首页 > 论文 > 激光与光电子学进展 > 56卷 > 15期(pp:151006--1)

利用残差密集网络的高光谱图像分类

Hyperspectral Image Classification Based on Residual Dense Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

卷积神经网络模型能够提取图像不同层次的分层特征,提取图像包含有大量的细节信息,然而,现有方法没有充分利用网络模型提取的所有分层特征。为了充分利用所有分层特征,增强特征重利用和信息连续传递,设计了适用于高光谱图像分类的残差密集网络模型。残差密集网络结合了残差网络和密集网络,包括浅层特征提取、残差密集单元和密集特征融合三部分。利用卷积操作提取原始图像的浅层特征,将浅层特征作为残差密集单元的输入,残差密集单元的输出与下一个单元中每个卷积层的输出建立短连接,实现了信息连续传递;将两个单元提取的密集特征与浅层特征相加形成全局残差学习,实现了所有分层特征的融合,最终的融合特征用于高光谱图像分类。实验表明,本文方法用于Indian Pines数据、University of Pavia数据及Salinas数据能够分别取得98.71%、99.31%及97.91%的分类精度,有效提高了高光谱图像的分类精度,增强了分类方法的稳定性。

Abstract

A convolutional neural network (CNN) can extract hierarchical features in an image, and the extracted images include a large amount of detailed information contained in the image. However, CNN-based methods do not take full advantage of all hierarchical features extracted by the network. To make full use of all hierarchical features and enhance feature reuse and information flow, we design a residual dense network suitable for hyperspectral image classification. The residual dense network combines residual and dense networks, including shallow feature extraction, residual dense units, and dense feature fusion. Firstly, shallow features of the original image are extracted using a convolution operation, which is input to the residual dense unit. Secondly, the output of the residual dense unit establishes a shortcut connection with each convolution layer and output layer in the next unit, thereby realizing continuous information transmission. Subsequently, dense features extracted from the two units are added to the shallow features to form global residual learning, which realizes the fusion of all hierarchical features. The fused features are then used for hyperspectral image classification. Experimental results demonstrate that the proposed method can obtain 98.71%, 99.31%, and 97.91% classification accuracies on the Indian Pines, University of Pavia, and Salinas data, respectively, which effectively improves the classification accuracy of hyperspectral images and enhances the stability of classification methods.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.151006

所属栏目:图像处理

基金项目:国家自然科学基金(41801388)、河南省科技攻关计划项目(152102210014);

收稿日期:2019-01-03

修改稿日期:2019-03-06

网络出版日期:2019-08-01

作者单位    点击查看

魏祥坡:信息工程大学, 河南 郑州 450001
余旭初:信息工程大学, 河南 郑州 450001
谭熊:信息工程大学, 河南 郑州 450001
刘冰:信息工程大学, 河南 郑州 450001

联系人作者:魏祥坡(13526635671@163.com)

备注:国家自然科学基金(41801388)、河南省科技攻关计划项目(152102210014);

【1】Bioucas-Dias J M, Plaza A, Camps-Valls G et al. . Hyperspectral remote sensing data analysis and future challenges. IEEE Geoscience and Remote Sensing Magazine. 1(2), 6-36(2013).

【2】Chen Y S, Lin Z H, Zhao X et al. Deep learning-based classification of hyperspectral data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 7(6), 2094-2107(2014).

【3】Chen Y S, Zhao X and Jia X P. Spectral-spatial classification of hyperspectral data based on deep belief network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 8(6), 2381-2392(2015).

【4】Huang H, He K, Zheng X L et al. Spatial-spectral feature extraction of hyperspectral image based on deep learning. Laser & Optoelectronics Progress. 54(10), (2017).
黄鸿, 何凯, 郑新磊 等. 基于深度学习的高光谱图像空-谱联合特征提取. 激光与光电子学进展. 54(10), (2017).

【5】Hu W, Huang Y Y, Wei L et al. Deep convolutional neural networks for hyperspectral image classification. Journal of Sensors. 258619, (2015).

【6】Yan M, Zhao H D, Li Y H et al. Multi-classification and recognition of hyperspectral remote sensing objects based on convolutional neural network. Laser & Optoelectronics Progress. 56(2), (2019).
闫苗, 赵红东, 李宇海 等. 基于卷积神经网络的高光谱遥感地物多分类识别. 激光与光电子学进展. 56(2), (2019).

【7】He K M, Zhang X Y, Ren S Q et al. Deep residual learning for image recognition. [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 770-778(2016).

【8】Lu Y S, Li Y X, Liu B et al. Hyperspectral data haze monitoring based on deep residual network. Acta Optica Sinica. 37(11), (2017).
陆永帅, 李元祥, 刘波 等. 基于深度残差网络的高光谱遥感数据霾监测. 光学学报. 37(11), (2017).

【9】Wang C, Liu Y, Bai X et al. Deep residual convolutional neural network for hyperspectral image super-resolution. ∥Zhao Y, Kong X, Taubman D. Image and graphics. ICIG 2017. Lecture notes in computer science. Cham: Springer. 10668, 370-380(2017).

【10】Zhang C and Chen Y. Object detection based on hard examples mining using residual network. Laser & Optoelectronics Progress. 55(10), (2018).
张超, 陈莹. 残差网络下基于困难样本挖掘的目标检测. 激光与光电子学进展. 55(10), (2018).

【11】Zhong J. Research on semi-supervised learning method of remote sensing image based on deep neural network. Shenyang: Shenyang Aerospace University. 38-47(2018).
钟健. 基于深度神经网络的遥感图像半监督学习方法研究. 沈阳: 沈阳航空航天大学. 38-47(2018).

【12】Song W W, Li S T, Fang L Y et al. Hyperspectral image classification with deep feature fusion network. IEEE Transactions on Geoscience and Remote Sensing. 56(6), 3173-3184(2018).

【13】Zhong Z L, Li J, Luo Z M et al. Spectral-spatial residual network for hyperspectral image classification: a 3-D deep learning framework. IEEE Transactions on Geoscience and Remote Sensing. 56(2), 847-858(2018).

【14】Huang G. Liu Z, van der Maaten L, et al. Densely connected convolutional networks. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2261-2269(2017).

【15】Wang W J, Dou S G, Jiang Z M et al. A fast dense spectral-spatial convolution network framework for hyperspectral images classification. Remote Sensing. 10(7), (2018).

【16】Zhang Y L, Tian Y P, Kong Y et al. Residual dense network for image super-resolution. [C]∥2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 2472-2481(2018).

【17】Kingma D P. -01-30)[2019-01-05]. https:∥arxiv. org/abs/1412, (2017).

【18】Liu B, Yu X C, Zhang P Q et al. A semi-supervised convolutional neural network for hyperspectral image classification. Remote Sensing Letters. 8(9), 839-848(2017).

【19】Li W, Wu G D, Zhang F et al. Hyperspectral image classification using deep pixel-pair features. IEEE Transactions on Geoscience and Remote Sensing. 55(2), 844-853(2017).

引用该论文

Wei Xiangpo,Yu Xuchu,Tan Xiong,Liu Bing. Hyperspectral Image Classification Based on Residual Dense Network[J]. Laser & Optoelectronics Progress, 2019, 56(15): 151006

魏祥坡,余旭初,谭熊,刘冰. 利用残差密集网络的高光谱图像分类[J]. 激光与光电子学进展, 2019, 56(15): 151006

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF