Rapid detection and social media supervision of runway incursion based on deep learning. (2018)

• Record Type: Journal Article
• Authors: Cai, Chengtao; Wu, Kejun; Yan, Yongjie
• Is Part Of: International journal of innovative computing and applications. Volume 9:Number 2(2018)
• Page Start: 98
• Page End: 106
• Publication Date: 2018
• Subjects: runway incursion -- social media supervision -- target detection -- deep learning -- you only look once -- YOLO; Evolutionary computation -- Periodicals; Neural networks (Computer science) -- Periodicals; Genetic programming (Computer science) -- Periodicals; Biologically-inspired computing -- Periodicals; Swarm intelligence -- Periodicals; Quantum computers -- Periodicals; 006.3
• Languages: English
• ISSNs: 1751-648X

Abstract

In order to solve the problem of runway incursion, which is a serious threat to the safety of the aviation industry, we analyse social media data which shows people's concern about safety of the aviation industry, we analyse social media data which shows people's concern about airport runway incursion. We take the target of aircrafts and vehicles on the runway as the research objects, and put forward the airport target detection method based on optimised YOLO framework. The simulation experiment is carried out by constructing the airport simulation environment. We study the airport target detection in single target, multi-target and extreme environment target, and focus on the influence of the overlooking angle of the monitoring system on the detection results. We selected Tiny YOLO and Faster R-CNN as the control group to demonstrate the performance of the optimised YOLO detector at speed. The experimental result shows that the airport target detection based on optimised YOLO has excellent fastness and accuracy.