文献详情
Dual-Branch Deep Convolution Neural Network for Polarimetric SAR Image Classification
文献类型期刊
作者Gao, Fei[1];Huang, Teng[2];Wang, Jun[3];Sun, Jinping[4];Hussain, Amir[5];Yang, Erfu[6]
机构
通讯作者Wang, J (reprint author), Beihang Univ, Sch Elect & Informat Engn, Beijing 100191, Peoples R China.
来源信息年:2017  卷:7  期:5  
期刊信息APPLIED SCIENCES-BASEL影响因子和分区  ISSN:2076-3417
关键词polarimetric SAR images; deep convolution neural network; dual-branch convolution neural network; land cover classification
增刊正刊
摘要The deep convolution neural network (CNN), which has prominent advantages in feature learning, can learn and extract features from data automatically. Existing polarimetric synthetic aperture radar (PolSAR) image classification methods based on the CNN only consider the polarization information of the image, instead of incorporating the image's spatial information. In this paper, a novel method based on a dual-branch deep convolution neural network (Dual-CNN) is proposed to realize the classification of PolSAR images. The proposed method is built on two deep CNNs: one is used to extract the polarization features from the 6-channel real matrix (6Ch) which is derived from the complex coherency matrix. The other is utilized to extract the spatial features of a Pauli RGB (Red Green Blue) image. These extracted features are first combined into a fully connected layer sharing the polarization and spatial property. Then, the Softmax classifier is employed to classify these features. The experiments are conducted on the Airborne Synthetic Aperture Radar (AIRSAR) data of Flevoland and the results show that the classification accuracy on 14 types of land cover is up to 98.56%. Such results are promising in comparison with other state-of-the-art methods.
收录情况SCIE(WOS:000404449000015)  
所属部门电子信息工程学院
DOI10.3390/app7050447
百度学术Dual-Branch Deep Convolution Neural Network for Polarimetric SAR Image Classification
语言外文
被引频次44
人气指数71
浏览次数71
基金National Natural Science Foundation of China [61071139, 61471019, 61671035]; Aeronautical Science Foundation of China [20142051022]; Pilot Project [9140A07040515HK01009]; Scientific Research Foundation of Guangxi Education Department [KY 2015LX443]; Scientific Research and Technology Development Project of Wuzhou City, GuangXi, China [201402205]
全部评论(0 条评论)
作者其他论文

Re-scaling and adaptive stochastic resonance as a tool for weak GNSS signal acquisition.

Lang, Rongling;Li, Xinyue;Gao, Fei,等.JOURNAL OF SYSTEMS ENGINEERING AND ELECTRONICS.2016,27(2),290-296.

Special issue on image feature detection and description.

Pang, Yanwei;Cao, Xianbin;Zhang, Lei,等.NEUROCOMPUTING.2013,120(,SI),1-3.

Self-healing in fractured GaAs nanowires.

Wang, Jun;Lu, Chunsheng;Wang, Qi,等.ACTA MATERIALIA.2012,60(15),5593-5600.

A Domain Partition Model Approach to the Online Fault Recovery of FPGA-Based Reconfigurable Systems.

Shang, Lihong;Zhou, Mi;Hu, Yu,等.IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES.2011,E94A(1),290-299.

结构的概率-非概率混合可靠性模型.

王军;邱志平.航空学报.2009,30(8),1398-1404.

登录