Brightearth roads: Towards fully automatic road network extraction from satellite imagery

TL;DR

This paper presents a fully automated pipeline that extracts accurate, up-to-date road networks from high-resolution satellite images by combining neural networks, graph optimization, and machine learning classification.

Contribution

It introduces a novel end-to-end method for generating precise, connected road line-strings directly from satellite imagery, improving upon existing map data accuracy.

Findings

Demonstrates high accuracy in road network extraction

Provides up-to-date road layouts compared to OSM

Achieves seamless connection and precise positioning of roads

Abstract

The modern road network topology comprises intricately designed structures that introduce complexity when automatically reconstructing road networks. While open resources like OpenStreetMap (OSM) offer road networks with well-defined topology, they may not always be up to date worldwide. In this paper, we propose a fully automated pipeline for extracting road networks from very-high-resolution (VHR) satellite imagery. Our approach directly generates road line-strings that are seamlessly connected and precisely positioned. The process involves three key modules: a CNN-based neural network for road segmentation, a graph optimization algorithm to convert road predictions into vector line-strings, and a machine learning model for classifying road materials. Compared to OSM data, our results demonstrate significant potential for providing the latest road layouts and precise positions of road segments.