Deep Learning Method for Hyperspectral Remote Sensing Images with Small Samples

Authors

Xiangbin Shi, 1. School of Computer, Shenyang Aerospace University, Shenyang 110136, China;;2. College of Information Science and Technology, Liaoning University, Shenyang 110036, China;
Zhong Jian, 1. School of Computer, Shenyang Aerospace University, Shenyang 110136, China;;
Cuiwei Liu, 1. School of Computer, Shenyang Aerospace University, Shenyang 110136, China;;
Liu Fang, 1. School of Computer, Shenyang Aerospace University, Shenyang 110136, China;;
Deyuan Zhang, 1. School of Computer, Shenyang Aerospace University, Shenyang 110136, China;;

Abstract

Abstract: In order to solve the problem of large information dimension and fewer labeled training samples of hyperspectral remote sensing images, this paper proposes a hyperspectral remote sensing image classification framework HSI-CNN, which reduces the number of model parameters while maintaining the depth of neural network. Image pattern invariance and spectral channel contribution rate are analyzed, and the spectral redundancy information is reduced by principal component analysis. A full convolution neural network structure suitable for small sample hyperspectral remote sensing images is designed and the amount of network parameters is effectively reduced. Three kinds of HSI-CNN structures are proposed and compared. The experimental results on Pavia University and Salinas hyperspectral remote sensing data sets show that HSI-CNN can extract the spectral feature information only by using a small amount of training samples effectively.

Recommended Citation

Shi, Xiangbin; Jian, Zhong; Liu, Cuiwei; Fang, Liu; and Zhang, Deyuan (2019) "Deep Learning Method for Hyperspectral Remote Sensing Images with Small Samples," Journal of System Simulation: Vol. 30: Iss. 7, Article 39.
DOI: 10.16182/j.issn1004731x.joss.201807039
Available at: https://dc-china-simulation.researchcommons.org/journal/vol30/iss7/39

First Page

2744

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.201807039

Last Page

2752

CLC

TP391.4

Recommended Citation

Shi Xiangbin, Zhong Jian, Liu Cuiwei, Liu Fang, Zhang Deyuan. Deep Learning Method for Hyperspectral Remote Sensing Images with Small Samples[J]. Journal of System Simulation, 2018, 30(7): 2744-2752.

DOI

10.16182/j.issn1004731x.joss.201807039