Synthetic aperture radar (SAR) data is becoming increasingly available to a wide range of users through commercial service providers with resolutions reaching 0.5m/px. Segmenting SAR data still requires skilled personnel, limiting the potential for large-scale use. We show that it is possible to automatically and reliably perform urban scene segmentation from next-gen resolution SAR data (0.15m/px) using deep neural networks (DNNs), achieving a pixel accuracy of 95.19% and a mean IoU of 74.67% with data collected over a region of merely 2.2km2. The presented DNN is not only effective, but is very small with only 63k parameters and computationally simple enough to achieve a throughput of around 500Mpx/s using a single GPU. We further identify that additional SAR receive antennas and data from multiple flights massively improve the segmentation accuracy. We describe a procedure for generating a high-quality segmentation ground truth from multiple inaccurate building and road annotations, which has been crucial to achieving these segmentation results.
@article{arxiv.1912.04441,
title = {HR-SAR-Net: A Deep Neural Network for Urban Scene Segmentation from High-Resolution SAR Data},
author = {Xiaying Wang and Lukas Cavigelli and Manuel Eggimann and Michele Magno and Luca Benini},
journal= {arXiv preprint arXiv:1912.04441},
year = {2023}
}