Novel view synthesis with compressed sensing as data augmentation for SAR ATR

被引：1

作者：

Banas, Katherine M. ^{[1
]}

Hill, Tyler A. ^{[1
]}

Kreucher, Chris ^{[1
]}

Raeker, Brian O. ^{[1
]}

Simpson, Kyle ^{[2
]}

Weeks, Kirk ^{[2
]}

机构：

[1] KBR Inc, 900 Victors Way, Ann Arbor, MI 48108 USA

[2] Signature Res Inc, 2045 Fountain Profess Ct, Navarre, FL 32566 USA

来源：

ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXX | 2023年 / 12520卷

关键词：

novel view synthesis; data augmentation; synthetic aperture radar; automatic target recognition; basis pursuit denoising; transfer learning; deep learning; MSTAR dataset;

D O I：

10.1117/12.2664250

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This work investigates the application of compressed sensing algorithms to the problem of novel view synthesis in synthetic aperture radar (SAR). We demonstrate the ability to generate new images of a SAR target from a sparse set of looks at said target, and we show that this can be used as a data augmentation technique for deep learning-based automatic target recognition (ATR). The newly synthesized views can be used both to enlarge the original, sparse training set, and in transfer learning as a source dataset for initial training of the network. The success of the approach is quantified by measuring ATR performance on the MSTAR dataset

引用

页数：8

共 14 条

[1] Enhancing Sparsity by Reweighted l1 Minimization
Candes, Emmanuel J.
Wakin, Michael B.
Boyd, Stephen P.
[J]. JOURNAL OF FOURIER ANALYSIS AND APPLICATIONS, 2008, 14 (5-6) : 877 - 905
[2] Target Classification Using the Deep Convolutional Networks for SAR Images
Chen, Sizhe
Wang, Haipeng
Xu, Feng
Jin, Ya-Qiu
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (08): : 4806 - 4817
[3] Coleman CM, 2012, 2012 IEEE STATISTICAL SIGNAL PROCESSING WORKSHOP (SSP), P544, DOI 10.1109/SSP.2012.6319755
[4] Zeiler MD, 2012, Arxiv, DOI arXiv:1212.5701
[5] Eker T., 2021, THESIS
[6] Bridging a Gap in SAR-ATR: Training on Fully Synthetic and Testing on Measured Data
Inkawhich, Nathan
Inkawhich, Matthew J.
Davis, Eric K.
Majumder, Uttam K.
Tripp, Erin
Capraro, Chris
Chen, Yiran
[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 2942 - 2955
[7] Realistic SAR Data Augmentation using Machine Learning Techniques
Lewis, Benjamin
DeGuchy, Omar
Sebastian, Joseph
Kaminski, John
[J]. ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY XXVI, 2019, 10987
[8] Data Augmentation Based on Attributed Scattering Centers to Train Robust CNN for SAR ATR
Lv, Junta
Liu, Yue
[J]. IEEE ACCESS, 2019, 7 : 25459 - 25473
[9] Masarik M., 2022, SYNTHETIC APERTURE R
[10] Standard SAR ATR evaluation experiments using the MSTAR public release data set
Ross, T
Worrell, S
Velten, V
Mossing, J
Bryant, M
[J]. ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY V, 1998, 3370 : 566 - 573

← 1 2 →