APPLICATION OF DEEP-LEARNING ALGORITHMS TO MSTAR DATA

被引：0

作者：

Wang, Haipeng ^{[1
]}

Chen, Sizhe ^{[1
]}

Xu, Feng ^{[1
]}

Jin, Ya-Qiu ^{[1
]}

机构：

[1] Fudan Univ, Key Lab Informat Sci Electromagnet Waves MoE, Shanghai 200433, Peoples R China

来源：

2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | 2015年

关键词：

deep learning; synthetic aperture radar; automatic target recognition; TARGET RECOGNITION; SAR; PERFORMANCE; CLASSIFIER;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, a new All-Convolutional Networks (A-ConvNets) is proposed and applied to Moving and Stationary Target Acquisition and Recognition (MSTAR) data. Conventional deep learning algorithms, especially the deep convolutional networks (ConvNets) have achieved many success state-of-art results. However, directly applying ConvNets to SAR data will yield severe overfitting because of limited data availability. The proposed A-ConvNets can significantly reduce the number of free parameters and the degree of overfitting. Average accuracy of 99.1% on classification of 10-class targets was obtained by applying A-ConvNets to MSTAR datasets.

引用

页码：3743 / 3745

页数：3

共 14 条

[1]

[Anonymous], LINCOLN LAB J

[2] Sparse Representation of Monogenic Signal: With Application to Target Recognition in SAR Images [J].

Dong, Ganggang ;

Wang, Na ;

Kuang, Gangyao .

IEEE SIGNAL PROCESSING LETTERS, 2014, 21 (08) :952-956

[3]

Geoffrey EHinton., 2012, IMPROVING NEURAL NET

[4] Reducing the dimensionality of data with neural networks [J].

Hinton, G. E. ;

Salakhutdinov, R. R. .

SCIENCE, 2006, 313 (5786) :504-507

[5] MSTAR extended operating conditions - A tutorial [J].

Keydel, ER ;

Lee, SW ;

Moore, JT .

ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY III, 1996, 2757 :228-242

[6] ImageNet Classification with Deep Convolutional Neural Networks [J].

Krizhevsky, Alex ;

Sutskever, Ilya ;

Hinton, Geoffrey E. .

COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90

[7] SAR ATR performance using a conditionally Gaussian model [J].

O'Sullivan, JA ;

DeVore, MD ;

Kedia, V ;

Miller, MI .

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2001, 37 (01) :91-108

[8] Modified Polar Mapping Classifier for SAR Automatic Target Recognition [J].

Park, Jong-Il ;

Kim, Kyung-Tae .

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2014, 50 (02) :1092-1107

[9] Performance of the extended maximum average correlation height (EMACH) filter and the polynomial distance classifier correlation filter (PDCCF) for multi-class SAR detection and classification [J].

Singh, R ;

Kumar, BVKV .

ALGORITHMS FOR SYNTHETIC APERTURE RADAR IMAGERY IX, 2002, 4727 :265-276

[10] SAR Automatic Target Recognition Using Discriminative Graphical Models [J].

Srinivas, Umamahesh ;

Monga, Vishal ;

Raj, Raghu G. .

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2014, 50 (01) :591-606

← 1 2 →