Abstract
Aircraft skin defect detection is one of the crucial steps in the regular maintenance. However, the performance of defect detection algorithms is limited by insufficient data, which makes a challenge for automated defect detection of aircraft skin. Although image generation techniques relieve the problem of insufficient defect data, they are not effective under the condition of limited original data. To tackle this issue, this paper proposes an image generation method that can obtain high-quality images of aircraft skin defects under limited data. Firstly, high-frequency skip connection (HSC) is performed in the generator to enhance the utilization of frequency information. Moreover, high-frequency features fusion blocks (HFFB) are utilized to effectively improve the high-frequency awareness of the discriminator. Meanwhile, adaptive high-dimensional diffusion (AHD) is introduced into the discriminator, which can automatically adjust the diffusion intensity according to the degree of discriminator overfitting. Finally, an aircraft skin defect dataset is constructed and a Generation-Poisson blending data augmentation method is proposed. The mAP of YOLOX trained using the augmentation dataset can reach 78.55%, which is 5.27% higher than the original data. The proposed method is capable of generating realistic and diverse images of aircraft skin defects, which significantly enhances the precision of defect detection networks in various scenes.
Funding Information
  • National Natural Science Foundation of China (61573185)
  • Hui Yan Action of China (62502010224)
  • Innovative Experiment Competition for Postgraduate Students of Nanjing University of Aeronautics and Astronautics

This publication has 31 references indexed in Scilit: