Continental-Scale Building Detection from High Resolution Satellite Imagery

TL;DR

This paper presents a comprehensive pipeline for continent-scale building detection in Africa using high-resolution satellite imagery, incorporating novel training techniques to improve segmentation accuracy and creating a large-scale building footprint dataset.

Contribution

The study introduces new methods like mixup and self-training with soft KL loss to enhance building detection performance in satellite imagery.

Findings

Improved mAP scores with mixup (+0.12) and self-training (+0.06).

Created the Open Buildings dataset with 516 million footprints across Africa.

Effective detection across diverse rural and urban environments.

Abstract

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. In this work, we describe a model training pipeline for detecting buildings across the entire continent of Africa, using 50 cm satellite imagery. Starting with the U-Net model, widely used in satellite image analysis, we study variations in architecture, loss functions, regularization, pre-training, self-training and post-processing that increase instance segmentation performance. Experiments were carried out using a dataset of 100k satellite images across Africa containing 1.75M manually labelled building instances, and further datasets for pre-training and self-training. We 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.