Recently, substantial progress has been made towards designing,
building and test-flying remotely piloted Micro Air Vehicles
(MAVs). This progress in overcoming the aerodynamic obstacles to
flight at very small scales has, unfortunately, not been matched by
similar progress in autonomous MAV flight. Thus, we propose a robust,
vision-based horizon detection algorithm as the first step towards
autonomous MAVs. In this paper, we first motivate the use of computer
vision for the horizon detection task by examining the flight of birds
(biological MAVs) and considering other practical factors. We then
describe our vision-based horizon detection algorithm, which has been
demonstrated at 30Hz with over 99.9% correct horizon identification,
over terrain that includes roads, buildings large and small, meadows,
wooded areas, and a lake. We conclude with some sample horizon
detection results and preview a companion paper [4], where the work
discussed here forms the core of a complete autonomous flight
stability system.
|
