Deformable kernel selection and hybrid attention fusion for airport runway foreign object debris detection

Authors:
Publisher website
Google Scholar
Abstract
The foreign object debris (FOD) on airport runways poses a serious threat to the safe operation of airports. However, accurately identifying FOD during runway inspections is challenging due to its small pixel size and irregular shape in detection images. To address this issue, we propose a FOD detection network that incorporates deformable kernel selection and multi-channel hybrid attention fusion. A deformable large kernel selection module that automatically selects suitable receptive fields is introduced to enhance the learning capability for complex shape features of FODs. Additionally, a multi-channel hybrid attention fusion feature pyramid network and a Beast-Fusion module are designed to improve the efficiency of feature transmission and detection performance across FODs of varying scales. Experimental results indicate that the proposed method achieves an average precision of 90.9% on the FOD dataset, significantly outperforming existing object detection algorithms.

This publication has 11 references indexed in Scilit: