Road Asset Geometry and Condition Data Capture

"Road Asset Geometry and Condition Data Capture” Inspection of road networks is expensive and time consuming, with 50% of the £200m spent on road maintenance in the UK in 2016 dedicated to condition monitoring (Figure 1, Table 1). Visual inspection is still the most commonly employed way of inspection for most parts of the road network. The sheer amount of lane miles of the road network renders this type of road monitoring a costly process. The ultimate goal of this proposal is to reduce the time and cost needed to perform routine drive-by, visual and conditional data capturing automatically. In this proposal, Bentley Systems (an established provided of software solutions to Highways England) and Vivacity Labs (an innovate SME with expertise in developing Machine Learning for Highways applications) have joined forces to prove a concept to automatically assess the condition of road drainage covers, barriers and poles from a vehicle mounted camera – allowing continuous inspection whenever a Highways England patrol vehicle is on the network. This proposed novel framework focuses on automating two main tasks: a) localisation of the road assets (drainage, pole and barrier) b) assessment of their condition.