Airport Detection for Fixed-Wing Unmanned Aerial Vehicle Landing Using a Hierarchical Architecture

Airport detection plays an important role in vision-based fixed-wing unmanned aerial vehicle landing. A large amount of image analysis is required for vision-based detection. This paper addresses the efficiency and difficulty of airport detection in the initial stage of landing. A hierarchical architecture and a decision criterion are proposed to quickly locate candidate airport regions. Then. the spatial-pyramid matching using sparse coding algorithm is used to obtain a more discriminative feature map representation of airports. A linear support vector machine is employed to recognize potential airports from feature maps. Several experiments are conducted to test the robustness and efficiency of the proposed algorithm. Promising results are obtained under challenging backgrounds and different weather conditions.