Implementation of a prototype for capture and digital processing of thermal images acquired from a UAV

Abstract

The present work focuses on the development of a prototype for capturing and processing thermal images from an Unmanned Aerial Vehicle (UAV). The system consists of two parts: an "air" stage installed in a DJI Phantom 3 Standard. And another programmed into a receiving PC called "ground". The “air” system is composed by a Flir Lepton thermal camera, a Raspberry Pi card and a GPS module (for georeferencing). After that the images are sent to the PC using an Ad-Hoc network. The PC performs an analysis of the information through the use of histograms and edge detection (Canny algorithm). An algorithm is obtained in order to discriminate photographs with clearly heat points. Through the use of the algorithm the probability of detecting false positives in the images is reduced avoiding a waste of time and power during the processing. Finally, to verify the correct operation of the system, the prototype was tested in adverse weather conditions (fog) in the Pululahua Volcano sector.