Crowd-Sourced Road Quality Mapping in the Developing World

TL;DR

This paper introduces a crowd-sourced method for mapping road quality in developing countries, addressing data scarcity and leveraging deep learning, with implications for infrastructure planning and conservation.

Contribution

It presents a novel crowd-sourced approach for assessing road quality and discusses transferability of deep learning methods across different domains.

Findings

Effective crowd-sourced data collection for road quality mapping

Insights into transferability of deep learning models in this context

Identification of key challenges and opportunities in the approach

Abstract

Road networks are among the most essential components of a country's infrastructure. By facilitating the movement and exchange of goods, people, and ideas, they support economic and cultural activity both within and across borders. Up-to-date mapping of the the geographical distribution of roads and their quality is essential in high-impact applications ranging from land use planning to wilderness conservation. Mapping presents a particularly pressing challenge in developing countries, where documentation is poor and disproportionate amounts of road construction are expected to occur in the coming decades. We present a new crowd-sourced approach capable of assessing road quality and identify key challenges and opportunities in the transferability of deep learning based methods across domains.