Towards optimal foreign object debris detection in an airport environment

作者：

Highlights：

• Quick and accurate detection of foreign object debris on runways for fast removal.

• An AI-based framework consisting of unmanned aerial system and computer vision model.

• Open world recognition for foreign object debris detection in an airport environment.

• Problem-specific data augmentation techniques to counter bounded data sets.

• Real-world airport data experiment using AI framework helps detect new object types.

摘要

•Quick and accurate detection of foreign object debris on runways for fast removal.•An AI-based framework consisting of unmanned aerial system and computer vision model.•Open world recognition for foreign object debris detection in an airport environment.•Problem-specific data augmentation techniques to counter bounded data sets.•Real-world airport data experiment using AI framework helps detect new object types.

论文关键词：Foreign object debris,Optimal FOD detection,Hazard detection on runways,YOLO object detector,Computer vision,Data augmentation

论文评审过程：Received 13 March 2022, Revised 23 August 2022, Accepted 11 September 2022, Available online 20 September 2022, Version of Record 28 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118829