Shared Representation of SAR Target and Shadow Based on Multilayer Auto-encoder
Sun Zhi-jun① Xue Lei①② Xu Yang-ming①② Sun Zhi-yong①②
① (Electronic Engineering Institute, Hefei 230037, China)② (Anhui Province Key Laboratory of Electronic Restriction, Hefei 230037, China)
Guide null
Abstract Automatic Target Recognition (ATR) of Synthetic Aperture Radar (SAR) image is investigated. A SAR feature extraction algorithm based on multilayer auto-encoder is proposed. The method makes use of a probabilistic neural network, Restricted Boltzmann Machine (RBM) modeling probability distribution of environment. Through the formation of more expressive multilayer neural network, the deep learning model learns shared representation of the target and its shadow outline reflecting the target shape characteristics. Targets are classified automatically through two recognition models. The experiment results based on the MSTAR verify the effectiveness of proposed algorithm.
Key words ： SAR
Feature extraction
Multilayer auto-encoder
Shadow
Received: 2012-11-20;
Published: 2013-03-11
Cite this article:
Sun Zhi-jun,Xue Lei,Xu Yang-ming et al. Shared Representation of SAR Target and Shadow Based on Multilayer Auto-encoder[J]. JOURNAL OF RADARS, 2013, 2(2): 195-202.
[1]
Liu Xiangyang, Yang Jungang, Meng Jin, Zhang Xiao, Niu Dezhi. Sparse Three-dimensional Imaging Based on Hough Transform for Forward-looking Array SAR in Low SNR
[2]
Zeng Lina, Zhou Deyun, Li Xiaoyang, Zhang Kun. Novel SAR Target Detection Algorithm Using Free Training
[3]
Wen Gongjian, Zhu Guoqiang, Yin Hongcheng, Xing Mengdao, Yang Hu, Ma Conghui, Yan Hua, Ding Baiyuan, Zhong Jinrong. SAR ATR Based on 3D Parametric Electromagnetic Scattering Model
[4]
Wen Xuejiao, Qiu Xiaolan, You Hongjian, Lu Xiaojun. Focusing and Parameter Estimation of Fluctuating Targets in High Resolution Spaceborne SAR
[5]
Wang Siyu, Gao Xin, Sun Hao, Zheng Xinwei, Sun Xian. An Aircraft Detection Method Based on Convolutional Neural Networks in High-Resolution SAR Images
[6]
Leng Ying, Li Ning. Improved Change Detection Method for Flood Monitoring
[7]
Kang Miao, Ji Kefeng, Leng Xiangguang, Xing Xiangwei, Zou Huanxin. SAR Target Recognition with Feature Fusion Based on Stacked Autoencoder
[8]
Ji Kefeng, Wang Haibo, Leng Xiangguang, Xing Xiangwei, Kang Lihong. Spaceborne Compact Polarimetric Synthetic Aperture Radar for Ship Detection
[9]
Hong Wen. Hybrid-polarity Architecture Based Polarimetric SAR: Principles and Applications (in Chinese and in English)
[10]
Zhang Jie, Zhang Xi, Fan Chenqing, Meng Junmin. Discussion on Application of Polarimetric Synthetic Aperture Radar in Marine Surveillance
[11]
Hou Liying, Lin Yun, Hong Wen. Three-dimensional Reconstruction Method Study Based on Interferometric Circular SAR
[12]
Wang Yanfei, Liu Chang, Zhan Xueli, Han Song. Technology and Applications of UAV Synthetic Aperture Radar System
[13]
HU Chen, ZHANG Fan, LI Guojun, LI Wei, CUI Zhongma. Computation Reduction Oriented Circular Scanning SAR Raw Data Simulation on Multi-GPUs
[14]
Hu Cheng, Liu Changjiang, Zeng Tao. Bistatic Forward Scattering Radar Detection and Imaging
[15]
Hu Wenlong. Impact of Earth's Oblateness Perturbations on Geosynchronous SAR Data Focusing
2013, Vol. 2 
