Road Mapping in Low Data Environments with OpenStreetMap

TL;DR

This paper explores the use of high-resolution satellite imagery and OpenStreetMap data with deep learning to map roads in low-data environments, highlighting challenges and the importance of local training data.

Contribution

It demonstrates the utility and limitations of OpenStreetMap data combined with satellite imagery for road mapping, emphasizing the need for region-specific training data.

Findings

OpenStreetMap data can aid road classification but has limitations.

Model performance drops with occlusion and cross-region application.

Local training data improves classification reliability.

Abstract

Roads are among the most essential components of any country's infrastructure. By facilitating the movement and exchange of people, ideas, and goods, they support economic and cultural activity both within and across local and international borders. A comprehensive, up-to-date mapping of the geographical distribution of roads and their quality thus has the potential to act as an indicator for broader economic development. Such an indicator has a variety of high-impact applications, particularly in the planning of rural development projects where up-to-date infrastructure information is not available. This work investigates the viability of high resolution satellite imagery and crowd-sourced resources like OpenStreetMap in the construction of such a mapping. We experiment with state-of-the-art deep learning methods to explore the utility of OpenStreetMap data in road classification and segmentation tasks. We also compare the performance of models in different mask occlusion scenarios as well as out-of-country domains. Our comparison raises important pitfalls to consider in image-based infrastructure classification tasks, and shows the need for local training data specific to regions of interest for reliable performance.