Automated Condition Survey of Low Volume Roads in Tanzania
The majority of roads in Tanzania are unpaved and rural roads.
Their condition can only be determined through a slow and expensive survey teams covering 50km a day. With a rural road network of over 100,000km it would take 10 teams over a year to determine their condition, by which stage those roads are likely to have changed to weather or traffic.
This project will explore whether machine learning and detailed satellite imagery can reduce the cost and increase the speed of road surveying to allocate funding to those roads that need it most.