Pavement condition assessment using ground penetrating Radar

Past approaches to the interpretation of sensor data, such as ground penetrating radar (GPR) condition assessment data, using artificial neural networks (ANNs) have been one-step monolithic methods. These methods involve using a single neural network to map raw CPR data directly to properties of the environment, such as pavement layer thickness. This paper describes a segmented approach to pavement condition assessment using ANNs that follows the steps performed during manual interpretation. It will be shown that following these steps with ANNs provides better condition assessment results than performing assessment in one step with a single ANN. For the investigation described, the segmented approach determined asphalt layer thickness values approximately two times more accurately than the one-step approach performed on the same data.