收藏本站
《第37届中国控制会议论文集(G)》2018年
收藏 | 手机打开
二维码
手机客户端打开本文

Hyperspectral Remote Sensing Image Classification Based on Convolutional Neural Network

Xiangyang Dai  Wei Xue  
【摘要】:Remote sensing hyperspectral imaging can obtain rich spectral information of terrestrial objects, which allows the indistinguishable matter in the traditional wideband remote sensing to be distinguished in hyperspectral remote sensing.Hyperspectral image has the characteristics of "combining image with spectrum". Making full use of spectral information and spatial information in hyperspectral image is the premise of obtaining accurate classification results. At present, most of hyperspectral data feature extraction algorithms mainly utilize local spatial information in the same channel and spectral information in the same spatial location of different channels. However, these methods require a large amount of prior knowledge, it is difficult to fully grasp the hyperspectral data of all spatial and spectral information, and the model generalization ability is poor. With the development of deep learning, convolutional neural network shows superior performance in all kinds of visual tasks, especially in the two-dimensional image classification, and could get a high classification accuracy. In this paper, an image classification method based on three-dimensional convolution neural network is proposed based on the structural properties of hyperspectral data. In the proposed method, first the stereo image blocks of hyperspectral data are intercepted, then multi-layer convolution and pooling operation of extracted blocks by convolutional neural network are implemented to obtain the essential information of hyperspectral data, finally the classification of hyperspectral data is completed. The experimental results show the proposed method could provide better feature expression and classification accuracy for hyperspectral image.

【相似文献】
中国期刊全文数据库 前10条
1 ;Exposition As Beautiful As Brocade[J];人与自然;1999年02期
2 雷鸣;;A Tentative Analysis on Two Versions of EMMA at the Semantic Level[J];校园英语;2015年09期
3 ;Information for Authors[J];Journal of Zhejiang University-Science A(Applied Physics & Engineering);2017年11期
4 ;Chinese Journal of Polymer Science[J];Chinese Journal of Polymer Science;2016年05期
5 ;Information for Authors[J];Frontiers of Information Technology & Electronic Engineering;2015年06期
6 ;Aims and Scope[J];Chinese Journal of Polymer Science;2015年06期
7 Zhao Yang;;The New Bike Sharing A Concept for Urban Commuters[J];Voice of Friendship;2017年02期
8 ;Information for Authors[J];Journal of Zhejiang University-Science A(Applied Physics & Engineering);2013年01期
9 ;Information for Authors[J];Journal of Zhejiang University-Science C(Computers & Electronics);2012年04期
10 ;Information for Authors[J];Journal of Zhejiang University-Science A(Applied Physics & Engineering);2011年04期
中国重要会议论文全文数据库 前10条
1 Xiangyang Dai;Wei Xue;;Hyperspectral Remote Sensing Image Classification Based on Convolutional Neural Network[A];第37届中国控制会议论文集(G)[C];2018年
2 李石洋;刘耀辉;万雅娟;杜明娟;李鸿鹭;张翠竹;曹又佳;;Guanine nucleotide exchange factor Vav1 plays a distinguished role in T-cell calcium signaling by binding to Calmodulin[A];生命的分子机器及其调控网络——2012年全国生物化学与分子生物学学术大会摘要集[C];2012年
3 ;Traditional Chinese Medicine(TCM)[A];2008全国消化肿瘤新技术治疗研讨会论文汇编[C];2008年
4 ;Speech at the Banquet of Beijing Forum 2006[A];文明的和谐与共同繁荣:对人类文明方式的思考——北京论坛(2006)论文选集[C];2006年
5 ;A Mode Based De-convolution Algorithm in CT Cerebral Tumor Perfusion Image[A];第24届中国控制与决策会议论文集[C];2012年
6 A:Kern;A.A.Coelho;R.W.Cheary;;CONVOLUTION BASED PROFILE FITTING[A];第八届全国X射线衍射学术会议论文集[C];2003年
7 ;The Research of Ultra-wideband Narrow Pulse Circuit Based on Avalanche Effect Theory[A];第二十九届中国控制会议论文集[C];2010年
8 Chey Jae-Won;;The Universal Values and the Development Trend of Civilization[A];文明的和谐与共同繁荣:文明的普遍价值和发展趋向——北京论坛(2008)论文选集[C];2008年
9 Hai Sha;Huaming Chen;Zhicheng Lv;Guozhu Zhang;Gang Ou;;Dynamic Delay Generation Method Based on Variable Fractional Delay Filter[A];第五届中国卫星导航学术年会论文集-S7 北斗/GNSS用户终端技术[C];2014年
10 王野秋;;A New Accurately Locating Algorithm for Vehicles Positioning System Based on Ultra-wideband[A];2006通信理论与技术新进展——第十一届全国青年通信学术会议论文集[C];2006年
 快捷付款方式  订购知网充值卡  订购热线  帮助中心
  • 400-819-9993
  • 010-62791813
  • 010-62985026