A method of airport runway dataset construction for the visual detection algorithm

Autor:	Xiangrui Weng, Bangjun Guo
Rok vydání:	2023
Předmět:	History Computer Science Applications Education
Zdroj:	Journal of Physics: Conference Series. 2435:012016
ISSN:	1742-6596 1742-6588
DOI:	10.1088/1742-6596/2435/1/012016
Popis:	One of the key technologies for the autonomous landing of fixed-wing UAVs is runway detection and tracking. The survey reveals that there is no publicly available runway image dataset. However, we proposed a new method, which was different from the traditional dataset construction method. In this method, we innovatively combined UE4 (Unreal Engine 4) and Cesium software to construct an airport runway scene closer to the real world. And put forward our own calibration standards in the post-processing of datasets. Based on this method, we also conduct a runway dataset called RAW. Experiments show that this method can be used for Airport runway detection and algorithm validation and has a good effect on the application of visual detection algorithms from simulation to realistic scenarios.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::3da2c7930a664d7b3593139b6a74c1cc https://doi.org/10.1088/1742-6596/2435/1/012016 Zobrazit plný text záznamu