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 https://arxiv.org/abs/2107.12283
arXiv PDF paper https://arxiv.org/pdf/2107.12283.pdf
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.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
תגובות