Visual inspection for road damages demands significant human effort. Automating these inspections would reduce costs and errors. Using photogrammetry to generate 3D models of roads has become popular thanks to advances in cameras and image processing techniques. Using UAVs, these models depend on images' capturing parameters such as height, overlap, and camera angle over the studied infrastructure. Traditionally, these flight parameters are defined on a trial-and-error basis without any systematic procedure. To fill this gap, the application of Taguchi's orthogonal arrays to calibrate the main flight parameters is proposed. To evaluate this methodology, the area and volume of pavement potholes were reconstructed from 3D models generated with UAV photographs. This article contributes with a methodology for developing 3D models and replicable for other types of infrastructure. Moreover, the results obtained allow defining a flight and image capture strategy adequate to the quality requirements of the modelling, optimising time and resources.