This project focuses on advancing civilian airport detection worldwide through the integration of optical imaging technology and the YOLOv9 deep learning architecture. Manual methods for identifying civilian airports using satellite images are slow, expensive, and prone to errors, posing challenges in urban planning, transportation management, and aviation security. To overcome these limitations, this project proposes an automated system that leverages high-resolution satellite imagery and advanced object detection algorithms. By integrating optical imaging data with the YOLOv9 model, this project enables quick and accurate detection and classification of civilian airports. With features including AI cameras, detectors, and automatic separators, this project offers a cost-effective approach to airport detection, catering to both large and small-scale facilities. By addressing the inefficiencies in current airport detection methods, this project aims to enhance, accuracy, and cost-effectiveness in civilian aviation surveillance and infrastructure planning.
Enhanced Civilian Airport Detection with Optical Imaging and YOLOv9
2024-12-07
1142198 byte
Conference paper
Electronic Resource
English