Hyperspectral Remote Sensing Image Classification Based on Three-Dimensional Convolution Neural Network Combined with Conditional Random Field Optimization

doi:10.3788/AOS201838.0828001

CIOMP OpenIR

	Hyperspectral Remote Sensing Image Classification Based on Three-Dimensional Convolution Neural Network Combined with Conditional Random Field Optimization
	Li, Zhuqiang; Zhu, Ruifei; Gao, Fang; Meng, Xiangyu; An, Yuan; Zhong, Xing
	2018
发表期刊	Guangxue Xuebao/Acta Optica Sinica
ISSN	2532239
卷号	38 期号:8
摘要	Hyperspectral remote sensing image classification is usually based on the spectral features of objects, but there are plenty of spatial informations in the images. The effective use of spatial information can significantly improve the image classification effect. Because of the special structure of convolution neural network (CNN), CNN has been successfully applied in the field of image classification, and has a good effect on the classification of two-dimensional images. How to improve classification performance through deep learning combined with spatial-spectral information is a key point. Combining the spatial features and spectral information of hyperspectral images, we have developed a three-dimensional convolution neural network model (3D-CNN) for hyperspectral pixel classification, and the multi labels conditional random field is optimized on the basis of the initial classification. Three general open hyperspectral datasets (Indian Pines dataset, Pavia University dataset, Pavia Center dataset) are selected for testing. Experiments show that the accuracy is greatly improved after the classification optimization, the overall accuracy can reach 98%, and the Kappa coefficient reaches 97.2%. 2018, Chinese Lasers Press. All right reserved.
关键词	Classification (of information) Convolution Deep learning Hyperspectral imaging Image classification Image enhancement Independent component analysis Random processes Remote sensing Spectroscopy Statistical tests
DOI	10.3788/AOS201838.0828001
收录类别	EI
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/60692
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	Li, Zhuqiang,Zhu, Ruifei,Gao, Fang,et al. Hyperspectral Remote Sensing Image Classification Based on Three-Dimensional Convolution Neural Network Combined with Conditional Random Field Optimization[J]. Guangxue Xuebao/Acta Optica Sinica,2018,38(8).
APA	Li, Zhuqiang,Zhu, Ruifei,Gao, Fang,Meng, Xiangyu,An, Yuan,&Zhong, Xing.(2018).Hyperspectral Remote Sensing Image Classification Based on Three-Dimensional Convolution Neural Network Combined with Conditional Random Field Optimization.Guangxue Xuebao/Acta Optica Sinica,38(8).
MLA	Li, Zhuqiang,et al."Hyperspectral Remote Sensing Image Classification Based on Three-Dimensional Convolution Neural Network Combined with Conditional Random Field Optimization".Guangxue Xuebao/Acta Optica Sinica 38.8(2018).

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Hyperspectral Remote（1448KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文