TechRxiv
bare_jrnl_new_new.pdf (2.19 MB)
0/0

Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning

Download (2.19 MB)
preprint
posted on 07.01.2020 by Zhongling Huang

The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes’ problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What’s more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%.

History

Email Address of Submitting Author

huangzhongling15@mails.ucas.ac.cn

ORCID of Submitting Author

https://orcid.org/0000-0003-2368-9229

Submitting Author's Institution

Chinese Academy of Sciences

Submitting Author's Country

China

Licence

Exports

Read the peer-reviewed publication

in IEEE Geoscience and Remote Sensing Letters

Licence

Exports