Target Recognition in SAR Images by Deep Learning with Training Data Augmentation
Sensors · 13.01.2023 · 23 (2) · 941
DOI: 10.3390/s23020941 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 13.01.2023. Verfasst von Zhe Geng und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China. Die Arbeit wurde bisher 66-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation from Jiangsu Province.
Abstract (Originalsprache)
Mass production of high-quality synthetic SAR training imagery is essential for boosting the performance of deep-learning (DL)-based SAR automatic target recognition (ATR) algorithms in an open-world environment. To address this problem, we exploit both the widely used Moving and Stationary Target Acquisition and Recognition (MSTAR) SAR dataset and the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset, which consists of selected samples from the MSTAR dataset and their computer-generated synthetic counterparts. A series of data augmentation experiments are carried out. First, the sparsity of the scattering centers of the targets is exploited for new target pose synthesis. Additionally, training data with various clutter backgrounds are synthesized via clutter transfer, so that the neural networks are better prepared to cope with background changes in the test samples. To effectively augment the synthetic SAR imagery in the SAMPLE dataset, a novel contrast-based data augmentation technique is proposed. To improve the robustness of neural networks against out-of-distribution (OOD) samples, the SAR images of ground military vehicles collected by the self-developed MiniSAR system are used as the training data for the adversarial outlier exposure procedure. Simulation results show that the proposed data augmentation methods are effective in improving both the target classification accuracy and the OOD detection performance. The purpose of this work is to establish the foundation for large-scale, open-field implementation of DL-based SAR-ATR systems, which is not only of great value in the sense of theoretical research, but is also potentially meaningful in the aspect of military application.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China.
- School of Computer Engineering, Nanjing Institute of Technology, Nanjing 211167, China.
ORCID-Profile: Zhe Geng
Förderung
- Natural Science Foundation from Jiangsu Province
Zitieren
APA
Geng, Z., Xu, Y., Wang, B. N., Yu, X., Zhu, D. Y., & Zhang, G. (2023). Target Recognition in SAR Images by Deep Learning with Training Data Augmentation. Sensors, 23(2), 941. https://doi.org/10.3390/s23020941
Vancouver
Geng Z, Xu Y, Wang BN, Yu X, Zhu DY, Zhang G. Target Recognition in SAR Images by Deep Learning with Training Data Augmentation. Sensors. 2023;23(2):941. doi:10.3390/s23020941
BibTeX
@article{Geng2023,
author = {Geng, Zhe and Xu, Ying and Wang, Bei-Ning and Yu, Xiang and Zhu, Dai-Yin and Zhang, Gong},
title = {Target Recognition in SAR Images by Deep Learning with Training Data Augmentation},
journal = {Sensors},
year = {2023},
volume = {23},
number = {2},
pages = {941},
doi = {10.3390/s23020941}
}
EUVIMED