SAR ATR with full-angle data augmentation and feature polymerisation

SAR ATR with full-angle data augmentation and feature polymerisation

Utilising neural networks to learn and extract valuable features has achieved satisfactory performance for synthetic aperture radar automatic target recognition (SAR ATR). However, such target recognition capability could be seriously limited by severe image rotation. To greatly improve the performa...

Full description

Bibliographic Details
Main Authors: Yikui Zhai, Hui Ma, Jian Liu, Wenbo Deng, Lijuan Shang, Bing Sun, Ziyi Jiang, Huixin Guan, Yihang Zhi, Xi Wu, Jihua Zhou
Format: Article
Language:English
Published: Wiley 2019-07-01
Series:The Journal of Engineering
Subjects:
radar imaging
synthetic aperture radar
image recognition
radar target recognition
feature extraction
object recognition
convolutional neural nets
radar computing
feature polymerisation
synthetic aperture radar automatic target recognition
target recognition capability
convolutional neural networks-based SAR ATR
full-angle rotation method
multibranch feature maps
inception-SAR NET structures
image rotation
data augmentation method
Online Access:https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0219

Internet

https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0219

Similar Items