A Vision Based Emergency Forced Landing System for an Autonomous UAV

This paper introduces the forced landing problem for UAVs and presents the machine-vision based approach taken for this research. The forced landing problem, is a new field of research for UAVs and this paper will show the preliminary analysis to date. The results are based on video data collected from a series of flight trials in a Cessna 172. The aim of this research is to locate " safe " landing sites for UAV forced landings, from low quality aerial imagery. Output video image frames, will highlight the algorithm's selected safe landing locations. The algorithms for the problem use image processing techniques and neural networks for the classification problem. It should be noted that although the system is being designed primarily for the forced landing problem for UAVs, the research can also be applied to forced landings or glider applications for piloted aircraft.