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

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 me...

Full description

Saved in:
Bibliographic Details
Published inJournal of physics. Conference series Vol. 2435; no. 1; pp. 12016 - 12023
Main Authors Weng, Xiangrui, Guo, Bangjun
Format Journal Article
LanguageEnglish
Published Bristol IOP Publishing 01.02.2023
Subjects
Aircraft landing
Airport construction
Airports
Algorithms
Cesium
Datasets
Physics
Runways
Unmanned aerial vehicles
Online AccessGet full text
ISSN1742-6588
1742-6596
1742-6596
DOI10.1088/1742-6596/2435/1/012016

Cover

More Information
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
1742-6596
DOI:10.1088/1742-6596/2435/1/012016