Advancing Aviation Safety and Sustainable Infrastructure: High-Accuracy Detection and Classification of Foreign Object Debris Using Deep Learning Models
Year: 2025
Type: article
Abstract: Foreign Object Debris (FOD) presents a critical threat to aviation safety, with the potential to damage aircraft and jeopardize lives. This study explores the use of Deep Convolutional Neural Networks (DCNNs) for the precise detection and classification of FOD, aiming to transform existing prevention strategies. By employing models such as Xception and YOLOv8, the system achieved detection accuracies of up to 98% on diverse datasets. The integration of AI-based approaches significantly enhances operational efficiency, contributing directly to the United Nations Sustainable Development Goals (SDGs), particularly SDG 9: Industry, Innovation, and Infrastructure: Industry, Innovation, and Infrastructure, by promoting smart, safe, and sustainable aviation systems. The findings highlight the pivotal role of innovation in strengthening critical transportation infrastructure and ensuring resilient airport operations aligned with global development goals.
Authors: Yaseen Mushtaq, Wajid Ali, Usman Ghani, Rahim Ullah Khan, Amal Kumar Adak
Institution: Air University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410741038