Determining the Location of UAVs Automatically Using Aerial or Remotely Sensed High-Resolution Images for Intelligent Navigation of UAVs at the Time of Disconnection with GPS

摘要

Currently, UAVs are being used in various industries increasingly. UAV's navigation under the conditions in which their GPS signals are disturbed is among the main discussions regarding them. In an attempt to remove this problem, several methods have been presented, which yielded good results in restricted conditions. These methods face the restrictions such as lack of moving object in the imaging range and impossibility of using various reference images, in particular satellite images. In this study, the comprehensive system has been developed that is able to use the satellite, aerial, and UAV georeferenced images as the reference image and determine UAV location by combining reference image with the area elevation model instantly. In this regard, a suitable matching algorithm has been used for matching UAV images with satellite and aerial images, which allows for determining UAV location using any relevant reference image type. According to the presence possibility of moving object in the images taken by airplane and UAV, especially in urban areas that led to error in matching process during positioning, an algorithm has been developed in this system for removing such errors. This system has been tested using aerial and satellite reference data from Bushehr port, Iran. It has been successful to locate UAV over the area with a horizontal difference less than 5 m using the coordinates obtained by UAV's GPS.