This paper introduces an algorithm that uses visual features for detecting airport runway lines. The purpose is to enable autonomous landing of unmanned aerial vehicles in the case of GPS denial, by providing runway line recognition, detection, and positioning information for the aircraft. The method uses Sobel edge detection and Hough transformation algorithms. First, it performs rough positioning of the left and right runway lines using high-level semantic understanding of the runway. Then, under the constraints of the left and right runway lines, it performs precise detection of the middle virtual lines. The article verifies the effectiveness and feasibility of the method with certain lighting conditions through experiments. Since the algorithm is based on traditional geometric information for runway line detection, it does not require expensive GPU training and reduces costs.
Geometric Feature-Based Airport Runway Line Detection
Lect. Notes Electrical Eng.
International Conference on Guidance, Navigation and Control ; 2024 ; Changsha, China August 09, 2024 - August 11, 2024
07.03.2025
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Transportation Research Record | 2013
|SAE Technical Papers | 2016