Radar Remote Sensing Data Augmentation Method Based on Generative Adversarial Network

Authors

Xu Kang, Beijing Institute of Remote Sensing Equipment, Beijing 100854, China;Follow
Xiaofeng Zhang, Beijing Institute of Remote Sensing Equipment, Beijing 100854, China;

Abstract

Abstract: In the research field of radar remote sensing, both the completeness and diversity of radar data samples cannot meet the requirement of effective training of deep learning models, and the models are prone to over-fitting, which significantly limits the wide application of deep learning techniques in this field. Targeting on the needs of intelligent application in radar remote sensing, a microwave imaging radar suited data augmentation method is proposed to solve the issue of insufficient radar data samples by leveraging the general framework of generative adversarial network. Aiming at the features of radar samples being not obvious, the label smoothing regularization technique is utilized to automatically classify the augmentated radar samples. The augmentated samples together with the real samples are collaboratively used to implement the robust training of deep learning models. The proposed method is verified by the experiments based on the extensive open-sourse radar remote sensing data.

Recommended Citation

Kang, Xu and Zhang, Xiaofeng (2022) "Radar Remote Sensing Data Augmentation Method Based on Generative Adversarial Network," Journal of System Simulation: Vol. 34: Iss. 4, Article 27.
DOI: 10.16182/j.issn1004731x.joss.20-0953
Available at: https://dc-china-simulation.researchcommons.org/journal/vol34/iss4/27

First Page

920

Revised Date

2021-01-30

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.20-0953

Last Page

927

CLC

TP391.9

Recommended Citation

Xu Kang, Xiaofeng Zhang. Radar Remote Sensing Data Augmentation Method Based on Generative Adversarial Network[J]. Journal of System Simulation, 2022, 34(4): 920-927.

DOI

10.16182/j.issn1004731x.joss.20-0953