SAR Automatic Target Recognition Using a Roto-Translational Invariant Wavelet-Scattering Convolution Network

The algorithm of synthetic aperture radar (SAR) for automatic target recognition consists of two stages: feature extraction and classification. The quality of extracted features has significant impacts on the final classification performance. This paper presents a SAR automatic target classification...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2018-04, Vol.10 (4), p.501
Main Authors: Wang, Haipeng, Li, Suo, Zhou, Yu, Chen, Sizhe
Format: Article
Language:English
Subjects:
automatic target classification (ATR)
Automatic target recognition
Classification
Convolution
Electromagnetic wave filters
Feature extraction
Feature recognition
roto-translation invariance
Scattering
scattering convolution network
Support vector machines
Synthetic aperture radar
Target acquisition
Target recognition
Wavelet analysis
wavelet transform
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The algorithm of synthetic aperture radar (SAR) for automatic target recognition consists of two stages: feature extraction and classification. The quality of extracted features has significant impacts on the final classification performance. This paper presents a SAR automatic target classification method based on the wavelet-scattering convolution network. By introducing a deep scattering convolution network with complex wavelet filters over spatial and angular variables, robust feature representations can be extracted across various scales and angles without training data. Conventional dimension reduction and a support vector machine classifier are followed to complete the classification task. The proposed method is then tested on the moving and stationary target acquisition and recognition (MSTAR) benchmark data set and achieves an average accuracy of 97.63% on the classification of ten-class targets without data augmentation.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs10040501