Improving Building Segmentation for Off-Nadir Satellite Imagery

TL;DR

This paper introduces a Bayesian deep learning approach that incorporates satellite image metadata and uncertainty modeling to improve building segmentation accuracy across a wide range of off-nadir angles, especially in noisy images.

Contribution

It presents a novel method combining uncertainty modeling and metadata injection to enhance building segmentation in off-nadir satellite imagery, outperforming baseline models.

Findings

Improved segmentation accuracy on off-nadir images.

Effective noise handling through uncertainty modeling.

Metadata integration enhances model performance.

Abstract

Automatic building segmentation is an important task for satellite imagery analysis and scene understanding. Most existing segmentation methods focus on the case where the images are taken from directly overhead (i.e., low off-nadir/viewing angle). These methods often fail to provide accurate results on satellite images with larger off-nadir angles due to the higher noise level and lower spatial resolution. In this paper, we propose a method that is able to provide accurate building segmentation for satellite imagery captured from a large range of off-nadir angles. Based on Bayesian deep learning, we explicitly design our method to learn the data noise via aleatoric and epistemic uncertainty modeling. Satellite image metadata (e.g., off-nadir angle and ground sample distance) is also used in our model to further improve the result. We show that with uncertainty modeling and metadata injection, our method achieves better performance than the baseline method, especially for noisy images taken from large off-nadir angles.