Crowd-Sourced Road Quality Mapping in the Developing World
This work is significant for developing countries, where up-to-date road quality mapping is crucial for land use planning and conservation, and where significant road construction is anticipated.
This paper addresses the problem of mapping road quality in developing countries, where documentation is often poor. It proposes a crowd-sourced approach to assess road quality and discusses challenges and opportunities for transferring deep learning methods across different domains in this context.
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.