Evaluating the accuracy of vehicle tracking data obtained from Unmanned Aerial Vehicles

This paper presents a methodology for tracking moving vehicles that integrates Unmanned Aerial Vehicles with videoprocessing techniques. The authors investigated the usefulness of Unmanned Aerial Vehicles to capture reliableindividual vehicle data by using GPS technology as a benchmark. A video processing algorithm is introduced forvehicles trajectory acquisition based on OpenCV libraries. In order to assess the accuracy of the proposed videoprocessing algorithm an instrumented vehicle was equipped with a high precision GPS and video capture experimentswere performed in two case studies. From the field, about 24,000 positioning data were acquired for the analysis. Theresults of these experiments highlight the versatility of the UAV technology combined with video processing techniquein monitoring real traffic data.