SpaceNet 8 - The Detection of Flooded Roads and Buildings

Ronny Hänsch, Jacob Arndt, Dalton Lunga, Matthew Gibb, Tyler Pedelose, Arnold Boedihardjo, Desiree Petrie, Todd M. Bacastow; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 1472-1480


The frequency and intensity of natural disasters (i.e. wildfires, storms, floods) has increased over recent decades. Extreme weather can often be linked to climate change, and human population expansion and urbanization have led to a growing risk. In particular floods due to large amounts of rainfall are of rising severity and are causing loss of life, destruction of buildings and infrastructure, erosion of arable land, and environmental hazards around the world. Expanding urbanization along rivers and creeks often includes opening flood plains for building construction and river straightening and dredging speeding up the flow of water. In a flood event, rapid response is essential which requires knowledge which buildings are susceptible to flooding and which roads are still accessible. To this aim, SpaceNet 8 is the first remote sensing machine learning training dataset combining building footprint detection, road network extraction, and flood detection covering 850km 2, including 32k buildings and 1,300km roads of which 13% and 15% are flooded, respectively.

Related Material

@InProceedings{Hansch_2022_CVPR, author = {H\"ansch, Ronny and Arndt, Jacob and Lunga, Dalton and Gibb, Matthew and Pedelose, Tyler and Boedihardjo, Arnold and Petrie, Desiree and Bacastow, Todd M.}, title = {SpaceNet 8 - The Detection of Flooded Roads and Buildings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {1472-1480} }