MapSwipe wins Global Mobile Award for the Best Mobile Innovation Supporting Emergency or Humanitarian Situations
Last week, at the prestigious GSMA MWC series (formally known as Mobile World Congress) MapSwipe was awarded the top prize in the Global Mobile Awards’ category for the Best Mobile Innovation Supporting Emergency or Humanitarian Situations. The award recognizes how mobile connectivity can provide a lifeline in major humanitarian disasters, providing access to critical information and communication. The judges prized MapSwipe as “an exceptionally important project with clear results and impact across multiple geographies – definitely a stand-out winner showing clear innovation and potential”.
The team at the Heidelberg Institute for Geoinformation Technology (HeiGIT) and the GIScience Research Group at Heidelberg University has shaped MapSwipe’s development from the very beginning by designing the crowdsourcing approach behind MapSwipe, providing the tools needed to manage such a global project and make use of the data in timely manner. As part of the Missing Maps project, MapSwipe is a mobile app that was created to crowdsource map data from a network of global volunteers - just one swipe at a time. Individuals, volunteers from communities all over the world, can swipe through the app and tap areas where they find crucial infrastructure such as buildings and roads, identify changes in areas.
Through the research at HeiGIT and GIScience Research Group Heidelberg University it will soon be able to use machine-learning technologies to improve the open mapping. HeiGIT provides an API for enriched data sets based on MapSwipe results for humanitarian organization, develops and researches new project types such as for change detection or improving data completeness and also develops tutorials to help users contribute better data, to name a few Heidelberg contributions since the initial concept development.
MapSwipe is an open source project built and maintained by volunteers, with the support of the British Red Cross, HeiGIT and the GIScience Research Group, Humanitarian OpenStreetMap Team and Medecins Sans Frontieres. The projects have supported a range of missions and global organizations, such as the Red Cross Red Crescent Movement and Medecins Sans Frontieres, as well as local NGOs like the Tanzania Development Trust and MapPH.
Once a project has been requested by a community, the MapSwipe team creates it in the app, using imagery from a variety of sources and creating instructions that help the user to understand what to look for and the resulting action they should take. Each set of imagery is viewed by at least 3 individuals to improve data-quality. Users can track their impact, receiving badges for the distance swiped.
MapSwipe has engaged more than 29,000 volunteers around the world to map vulnerable communities across 29 different countries, with projects ranging from supporting the refugee response in Colombia, identifying populations for vaccination campaigns in Chad, and identifying buildings in the Democratic Republic of Congo to support ongoing response to the Ebola outbreak. The data can be used to identify population size and needs, address critical health challenges and prevent the spread of disease, and create resilience for communities in the midst of climate change. To date, volunteers have swiped over 850,000 sq.km of imagery, nearly the size of Pakistan.
The team behind MapSwipe wants to send a big “Thank You” to all our passionate volunteers that keep on swiping day to day and help us filling the missing maps.
The objective of HeiGIT gGmbH is to improve knowledge and technology transfer from fundamental research in geoinformatics to practical applications. This includes developing open geoinformation technology related to disaster, health and environmental topics. A focus is on generating open geoinformation data products, routing and navigation based on OpenStreetMap data, improving mobile crowdsourcing apps, and research on analysing and improving open geodata or effective combination of crowdsourcing and machine learning. HeiGIT receives core funding from the Klaus Tschira Stiftung (KTS).
Selected related references from HeiGIT/GIScience:
- The initial MapSwipe idea and prototype developed by us:
- Albuquerque, J. P., B. Herfort, and M. Eckle. “The tasks of the crowd: A typology of tasks in geographic information crowdsourcing and a case study in humanitarian mapping.” Remote Sensing 8.10 (2016): 859.
- First analysis of MapSwipe data quality:
- Herfort, B., Reinmuth, M., Albuquerque, J.P., Zipf, A. (2017): Towards evaluating crowdsourced image classification on mobile devices to generate geographic information about human settlements. Proceedings of the 20th AGILE Conference on Geographic Information Science (2017). Wageningen, NL, Association of Geographic Information Laboratories in Europe: 1-7.
- Recent work on combining machine learning, artificial intelligence and MapSwipe:
- Herfort, B., Li, H., Fendrich, S., Lautenbach, S., Zipf, A. (2019): Mapping Human Settlements with Higher Accuracy and Less Volunteer Efforts by Combining Crowdsourcing and Deep Learning. Remote Sensing 11(15), 1799. https://doi.org/10.3390/rs11151799
- Chen, J., Y. Zhou, A. Zipf and H. Fan (2018): Deep Learning from Multiple Crowds: A Case Study of Humanitarian Mapping. IEEE Transactions on Geoscience and Remote Sensing (TGRS). 1-10. https://doi.org/10.1109/TGRS.2018.2868748
- Li, H., Herfort, B., Zipf, A. (2019): Estimating OpenStreetMap Missing Built-up Areas using Pre-trained Deep Neural Networks. Proceedings of the 22nd AGILE Conference on Geographic Information Science, Association of Geographic Information Laboratories in Europe. Limassol, Cyprus.
- Overview about Missing Maps:
- Scholz, S., Knight, P., Eckle, M., Marx, S., Zipf, A. (2018): Volunteered Geographic Information for Disaster Risk Reduction: The Missing Maps Approach and Its Potential within the Red Cross and Red Crescent Movement. Remote Sens., 10(8), 1239, doi: 10.3390/rs10081239.
https://twitter.com/GIScienceHD http://giscienceblog.uni-hd.de https://scholar.google.com/citations?user=1TAZiPwAAAAJ