Road Segmentation in SAR Satellite Images with Deep Fully-Convolutional Neural Networks

TL;DR

This paper evaluates the use of Fully-Convolutional Neural Networks for extracting roads from SAR satellite images, demonstrating that with proper tuning, these models can effectively identify roads despite inherent challenges.

Contribution

It presents an assessment of deep learning models for SAR road segmentation, highlighting the importance of sensitivity tuning and suggesting the need for specialized architectures.

Findings

Models successfully extract most roads in test data

Sensitivity enhancement improves segmentation of thin objects

Deeper networks do not necessarily improve performance

Abstract

Remote sensing is extensively used in cartography. As transportation networks grow and change, extracting roads automatically from satellite images is crucial to keep maps up-to-date. Synthetic Aperture Radar satellites can provide high resolution topographical maps. However roads are difficult to identify in these data as they look visually similar to targets such as rivers and railways. Most road extraction methods on Synthetic Aperture Radar images still rely on a prior segmentation performed by classical computer vision algorithms. Few works study the potential of deep learning techniques, despite their successful applications to optical imagery. This letter presents an evaluation of Fully-Convolutional Neural Networks for road segmentation in SAR images. We study the relative performance of early and state-of-the-art networks after carefully enhancing their sensitivity towards thin objects by adding spatial tolerance rules. Our models shows promising results, successfully extracting most of the roads in our test dataset. This shows that, although Fully-Convolutional Neural Networks natively lack efficiency for road segmentation, they are capable of good results if properly tuned. As the segmentation quality does not scale well with the increasing depth of the networks, the design of specialized architectures for roads extraction should yield better performances.