3维卷积递归神经网络的高光谱图像分类方法

关世豪; 杨桄; 李豪; 付严宇

doi:doi:10.7510/jgjs.issn.1001-3806.2020.04.015

激光技术, 2020, 44 (4): 485, 网络出版: 2020-07-16

3维卷积递归神经网络的高光谱图像分类方法

Hyperspectral image classification based on 3-D convolutional recurrent neural network

论文大纲

关世豪杨桄李豪付严宇

作者单位

空军航空大学，长春 130022

摘要

为了针对高光谱图像中空间信息与光谱信息的不同特性进行特征提取，提出一种3维卷积递归神经网络(3-D-CRNN)的高光谱图像分类方法。首先采用3维卷积神经网络提取目标像元的局部空间特征信息，然后利用双向循环神经网络对融合了局部空间信息的光谱数据进行训练，提取空谱联合特征，最后使用Softmax损失函数训练分类器实现分类。3-D-CRNN模型无需对高光谱图像进行复杂的预处理和后处理，可以实现端到端的训练，并且能够充分提取空间与光谱数据中的语义信息。结果表明，与其它基于深度学习的分类方法相比，本文中的方法在Pavia University与Indian Pines数据集上分别取得了99.94%和98.81%的总体分类精度，有效地提高了高光谱图像的分类精度与分类效果。该方法对高光谱图像的特征提取具有一定的启发意义。

Abstract

In order to extract the features of spatial information and spectral information in hyperspectral image, a 3-D convolutional recursive neural network (3-D-CRNN) hyperspectral image classification method was proposed. Firstly, 3-D convolutional neural network was used to extract local spatial feature information of target pixel, then bidirectional circular neural network was used to train spectral data fused with local spatial information, and joint features of spatial spectrum were extracted. Finally, Softmax loss function was used to train classifier to realize classification. The 3-D-CRNN model did not require complex pre-processing and post-processing of hyperspectral image, which can realize end-to-end training and fully extract semantic information in spatial and spectral data. Experimental results show that compared with other deep learning-based classification methods, the overall classification accuracy of the method in this paper is 99.94% and 98.81% respectively in Pavia University and Indian Pines data set, effectively improving the classification accuracy and efficiency of hyperspectral image. This method has some enlightening significance for feature extraction of hyperspectral image.

参考文献

[1] BIOUCAS-DIAS J M, PLAZA A, CAMPS-VALLS G, et al. Hyperspectral remote sensing data analysis and future challenges［J］. IEEE Geoscience and Remote Sensing Magazine, 2013, 1(2):6-36.

[2] DALE L M, THEWIS A, BOUDRY C, et al. Hyperspectral imaging applications in agriculture and agro-food product quality and safety control: A review［J］. Applied Spectroscopy Reviews, 2013, 48(2):142-159.

[3] GHIYAMAT A, SHAFRI H Z M. A review on hyperspectral remote sensing for homogeneous and heterogeneous forest biodiversity assessment［J］. International Journal of Remote Sensing, 2010, 31(7):1837-1856.

[4] van der MEER F D, van dwe WERFF H M A, van RUITENBEEK F J A, et al. Multi- and hyperspectral geologic remote sensing: A review［J］. International Journal of Applied Earth Observation & Geoinformation, 2012, 14(1):112-128.

[5] ELIZABETH A W，SHAROLYN A，MICHAIL F，et al. Supporting global environmental change research: A review of trends and know-ledge gaps in urban remote sensing［J］. Remote Sensing, 2014, 6(5):3879-3905.

[6] YUEN P W, RICHARDSON M. An introduction to hyperspectral imaging and its application for security, surveillance and target acquisition［J］. The Imaging Science Journal, 2010, 58(5):241-253.

[7] PILORGET C, BIBRING J P. Automated algorithms to identify and locate grains of specific composition for NIR hyperspectral microscopes: Application to the micromega instrument onboard exomars［J］. Planetary and Space Science, 2014, 99:7-18.

[8] HU W, HUANG Y Y, WEI L, et al. Deep convolutional neural networks for hyperspectral image classification［J］. Journal of Sensors, 2015(10): 1-12.

[9] YANG J, ZHAO Y Q, CHAN C W. Learning and transferring deep joint spectral-spatial features for hyperspectral classification［J］. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(8):4729-4742.

[10] HE M, LI B, CHEN H. Multi-scale 3-D deep convolutional neural network for hyperspectral image classification［C］//2017 IEEE International Conference on Image Processing (ICIP). New York,USA:IEEE, 2017:57-61.

[11] LI G D, ZHANG Ch J, GAO F, et al. Doubleconvpool-structured 3D-CNN for hyperspectral remote sensing image classification［J］. Journal of Image and Graphics, 2019, 24(4): 639-654(in Chin-ese).

[12] WU H, SAURABH P. Convolutional recurrent neural networks for hyperspectral data classification［J］. Remote Sensing, 2017, 9(3): 298-303.

[13] MOU L, GHAMISI P, ZHU X X. Unsupervised spectral-spatial feature learning via deep residual conv-deconv network for hyperspectral image classification［J］. IEEE Transactions on Geoscience and Remote Sensing, 2017, 56(1):391-406.

[14] MOU L, GHAMISI P, ZHU X X. Deep recurrent neural networks for hyperspectral image classification［J］. IEEE Transaction Geoscience and Remote Sensing, 2017, 55(7):3639-3655.

[15] ZHANG B. Hyperspectral image classification and target detection[M]. Beijing: Science Press, 2011: 9-10(in Chinese).

[16] DU P J, XIA J Sh, XUE Zh H, et al. Review of hyperspectral remote sensing image classification［J］. Journal of Remote Sensing, 2016, 20(2): 236-256(in Chinese).

[17] QI Y F, MA Zh Y. Hyperspectral image classification method based on neighborhood speetra and probability cooperative representation［J］.Laser Technology, 2019,43(4):448-452(in Chinese).

[18] ZHANG H K, LI Y, JIANG Y N. Deep learning for hyperspectral imagery classification: The state of the art and prospects［J］. Acta Automatia Sinica, 2018, 44(6): 961-977(in Chinese).

[19] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition［J］. Computer Science, 2014(9):34-37.

[20] LIU J. Hyperspectral image classification based on long short term memory network［D］. Xi’an：Xidian University, 2018: 19-21(in Chinese).

关世豪, 杨桄, 李豪, 付严宇. 3维卷积递归神经网络的高光谱图像分类方法[J]. 激光技术, 2020, 44(4): 485. GUAN Shihao, YANG Guang, LI Hao, FU Yanyu. Hyperspectral image classification based on 3-D convolutional recurrent neural network[J]. Laser Technology, 2020, 44(4): 485.

3维卷积递归神经网络的高光谱图像分类方法

关于本站 Cookie 的使用提示

全站搜索

3维卷积递归神经网络的高光谱图像分类方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索