Fast building segmentation from satellite imagery and few local labels

TL;DR

This paper demonstrates that high-accuracy building footprint segmentation from satellite imagery can be achieved with very few local labels, enabling efficient urban analysis in specific scenes without requiring extensive labeled datasets.

Contribution

It introduces a method for effective building segmentation using minimal labels in high-resolution satellite images, focusing on local scene adaptation rather than global generalization.

Findings

High recall (0.87) with only 527 sparse annotations.

R2 score of 0.93 for building count estimation.

Effective urban change detection in Amman, Jordan.

Abstract

Innovations in computer vision algorithms for satellite image analysis can enable us to explore global challenges such as urbanization and land use change at the planetary level. However, domain shift problems are a common occurrence when trying to replicate models that drive these analyses to new areas, particularly in the developing world. If a model is trained with imagery and labels from one location, then it usually will not generalize well to new locations where the content of the imagery and data distributions are different. In this work, we consider the setting in which we have a single large satellite imagery scene over which we want to solve an applied problem -- building footprint segmentation. Here, we do not necessarily need to worry about creating a model that generalizes past the borders of our scene but can instead train a local model. We show that surprisingly few labels are needed to solve the building segmentation problem with very high-resolution (0.5m/px) satellite imagery with this setting in mind. Our best model trained with just 527 sparse polygon annotations (an equivalent of 1500 x 1500 densely labeled pixels) has a recall of 0.87 over held out footprints and a R2 of 0.93 on the task of counting the number of buildings in 200 x 200-meter windows. We apply our models over high-resolution imagery in Amman, Jordan in a case study on urban change detection.