Road Network Reconstruction from Satellite Images with Machine Learning Supported by Topological Methods

TL;DR

This paper introduces a novel framework combining machine learning and topological methods, specifically discrete Morse theory, to automatically reconstruct road networks from satellite images with improved accuracy and reduced noise.

Contribution

It develops a fully automatic, training-free approach for road network extraction by integrating a discrete Morse-based graph reconstruction algorithm into the ML pipeline.

Findings

Enhanced connectivity and reduced noise in reconstructed road networks.

Successful application on SpaceNet Challenge datasets.

Iterative improvement of CNN accuracy using topological methods.

Abstract

Automatic Extraction of road network from satellite images is a goal that can benefit and even enable new technologies. Methods that combine machine learning (ML) and computer vision have been proposed in recent years which make the task semi-automatic by requiring the user to provide curated training samples. The process can be fully automatized if training samples can be produced algorithmically. Of course, this requires a robust algorithm that can reconstruct the road networks from satellite images reliably so that the output can be fed as training samples. In this work, we develop such a technique by infusing a persistence-guided discrete Morse based graph reconstruction algorithm into ML framework. We elucidate our contributions in two phases. First, in a semi-automatic framework, we combine a discrete-Morse based graph reconstruction algorithm with an existing CNN framework to segment input satellite images. We show that this leads to reconstructions with better connectivity and less noise. Next, in a fully automatic framework, we leverage the power of the discrete-Morse based graph reconstruction algorithm to train a CNN from a collection of images without labelled data and use the same algorithm to produce the final output from the segmented images created by the trained CNN. We apply the discrete-Morse based graph reconstruction algorithm iteratively to improve the accuracy of the CNN. We show promising experimental results of this new framework on datasets from SpaceNet Challenge.