View from a vehicle driving on a dirt road in a rural area with houses and people visible alongside the road
  • In category: Intelligente Mobilität
Collecting Street-Level Imagery in Mozambique to Advance Sustainable Development and Humanitarian Logistics
HeiGIT and Data4MOZ have launched a collaboration to collect street-level imagery in Mozambique, combining local field expertise with geospatial capacity to advance technologies for humanitarian logistics and actionable data for…
Read more
Outdoor event with people walking near white tents and a laptop showing a computer vision interface on a table indoors with people in the background
  • In category: Allgemein, Geoinformation für humanitäre Hilfe
A Computer Vision Workshop with Tomorrow’s Mappers
At Explore Science 2026, young students experimented with computer vision for humanitarian mapping: an occasion to learn how AI models are trained and why human input remains essential for generating…
Read more
Two hexagonal images above text: left shows a street with trees and plants, right shows a heatmap of trees and plants, above is the 'HeiGIT' logo and the text 'How Street-Level Imagery and Deep Learning Are Helping Map Global Infrastructure'
  • In category: Allgemein
How Street-Level Imagery and Deep Learning Are Helping Map Global Infrastructure
Street-level imagery combined with deep learning methods is transforming how we detect and map critical infrastructure characteristics that are often missing from existing datasets. Applications range from road surface classification…
Read more
Wavy measuring tape with centimeter and inch markings on yellow background
  • In category: Forschung
Measuring What You Never Notice: A Computer Vision Approach to Accessible Paths

This blog article was originally posted on Medium by Maciej Adamiak, machine learning expert at HeiGIT. It’s very easy to take many things around us for granted, especially when you live…

Read more
Streetscape Intelligence: GeoAI at Eye Level
  • In category: Geoinformation für humanitäre Hilfe
Streetscape Intelligence: GeoAI at Eye Level

Crowdsourced street-level imagery can be used to detect and map humanitarian-relevant features in near real time. We have developed a machine-learning-based analytical pipeline that integrates with the open-source imagery catalogue…

Read more