A Convolutional Neural Network with Fletcher-Reeves Algorithm for Hyperspectral Image Classification

doi:10.3390/rs11111325

	A Convolutional Neural Network with Fletcher-Reeves Algorithm for Hyperspectral Image Classification
	Chen, Chen 1; Ma, Yi 1,2; Ren, Guangbo 2
刊名	REMOTE SENSING
	2019-06
卷号	11 期号:11
关键词	convolutional neural network (CNN) Fletcher-Reeves algorithm (F-R) conjugate gradient coastal wetland classification hyperspectral imagery
ISSN号	2072-4292
DOI	10.3390/rs11111325
英文摘要	Deep learning models, especially the convolutional neural networks (CNNs), are very active in hyperspectral remote sensing image classification. In order to better apply the CNN model to hyperspectral classification, we propose a CNN model based on Fletcher-Reeves algorithm (F-R CNN), which uses the Fletcher-Reeves (F-R) algorithm for gradient updating to optimize the convergence performance of the model in classification. In view of the fact that there are fewer optional training samples in practical applications, we further propose a method of increasing the number of samples by adding a certain degree of perturbed samples, which can also test the anti-interference ability of classification methods. Furthermore, we analyze the anti-interference and convergence performance of the proposed model in terms of different training sample data sets, different batch training sample numbers and iteration time. In this paper, we describe the experimental process in detail and comprehensively evaluate the proposed model based on the classification of CHRIS hyperspectral imagery covering coastal wetlands, and further evaluate it on a commonly used hyperspectral image benchmark dataset. The experimental results show that the accuracy of the two models after increasing training samples and adjusting the number of batch training samples is improved. When the number of batch training samples is continuously increased to 350, the classification accuracy of the proposed method can still be maintained above 80.7%, which is 2.9% higher than the traditional one. And its time consumption is less than that of the traditional one while ensuring classification accuracy. It can be concluded that the proposed method has anti-interference ability and outperforms the traditional CNN in terms of batch computing adaptability and convergence speed.
资助项目	National Natural Science Foundation of China[61890964] ; National Natural Science Foundation of China[41206172] ; National Natural Science Foundation of China[41706209]
WOS关键词	SPECTRAL-SPATIAL CLASSIFICATION
WOS研究方向	Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000472648000068
内容类型	期刊论文
源URL	[http://ir.fio.com.cn:8080/handle/2SI8HI0U/24616]
专题	自然资源部第一海洋研究所
通讯作者	Ma, Yi
作者单位	1.Shandong Univ Sci & Technol, Coll Geomat, Qingdao 266590, Shandong, Peoples R China 2.Minist Nat Resources, Inst Oceanog 1, Qingdao 266061, Shandong, Peoples R China
推荐引用方式 GB/T 7714	Chen, Chen,Ma, Yi,Ren, Guangbo. A Convolutional Neural Network with Fletcher-Reeves Algorithm for Hyperspectral Image Classification[J]. REMOTE SENSING,2019,11(11).
APA	Chen, Chen,Ma, Yi,&Ren, Guangbo.(2019).A Convolutional Neural Network with Fletcher-Reeves Algorithm for Hyperspectral Image Classification.REMOTE SENSING,11(11).
MLA	Chen, Chen,et al."A Convolutional Neural Network with Fletcher-Reeves Algorithm for Hyperspectral Image Classification".REMOTE SENSING 11.11(2019).