Tag: machine-learning
-
OSMlanduse European Union validation effort EuroSDR conference 11/24/2020
During the EuroSDR workshop we will present our OSMlanduse product (earlier post) to the land use (LU) and land cover community (LC) and highlight class accuracies and a benchmark comparison towards existing national authoritative products. Accuracy estimated to be presented are based on more than 7k reference points collected in the past month through a…
-
Regional Variations of Context-based Association Rules in OpenStreetMap
As a user‐generated map of the whole world, OpenStreetMap (OSM) provides valuable information about the natural and built environment. However, the spatial heterogeneity of the data due to cultural differences and the spatially varying mapping process makes the extraction of reliable information difficult. A newly published study investigates the variability of association rules extracted from…
-
HeiKA Autumn school Urban Data Science
This week 19.-23.10. the autumn school Urban Data Science takes place as a online course set up together by GIScience Heidelberg and the Institute for Transport Studies (IfV), KIT. It is part of an ongoing application for a HeiKA (Heidelberg Karlsruhe Strategic Partnership) project that would foster joint teaching modules between GIScience HD and IfV…
-
OSMlanduse European Union validation effort
We launched a validation campaign of our new 10meter resolution OSMlanduse product for the member states of the European Union. Please contribute to the validation here. A technique where contributions are checked against each other is implemented to promote quality of information. The mapathon comes in four themes: nature, urban, agriculture or expert. While the expert…
-
Contiguous high resolution OSMlanduse map of the European Union by combining Copernicus data and OpenStreetMap
Find here a new update of the OSMlanduse.org map. By injecting known tags provided by OpenStreetMap (OSM) into a remote sensing feature space using deep learning, tags were predicted when absent thus creating a contiguous map – initially for the member states of the EU. By design our method can be applied when- and wherever…
-
Inferencing indoor room semantics using random forest and relational graph convolutional networks (deep learning)
Semantically rich maps are the foundation of indoor location‐based services. Many map providers such as OpenStreetMap and automatic mapping solutions focus on the representation and detection of geometric information (e.g., shape of room) and a few semantics (e.g., stairs and furniture) but often still neglect room usage. To mitigate the issue, a new published paper…
-
A Multi-Sensor Fusion Framework Based on Coupled Residual Convolutional Neural Networks
Multi-sensor remote sensing image classification has been considerably improved by deep learning feature extraction and classification networks. In this recent paper, we propose a novel multi-sensor fusion framework (CResNet-AUX) for the fusion of diverse remote sensing data sources. The novelty of this paper is grounded in three important design innovations: A unique adaptation of the…
-
Recap: Keynote on Smart Cities
Already in October 2019 Prof. Zipf was invited to give a keynote on “User Generated Geoinformation for Smart Cities” at the “Smart Cities, Smart Data, Smart Governance” ISPRS Conference at CEPT University in Ahmedabad (known for the Gandhi-Ashram), where he also participated as speaker in the inaugural session and acted as session chair for a…
-
MS Wissenschaft beendet Tour zur Künstlichen Intelligenz – aber weiter geht es im Web – auch mit unserem Exponat zu Trainingsdaten für Satellitenbilder
Gerade beendete die MS Wissenschaft ihre Tour durch 31 Städte zwischen Berlin und Wien in diesem Wissenschaftsjahr zum Thema “Künstliche Intelligenz“. 85.000 Menschen – Schulklassen, Familien und Interessierte aller Altersklassen – besuchten die Ausstellung zum Thema lernende Computersysteme an Bord des Wissenschaftsschiffs. Zu den Besonderheiten der Ausstellung zählten die zahlreiche Dialog- und Mitmachangebote an Bord.…
-
KI-Exponat des HeiGIT zu MissingMaps und Permafrostdetektion auf dem Portal zum Wissenschaftsjahr 2019 “Künstliche Intelligenz”
Seit einiger Zeit findet sich das gemeinsame Exponat des HeiGIT und des Alfred-Wegener-Instituts Helmholtz-Zentrum für Polar- und Meeresforschung für die Ausstellung “Künstliche Intelligenz” auf der “MS Wissenschaft” auch auf dem Webportal zum Wissenschaftsjahr 2019. Das Thema “Künstliche Intelligenz” des Wissenschaftjahres 2019 wird dabei an zwei Beispielen aufgegriffen. Diese zeigen wie jedermann durch das Erzeugen von…