Category: Research
-
Leveraging OpenStreetMap and Multimodal Remote Sensing Data with Joint Deep Learning for Wastewater Treatment Plants Detection
Humans rely on clean water for their health, well-being, and various socio-economic activities. During the past few years, the COVID-19 pandemic has been a constant reminder of about the importance of hygiene and sanitation for public health. The most common approach to securing clean water supplies for this purpose is via wastewater treatment. To date,…
-
New “Robert and Christine Danziger PhD Scholarships“ 2022 in Geoinformatics at GIScience Heidelberg University for PhD students from Africa – DL 15.July
It is our great pleasure to inform about the new “Robert and Christine Danziger Scholarships“ 2022 for doing a PhD in Geoinformatics at Heidelberg University. Please make yourself familiar with the research topics at GIScience Heidelberg and HeiGIT (e.g. projects, papers) when suggesting potential topics for your PhD research. Short facts: The Robert and Christine Danziger Scholarship is awarded to very…
-
ohsome Region of the month – Back on trail
Welcome back to our Region of the Month series. If you’re hearing about this format the first time you should definitely check out some of our older blog posts, e.g. this one on the tagged forests of different places in Canada or this first part of a street network analysis! Since it’s May and getting warmer again,…
-
Improving OpenStreetMap missing building detection using few-shot transfer learning in sub- Saharan Africa
OpenStreetMap (OSM) has been intensively used to support humanitarian aid activities, especially in the Global South. Its data availability in the Global South has been greatly improved via recent humanitarian mapping campaigns. However, large rural areas are still incompletely mapped. The timely provision of map data is often essential for the work of humanitarian actors…
-
New Paper and Data: 4D Point Clouds of a Beach-Dune System
A new data article on “A high-resolution 4D terrestrial laser scan dataset of the Kijkduin beach-dune system, The Netherlands” was just published in Scientific Data. Along with the fully openly available dataset, the article presents insights into the importance of frequent and spatially detailed surface measurements – and what to do with them. Get directly…
-
Praktikum Scientific Software Development
Die 3DGeo Forschungsgruppe (https://uni-heidelberg.de/3dgeo) der Abteilung Geoinformatik an der Universität Heidelberg sucht eine qualifizierte und motivierte Person für ein Praktikum als Scientific Software Developer*in (w/m/d) für einen Zeitraum von 3 bis 6 Monaten als stud./wiss. Hilfskraft. Im Anschluss besteht generell die Möglichkeit der Verlängerung oder die Bewerbung auf eine Stelle als wiss. Mitarbeiter*in (w/m/d). Die 3DGeo-Forschung…
-
Online seminar ‘Deep learning from Volunteered Geographical Information: a case study of humanitarian mapping with OpenStreetMap’
We invite to the upcoming online seminar at the Urban Analytics Lab seminar series at the National University of Singapore (NUS): ‘Deep learning from Volunteered Geographical Information: a case study of humanitarian mapping with OpenStreetMap’ on 29 April (9am German time, 3pm Singapore time) By Hao Li, GIScience Research Group, Heidelberg University @GIScienceHD As an emerging topic,…
-
Zooming-in for climate action—hyperlocal greenhouse gas data for mitigation action?
While the international community has made progress in adopting goals and agreements in the field of climate change mitigation, efforts to reduce greenhouse gas (GHG) emissions are significantly lacking behind global ambitions for acceptable climate change. In a recently published perspective in the journal Climate Action, we discuss whether a window of opportunity for more…
-
Preview of 3DGeo @ EGU 2022 – Meet us there
The 3DGeo Research Group will present some of their latest research at EGU General Assembly 2022. We are looking forward to meet you at the following talks: Virtual Laser Scanning using HELIOS++ – Applications in Machine Learning and Forestry: The presentation provides an introduction to VLS, possible use cases, pitfalls and best practices for successful…
-
New paper on “improving change analysis with full temporal information”
In recently published work, we show how change analysis from near-continuous 3D time series improves by considering full temporal information. How can it be done? Using 4D objects-by-change! The method was applied to an hourly time series of terrestrial laser scans acquired for snow cover monitoring. In the snow-covered scene at the Zugspitze ski resort,…
-
Where to map in OpenStreetMap next? Experiences from Mozambique, India, and Tonga
OpenStreetMap (OSM) has been intensively used to support humanitarian aid activities, especially in the Global South. Its data availability in the Global South has been greatly improved via recent humanitarian mapping campaigns and due to the efforts of local communities. However, large rural areas are still incompletely mapped. The timely provision of map data is…
-
Join our final “SocialMedia2Traffic” project presentation on March 22
Navigation services need time dependent information on traffic speed to generate suitable routes and yield accurate travel time estimations. However, this information is not available free of cost globally. Within the recently completed project “SocialMedia2Traffic”, we have developed a system to model traffic speed of urban roads depending on the time of day based on…