Airport runway operations and maintenance is a critical operation in aviation industry. One of the prominent problems over years in runway maintenance is the prevention of foreign objects from runways. Though there are checks between landing and take-off, for extremely busy runways, automation of Foreign Object Debris (FOD) is a crucial need of the hour compared to manual checks. Foreign objects include any objects like empty bottles, screws or parts that has fallen out of previous flights or maintenance vehicles. Anything lies in the runway is unwanted and foreign object. This has to be detected and removed immediately. In this chapter we review the latest literature and propose a system design for automatic detection of foreign objects. This system involves quick double checking in real time using millimetre wave (MM wave) radar and edge detection from IR images. When an object is confirmed by these two methods, the object is then classified using YOLO v8 classifier. Apart from the system design we have also proved the working of YOLO in real time object detection in our tailored augmented data set. The proposed system is able to address the short comings of the existing approaches and employs state of the art techniques.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Design of a Unified Framework for Automatic Detection of FOD (Foreign Object Debris) in Airport Runways

  • K. Sornalakshmi,
  • D. Hemavathi,
  • S. Sindhu,
  • S. Srividhya

摘要

Airport runway operations and maintenance is a critical operation in aviation industry. One of the prominent problems over years in runway maintenance is the prevention of foreign objects from runways. Though there are checks between landing and take-off, for extremely busy runways, automation of Foreign Object Debris (FOD) is a crucial need of the hour compared to manual checks. Foreign objects include any objects like empty bottles, screws or parts that has fallen out of previous flights or maintenance vehicles. Anything lies in the runway is unwanted and foreign object. This has to be detected and removed immediately. In this chapter we review the latest literature and propose a system design for automatic detection of foreign objects. This system involves quick double checking in real time using millimetre wave (MM wave) radar and edge detection from IR images. When an object is confirmed by these two methods, the object is then classified using YOLO v8 classifier. Apart from the system design we have also proved the working of YOLO in real time object detection in our tailored augmented data set. The proposed system is able to address the short comings of the existing approaches and employs state of the art techniques.