Tag: deep learning
-
Automatic building detection with ohsome2label and Tensorflow
Accurate and complete geographic data of human settlement is crucial for humanitarian aid and disaster response. OpenStreetMap (OSM) can serve as a valuable source, especially for global south countries where buildings are largely unmapped. In a previous blog, we introduced our recent work in detecting OpenStreetMap missing buildings, so this time we will show you…
-
Detecting OpenStreetMap missing buildings by transferring pre-trained deep neural networks
Recently, a new research paper “Detecting OpenStreetMap missing buildings by transferring pre-trained deep neural networks” (Pisl, J., Li, H., Herfort, B., Lautenbach, S., Zipf, A. 2021) has been accepted at the the 24th AGILE conference 2021. The conference will take place virually on June 8 to 11, 2021. Accurate and complete geographic data of human…
-
Talk: Deep Learning for Point Cloud Processing
Lukas Winiwarter of the 3DGeo group was invited by the Austrian Society of Surveying and Geoinformation (OVG) to give a talk on the application of deep learning on point clouds, which took place on March 24. In his talk, Lukas presented four different state-of-the-art approaches to consider the irregular, unordered structure of point clouds, which…
-
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 wird auf Geonet.MRN Meetup zu Flächennutzung und Flächenmanagement vorgestellt: Donnerstag 29.10.2020, 16:30
Am am 29.10.20, 16:30 Uhr veranstaltet das Netzwerk Geoinformation der Metropolregion Rhein-Neckar GeoNet.MRN zum Thema: Flächennutzung und Flächenmanagement: Ein Geoinformation Meetup Teilnahme: Kostenlos und ohne Anmeldung mit Teams unter diesem Link. Themen des Meetups sind die Online-Beteiligung von Kommunen, Bürgern sowie Firmen und Institutionen im Bereich Flächenmanagement mit Fokus auf die Siedlungs- und Verkehrsentwicklung und die…
-
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…
-
OSM Missing Areas Identification paper is featured in August by ISPRS Journal of Photogrammetry and Remote Sensing
We are pleased that our article has been selected by the editors of ISPRS Journal of Photogrammetry and Remote Sensing as the featured Article in August 2020. This means it will be available open access for 1 year. Get your copy here and enjoy a nice summer reading: Li, H., B. Herfort, W. Huang, M. Zia,…
-
Introducing ohsome2label tool to generate training samples from OpenStreetMap for geospatial deep learning
After more than a decade of rapid development of volunteered geographic information (VGI), VGI has already become one of the most important research topics in the GIScience community. Almost in the meantime, we have witnessed the ever-fast growth of geospatial deep learning technologies to develop smart GIServices and to address remote sensing tasks, for instance,…
-
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…