Feed on
Posts
Comments

Tag Archive 'MapSwipe'

KinderUni 2019 with GIScience

At Saturday the 23rd of March 2019, it was time again for very young researchers being introduced to GIScience. Melanie Eckle, Martin Hilljegerdes, Sven Lautenbach, Katharina Przybill, Leonie Schuchardt and Vivien Zahs introduced 16 highly motivated kids into GIScience as part of the KinderUni 2019. After an overview and an introduction into desktop mapping and [...]

Read Full Post »

Recently, earth observation by satellites has shown great capability in supporting a range of challenges such as disaster assessment, agriculture monitoring, and humanitarian mapping. MapSwipe, as a humanitarian mapping app, provides a crowdsourcing platform to collect volunteered geographical information (VGI), in order to generate the demanding base map of human settlements for better planning of [...]

Read Full Post »

Humanitarian organizations can’t help people if they can’t find them.
This was the simple reason to create MapSwipe back in 2016 and it is still as pressing as in the very beginning. In the last 2,5 years volunteers have contributed more than 18,000,000 results, which help humanitarian organizations to create maps of human [...]

Read Full Post »

The GIScience Research Group at Heidelberg University and the Heidelberg Institute for Geoinformation Technology (HeiGIT) are happy to share the their GIScience github repository contains now already over 50 open source repositories and it’s still growing. These contain results from several research projects and in particular also some very active long term activities. Most of the tools [...]

Read Full Post »

After the successful GeOnG conference 2018 in chambery we want to thank the organizers and all participants. We contributed in several ways, as already highlighed in our previous blogpost. Now, we also want to share our slides and workshop material with everyone interested.
Round table discussion:

Machine Learning, AI & satellite imagery: what impact on humanitarian mapping: [...]

Read Full Post »

Our paper about Deep Learning from Multiple Crowds: A Case Study of Humanitarian Mapping is available online now.
Satellite images are widely applied in humanitarian mapping which labels buildings, roads and so on for humanitarian aid and economic development. However, the labeling now is mostly done by volunteers. In a recently accepted study, we utilize deep learning [...]

Read Full Post »

Social Innovation and GIScience

This week sees the International Social Innovation Research Conference (ISIRC 2018) hosted at Heidelberg University.
ISIRC is the world’s leading  interdisciplinary social innovation research conference. The conference brings together scholars from across the globe to discuss social innovation in a variety of perspectives.
GIScience Heidelberg and HeiGIT.org will present their work related to social innovation such as [...]

Read Full Post »

Satellite images are widely applied in humanitarian mapping which labels buildings, roads and so on for humanitarian aid and economic development. However, the labeling now is mostly done by volunteers. In a recently accepted study, we utilize deep learning to solve humanitarian mapping tasks of a mobile software named MapSwipe. The current deep learning techniques [...]

Read Full Post »

Last weekend Heidelberg was the host city of this semesters geography “BuFaTa” (Bundesfachschaftentagung). During this four day event student associations from Germany, Austria and Switzerland and their members came together to discuss, learn and spend time together. The event was organized by an excellent student team from Heidelberg.
The disastermappers Heidelberg contributed to the BuFaTa by organising a Missing [...]

Read Full Post »

Among semi-automated methods and pre-processed data products, crowdsourcing is another tool which can help to collect information on human settlements and complement existing data, yet it’s accuracy is debated. Whereas the potential of crowdsourced datasets for training of machine learning algorithms has been explored recently, only few work has been done towards utilizing machine learning [...]

Read Full Post »

Older Posts »