity Toulouse

Our Mission

ISPRS Working Group II/6 aims to promote large-scale machine learning methods to analyze geo-referenced data. Nowadays, a multitude of different sensors provide an ever increasing amount of observations at varying scale, temporal, and spatial resolution, making the processing pipelines strive for methods able to process such large amounts of data. For instance, imagery (and point clouds) can be obtained from overhead or terrestrial sensors for 3D modelling, for semantic interpretation or for monitoring scenes at large-scale. Data can either be acquired with dedicated campaigns like aerial/satellite imaging campaigns and mobile mapping or be collected from crowd-sourced, publicly available data sets like OpenStreetMap. An important aspect is the combination of multiple complementary views (e.g., street view panoramas and aerial images) from different sensors, and acquisitions made at different times. Multi-modal, multi-temporal, and multi-scale image analysis are therefore of particular scientific relevance.

Instead of hierarchical, rule-based methods that are tailored for a particular scene layout and task, machine learning enables to model relevant object patterns directly from labeled training data. The larger the labeled set, the more accurately data can be represented by powerful machine learning models. However, one of the main bottlenecks is to generate and gather enough training data to achieve sufficient generalization accuracy. In practice, ground truth is often labeled manually resulting in high costs, and it is consequently a limiting factor. Research in weakly supervised learning, transfer learning, and self-taught learning aims at significantly reducing manual labeling efforts to build models that are relevant to applications in practice.

In order to facilitate scientific progress, this WG fosters collaboration between the Photogrammetry & Remote Sensing and the Computer Vision & Machine Learning communities. Workshops at both, ISPRS events and CV & ML conferences shall raise mutual awareness and knowledge exchange. A benchmark challenge shall provide a new, large-scale data set and a sound evaluation tool to make a high quality data set with ground truth publicly available that acts as a testbed to make different methods better comparable. People submitting to this challenge will be encouraged to publish their method and to publicly release source code to further accelerate scientific progress.

Working Group Officers

Chair

Jan Dirk Wegner, ChairJan Dirk Wegner
 
Photogrammetry & Remote Sensing
ETH Zurich
Zurich
SWITZERLAND
+41 44 633 68 08

 

Co-Chair

Ribana Roscher, Co-ChairRibana Roscher
 
Remote Sensing
University of Bonn
Bonn
GERMANY
+49 228 73 2716

 

Co-Chair

Michele Volpi, Co-ChairMichele Volpi
 
Swiss Data Science Center
ETH Zurich
SWITZERLAND
+41 44 632 80 45

 

Secretary

Clément Mallet, SecretaryClément Mallet
 
Univ. Paris Est
IGN-ENSG
Saint-Mandé
FRANCE
+33 1 43 98 84 36

 


Supporters

Industrial
Representative
Wolfgang Steinborn, Industrial<br>RepresentativeWolfgang Steinborn
 
Geo-Info-Systems
Rudolf-Hahn-Str. 152
53227 Bonn
GERMANY
+49 228 4339581
+49 228 461256

 

Industrial
Representative
Michaela Neumann, Industrial<br>RepresentativeMichaela Neumann
 
European Space Imaging
Arnulfstrasse 199
80634 Munich
GERMANY
+49 89 130142 0
+49 89 130142 22

 


Terms of Reference

  • Large-scale image classification,
  • Machine learning, deep learning,
  • Pixel-wise semantic segmentation at large-scale,
  • Supervised, weakly supervised, transfer, and human-in-the-loop learning
  • Multi-view, multi-temporal, multi-modal image interpretation
  • Change detection and environmental / urban monitoring

WG II/6

Fig1

Fig2

Fig3

Fig4

White

White

Logo

The International Society for Photogrammetry and Remote Sensing is a non-governmental organization devoted to the development of international cooperation for the advancement of photogrammetry and remote sensing and their applications. The Society operates without any discrimination on grounds of race, religion, nationality, or political philosophy.

Our Contact

ISPRS
c/o
Leibniz University Hannover
Institute of Photogrammetry and GeoInformation
Nienburger Str. 1
D-30167 Hannover
GERMANY
Email: isprs-sg@isprs.org