Attribute Feature Perturbation-Based Augmentation of SAR Target Data
Sensors · 02.08.2024 · 24 (15) · 5006
DOI: 10.3390/s24155006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 02.08.2024. Verfasst von Rubo Jin und 4 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Science and Technology on Automatic Target Recognition, College of Electronic Science and Technology, National University …. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The science and technology innovation Program of Hunan Province.
Abstract (Originalsprache)
Large-scale, diverse, and high-quality data are the basis and key to achieving a good generalization of target detection and recognition algorithms based on deep learning. However, the existing methods for the intelligent augmentation of synthetic aperture radar (SAR) images are confronted with several issues, including training instability, inferior image quality, lack of physical interpretability, etc. To solve the above problems, this paper proposes a feature-level SAR target-data augmentation method. First, an enhanced capsule neural network (CapsNet) is proposed and employed for feature extraction, decoupling the attribute information of input data. Moreover, an attention mechanism-based attribute decoupling framework is used, which is beneficial for achieving a more effective representation of features. After that, the decoupled attribute feature, including amplitude, elevation angle, azimuth angle, and shape, can be perturbed to increase the diversity of features. On this basis, the augmentation of SAR target images is realized by reconstructing the perturbed features. In contrast to the augmentation methods using random noise as input, the proposed method realizes the mapping from the input of known distribution to the change in unknown distribution. This mapping method reduces the correlation distance between the input signal and the augmented data, therefore diminishing the demand for training data. In addition, we combine pixel loss and perceptual loss in the reconstruction process, which improves the quality of the augmented SAR data. The evaluation of the real and augmented images is conducted using four assessment metrics. The images generated by this method achieve a peak signal-to-noise ratio (PSNR) of 21.6845, radiometric resolution (RL) of 3.7114, and dynamic range (DR) of 24.0654. The experimental results demonstrate the superior performance of the proposed method.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- National Key Laboratory of Science and Technology on Automatic Target Recognition, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China.
- School of Automation and Electrical Engineering, Linyi University, Linyi 276000, China.
ORCID-Profile: Jianda Cheng
Förderung
- The science and technology innovation Program of Hunan Province
Zitieren
APA
Jin, R., Cheng, J., Wang, W., Zhang, H., & Zhang, J. (2024). Attribute Feature Perturbation-Based Augmentation of SAR Target Data. Sensors, 24(15), 5006. https://doi.org/10.3390/s24155006
Vancouver
Jin R, Cheng J, Wang W, Zhang H, Zhang J. Attribute Feature Perturbation-Based Augmentation of SAR Target Data. Sensors. 2024;24(15):5006. doi:10.3390/s24155006
BibTeX
@article{Jin2024,
author = {Jin, Rubo and Cheng, Jianda and Wang, Wei and Zhang, Huiqiang and Zhang, Jun},
title = {Attribute Feature Perturbation-Based Augmentation of SAR Target Data},
journal = {Sensors},
year = {2024},
volume = {24},
number = {15},
pages = {5006},
doi = {10.3390/s24155006}
}
EUVIMED