Obstacle detection around aircraft on ramps and taxiways through the use of computer vision

Abstract

Ground collisions between aircraft and other obstacles in aerodrome areas are quite common, causing a lot of inconvenience to passengers, airport operators and airlines. This paper presents an onboard non-collaborative system to detect and track generic obstacles around the wingtips of large transport aircraft when maneuvering on ramps and taxiways. The requirements of such a system are outlined and it is shown that stereo vision is the most appropriate technology for this application. Then, the stereo vision setup and its processing blocks are discussed in detail. The system has been tested successfully, using both synthetic and real images, by replicating some of the most common ground conflict scenarios in an airport environment.