Vision-based landing method using structured line features of runway surface for fixed-wing unmanned aerial vehicles

For the estimation problem of pose and attitude of fixed-wing unmanned aerial vehicles in the terminal landing stage, a vision-based landing method using structured line features was proposed. One forward looking camera equipped in the fixed-wing unmanned aerial vehicles was used to capture multiple pictures of the structured line features and these features were extracted automatically. 6 degrees of freedom pose and attitude parameters (pitch angle, yaw angle, roll angle, longitudinal position, lateral position and altitude) were calculated by using geometric constraint of full configuration structured line features in the earlier stage of the landing, the key parameters (pitch angle, yaw angle, lateral position and altitude) were calculated by using degenerate configuration structured line features (only the runway edges) in the final stage of the landing. In the 3D stimulation experiment, the accuracy of distance is less than 0.5 m, the accuracy of angle is less than 0.1° when the fixed-wing unmanned aerial vehicle is 200 m distant from the airport. © 2016, NUDT Press. All right reserved.