Accuracy Assessment of Low-Cost Unmanned Aerial Vehicle (UAV) Photogrammetry

Abstract

This study aims to produce accurate geospatial 3D data from unmanned aerial vehicle (UAV) images. An image of a ≈ 0.05 km2 area of the Najran University campus in Najran, Saudi Arabia, was captured using a DJI Mavic Pro Platinum drone. Agisoft Metashape and Pix4dmapper programs were used to generate the solution. The horizontal and vertical accuracies of the obtained UAV solution were computed by comparing the coordinates of 21 ground control points (GCPs) with coordinates measured using the RTK GPS method. The accuracy of the four different GCP configurations was evaluated using both software packages. The root mean square error (RMSE) was calculated for some checkpoints. The generated model achieved the 2015 ASPRS accuracy standards for digital geospatial data, while horizontal RMSE values were 4–6 cm and vertical accuracy was 5–6 cm. The horizontal and vertical RMSE values were twice and three times the GSD, respectively.