Automated Multi-Camera Inspection System for Aircraft

In this paper, we present the development of an automated visual inspection system for detecting defects on the upper airframe surface. The system employs a multi-camera PTZ system to synchronously capture and process images at designated regions. Developed software handles path planning and camera localization, while a hybrid-AI framework is incorporated to detect various defect-types, such as hairline cracks, loose screws and bird strike damage. The demonstration showcases the detection capabilities and prototype functionalities on a large aircraft model, furnished with a user interface to run system features and visualize results. To support this work, performance testing is provided against relevant models.