Stereo Radargrammetry Using Deep Learning from Airborne SAR Images

TL;DR

This paper introduces a deep learning-based stereo radargrammetry technique for airborne SAR images, creating a new dataset and demonstrating improved elevation measurement accuracy over traditional methods.

Contribution

It presents a novel deep learning approach for SAR image stereo matching, including dataset creation and processing techniques that enhance elevation measurement accuracy.

Findings

Wider range of elevation measurements achieved

More accurate elevation measurements compared to conventional methods

Deep learning reduces geometric modulation effects

Abstract

In this paper, we propose a stereo radargrammetry method using deep learning from airborne Synthetic Aperture Radar (SAR) images. Deep learning-based methods are considered to suffer less from geometric image modulation, while there is no public SAR image dataset used to train such methods. We create a SAR image dataset and perform fine-tuning of a deep learning-based image correspondence method. The proposed method suppresses the degradation of image quality by pixel interpolation without ground projection of the SAR image and divides the SAR image into patches for processing, which makes it possible to apply deep learning. Through a set of experiments, we demonstrate that the proposed method exhibits a wider range and more accurate elevation measurements compared to conventional methods. The project web page is available at: https://gsisaoki.github.io/IGARSS2025_sasayama/