Author: GIScience HD

  • 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,…

  • Quiet route planning for pedestrians in traffic noise polluted environments

    #Noise #pollution is one of the main stressors in urban environments, having negative impacts on people’s quality of life and health. For some groups of citizens, such as school children, patients, and elders, there is a need to support them in finding pedestrian routes in noise polluted areas of cities. In a new paper, we…

  • How to become ohsome part 6: Introducing the magical filter parameter

    We are back again with a fresh part of the How to become ohsome blog series. In case this 6th part of the series is your first one, or you have not heard from our awesome OpenStreetMap History Data Analytics Platform before (short form: ohsome platform), don’t worry. We’ve added some context, as well as…

  • Jugend präsentiert zu Besuch bei HeiGIT

    Am 02.07. besuchte eine Delegation von Alumni von “Jugend präsentiert” im Rahmen der diesjährigen Summer School REMOTE von “Jugend präsentiert” das Heidelberg Institute for Geoinformation Technology (HeiGIT gGmbH) an der Universität Heidelberg. Aufgrund der Corona-Pandemie fand der Besuch allerdings nur virtuell statt: Prof. Alexander Zipf berichtete und diskutierte in einem Online-Meeting mit den Teilnehmerinnen über die…

  • 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…

  • Sphinx is ohsome – new documentation of the ohsome API

    What does the tool behind the recently published documentation of the ohsome API have in common with a statue made of stones in Egypt? – Apart from the name, both are of course awesome (and now also ohsome). As previously announced, together with the open source release 1.0 of the ohsome API, we have published a…

  • ohsome API 1.0 is here

    As we’ve announced it in a previous post, the Open Source release 1.0 of the ohsome API has finally arrived. As a reminder, or for those of you that hear “ohsome” for the first time, the aim of the ohsome OpenStreetMap History Data Analytics Platform is to make OpenStreetMap’s full-history data more easily accessible for various kinds…

  • Going green with MeinGrün – Today App launch in Heidelberg and Dresden

    Today the time has come: The “meinGrün” web app for Dresden and Heidelberg is officially launched. With the mobile application you can (re-)discover known and unknown green spaces and find a pleasant route to those. Users can learn about the functions of the app via virtual scavenger hunt. The app is the result of the…

  • Virtual disastermappers heidelberg OSM Mapathon “Mapping Human Rights” June 30th

    In scope of the disastermappers heidelberg mapathon series “Open Data & the Sustainable Development Goals”, the next virtual OpenStreetMap mapping event “Mapping Human Rights” will take place on Tuesday, June 30th from 6 pm, in cooperation with Amnesty International Heidelberg. Amnesty International Heidelberg will give us insights into Human Rights and the work of Amnesty International.…

  • Data Journalism WebApp about Accessibility in Sweden according to Corona Travel Recommendations

    Sveriges Television AB (the public Swedish television company) has published a data journalism WebApp showing how far one can travel according to the recommendations from the Swedish Public Health Authority. Of course the safest recommendation is not to travel at all during the corona crises – but if one absolutely has to, shorter trips of…

  • Exploration of OpenStreetMap Missing Built-up Areas using Twitter Hierarchical Clustering and Deep Learning in Mozambique

    Accurate and detailed geographical information digitizing human activity patterns plays an essential role in response to natural disasters. Volunteered geographical information, in particular OpenStreetMap (OSM), shows great potential in providing the knowledge of human settlements to support humanitarian aid, while often the availability and quality of OSM remains a major concern. The majority of existing…

  • Announcing release 1.0 of ohsome API

    Big news from the ohsome team: the release 1.0 of one of our major services, the ohsome API for ohsome OpenStreetMap History Analytics, is on the doorstep. We are bringing three major advancements along with this version. The first one is a completely new documentation of the API giving several examples to different endpoints. The…