Deep-Learning-Based Single-Image Height Reconstruction from Very-High-Resolution SAR Intensity Data

TL;DR

This paper demonstrates the first successful application of deep learning for single-image height estimation from SAR intensity data, showing promising transferability across different imaging modes and sites.

Contribution

It introduces a CNN-based approach for SAR data height prediction, along with a novel workflow for training data generation and extensive experimental validation.

Findings

Deep learning can accurately predict height from SAR images.

The method transfers well to unseen data and different imaging modes.

Extensive experiments validate the approach's robustness.

Abstract

Originally developed in fields such as robotics and autonomous driving with image-based navigation in mind, deep learning-based single-image depth estimation (SIDE) has found great interest in the wider image analysis community. Remote sensing is no exception, as the possibility to estimate height maps from single aerial or satellite imagery bears great potential in the context of topographic reconstruction. A few pioneering investigations have demonstrated the general feasibility of single image height prediction from optical remote sensing images and motivate further studies in that direction. With this paper, we present the first-ever demonstration of deep learning-based single image height prediction for the other important sensor modality in remote sensing: synthetic aperture radar (SAR) data. Besides the adaptation of a convolutional neural network (CNN) architecture for SAR intensity images, we present a workflow for the generation of training data, and extensive experimental results for different SAR imaging modes and test sites. Since we put a particular emphasis on transferability, we are able to confirm that deep learning-based single-image height estimation is not only possible, but also transfers quite well to unseen data, even if acquired by different imaging modes and imaging parameters.