Building detection in high-resolution satellite images

Building detection in high-resolution satellite images

Continental-Scale Building Detection from High Resolution Satellite Imagery
arXiv paper abstract
arXiv PDF paper
Google AI Blog

Identifying the locations and footprints of buildings is vital for many practical and scientific purposes.

Such information can be particularly useful in developing regions where alternative data sources may be scarce.

… describe a model training pipeline for detecting buildings across the entire continent of Africa, using 50 cm satellite imagery.

… study variations in architecture, loss functions, regularization, pre-training, self-training and post-processing that increase instance segmentation performance.

… report novel methods for improving performance of building detection with this type of model, including the use of mixup (mAP +0.12) and self-training with soft KL loss (mAP +0.06).

The resulting pipeline obtains good results even on a wide variety of challenging rural and urban contexts, and was used to create the Open Buildings dataset of 516M Africa-wide detected footprints.

Stay up to date. Subscribe to my posts
Web site with my other posts by category


Photo by Ivan Bandura on Unsplash



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
AI News Clips by Morris Lee: News to help your R&D

I apply innovative technologies like machine learning, computer vision, and physics to further an organization's goals. Am recognized innovator with 66 patents.