Aircraft Fuselage Defect Detection using Deep Neural Networks

TL;DR

This paper introduces a novel deep neural network-based method for automatic aircraft fuselage defect detection, achieving high accuracy and efficiency, which enhances maintenance procedures and flight safety.

Contribution

First application of DNNs for aircraft defect detection, combining feature extraction and defect patch identification for improved accuracy and speed.

Findings

Over 96% detection accuracy

Approximately 15 seconds processing time

Effective defect patch identification

Abstract

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.