Automatic Detection and Predictive Geo-location of Foreign Object Debris on Airport Runway

Abstract—This paper presents an advanced Foreign Object Debris (FOD) detection system for airport runways using YOLOv8 and a geolocation prediction model based on machine learning regression. By integrating a self- attention mechanism with CNNs, the system achieves high detection accuracy, especially for small objects under challenging weather conditions. Ablation studies show improved Mean Average Precision (mAP), and comparisons with YOLOv5, YOLOX, and YOLOv7 confirm YOLOv8's superior performance. The geolocation model further enhances practical deployment for real- world FOD detection and removal.