Mapping of road surface condition features for unpaved roads through the use of remotely sensed imagery from unmanned aerial vehicle

Evaluating road surface conditions is a crucial aspect of the operation and maintenance of road infrastructure. This issue is particularly pronounced for unpaved roads, which lack protective hard surfaces like concrete or asphalt. New methods are emerging for identifying and extracting road surface condition parameters from remotely sensed imagery. Accordingly, this study demonstrates an approach to identify and extract road surface condition parameters from remotely sensed images obtained from unpaved roads with distinctive environmental characteristics. An Unmanned Aerial Vehicle (UAV) was employed to capture images of unpaved roads, which were then pre-processed and analysed by constructing a digital elevation model (DEM) and orthomosaic. The processed imagery was validated against conventional field measurements of road defects. The number of defects identified and their severity was comparable for both methods. The defect counts were similar in all cases except for one, which varied between the two approaches. The predictions of defect severity, expressed as percent count, were accurate -vegetation encroachment had the highest rate at 100 %, while depression had the lowest at 25 %. These findings highlight thepotential of using remotely sensed imagery from UAVS to identify, extract, and measure road surface condition parameters for unpaved roads. The results can assist road agencies in the country in promoting low-cost and effective road maintenance operations.