Aircraft Fuselage Defect Detection using Deep Neural Networks
This addresses the need for efficient and accurate maintenance inspections in aviation safety, though it is incremental as it applies existing DNN methods to a new domain.
The paper tackles automatic defect detection in aircraft fuselage images using deep neural networks, achieving over 96% accuracy with a processing time of around 15 seconds per high-resolution image.
To ensure flight safety of aircraft structures, it is necessary to have regular maintenance using visual and nondestructive inspection (NDI) methods. In this paper, we propose an automatic image-based aircraft defect detection using Deep Neural Networks (DNNs). To the best of our knowledge, this is the first work for aircraft defect detection using DNNs. We perform a comprehensive evaluation of state-of-the-art feature descriptors and show that the best performance is achieved by vgg-f DNN as feature extractor with a linear SVM classifier. To reduce the processing time, we propose to apply SURF key point detector to identify defect patch candidates. Our experiment results suggest that we can achieve over 96% accuracy at around 15s processing time for a high-resolution (20-megapixel) image on a laptop.