Improving Building Segmentation for Off-Nadir Satellite Imagery

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.

arXiv commentThis is an extended version of our ACM SIGSPATIAL'21 conference paper

References in corpus (5)

• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• U${}^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
• SpaceNet MVOI: a Multi-View Overhead Imagery Dataset