Mastodawn

Robin Lovelace Dec 29, 2022

Anyone know how to extract road width data from open access remote sensing data? This repo shows it's doable for rivers https://github.com/seanyx/RivWidthCloudPaper and methods should be x-transferable 🙏 Tagging #EarthEngine and #gischat people in the know!

GitHub - seanyx/RivWidthCloudPaper: A Google Earth Engine based algorithm that extracts river centerlines and widths from satellite images

A Google Earth Engine based algorithm that extracts river centerlines and widths from satellite images - GitHub - seanyx/RivWidthCloudPaper: A Google Earth Engine based algorithm that extracts rive...

GitHub

Show thread

Robin Lovelace Dec 29, 2022

There is substantial prior art here but unfortunately not much in the way of reproducible code with open access data. Example from @DLR_en: https://www.dlr.de/eoc/en/desktopdefault.aspx/tabid-12760/22294_read-58694/ + cc @CarlinoDustin for #abstreet-esque city sim.

DLR - Earth Observation Center - DLR-SkyScapes: Aerial Semantic Segmentation Dataset for HD-mapping

High-Definition(HD) mapping is in many applications from autonomous driving to infrastructure monitoring, and urban management essential for the understanding of complex urban infrastructure with centimeter-level accuracy. Aerial images provide valuable information over a large area instantaneously; nevertheless, no current dataset captures the complexity of aerial scenes at the level of granularity required by real-world applications. To address this, we introduce SkyScapes, an aerial image dataset with highly-accurate, fine-grained annotations for pixel-level semantic labeling.

Show thread

Robin Lovelace Dec 29, 2022

And for parallel discussion on the #FOSS todon, possibly more appropiate place to discuss this, see here: https://fosstodon.org/@robinlovelace/109597800326363022 amazing growth of that online community 🚀

Robin Lovelace (@[email protected])

Attached: 1 image Aerial/satellite imagery from Google and other providers is now good enough to allow estimation of road widths. Anyone with Google Earth Engine experience up for helping to figure our how? Existing codebase for rivers: https://github.com/seanyx/RivWidthCloudPaper #geo #geocomputation #geocompx

Fosstodon

Show thread

gsapijaszko

@robinlovelace Years ago I was using imagemagick's convert with fill/fuzz combinations to extract the roads, however it was very sensitive to photo quality, shadows on the roads, cars etc. Now i would focus on LAS, which are becoming more and more available.