GIScience Logo
HeiGIT Logo
3DGeo Logo

GIScience Blog

Tag: convolutional neural networks

  • GIScience and HeiGIT contributions to AGILE 2021 conference

    The AGILE 2021 conference is taking place this week. It is the the 24rd AGILE conference on GIScience. AGILE is the Association of Geographic Information Laboratories in Europe and the 2021 conference is for the first time held as a virtual conference. As in earlier years GIScience Heidelberg and HeiGIT are contributing to the conference with several…

  • 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…

  • 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…

  • Detecting OSM Building Facades with Graffiti Artwork Based on Street View Images and Social Media using Deep Learning

    As a recognized type of art, graffiti is a cultural asset and an important aspect of a city’s aesthetics. As such, graffiti is associated with social and commercial vibrancy and is known to attract tourists. However, positional uncertainty and incompleteness are current issues of open geo-datasets containing graffiti data. In a newly published paper, we…

  • New DFG project: IdealVGI – Deep Learning with OSM

    Recently a new DFG project proposal was accepted to the GIScience Research Group Heidelberg within the DFG priority programme VisVGI (Volunteered Geographic Information: Interpretation, Visualisation and Social Computing” [SPP 1894]). It is joint collaboration project together with Prof. Begüm Demir from TU Berlin. IDEAL-VGI: Information Discovery from Big Earth Observation Data Archives by Learning from…

  • Hyperspectral and LiDAR Fusion Using Deep Three-Stream Convolutional Neural Networks

    Our feature paper “Hyperspectral and LiDAR Fusion Using Deep Three-Stream Convolutional Neural Networks” is now published online. Recently, convolutional neural networks (CNN) have been intensively investigated for the classification of remote sensing data by extracting invariant and abstract features suitable for classification. In this paper, a novel framework is proposed for the fusion of hyperspectral…