Data Augmentation for Hyperspectral Image Classification With Deep CNN

Li Wei; Chen Chen; Zhang Mengmeng; Li Hengchao; Du Qian

首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Data Augmentation for Hyperspectral Image Classification With Deep CNN

【24h】

Data Augmentation for Hyperspectral Image Classification With Deep CNN

机译：深度CNN的高光谱图像分类的数据增强

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Convolutional neural network (CNN) has been widely used in hyperspectral imagery (HSI) classification. Data augmentation is proven to be quite effective when training data size is relatively small. In this letter, extensive comparison experiments are conducted with common data augmentation methods, which draw an observation that common methods can produce a limited and up-bounded performance. To address this problem, a new data augmentation method, named as pixel-block pair (PBP), is proposed to greatly increase the number of training samples. The proposed method takes advantage of deep CNN to extract PBP features, and decision fusion is utilized for final label assignment. Experimental results demonstrate that the proposed method can outperform the existing ones.

机译：卷积神经网络（CNN）已广泛用于高光谱图像（HSI）分类。当培训数据规模相对较小时，数据增强被证明是非常有效的。在这封信中，广泛的比较实验是用常见的数据增强方法进行的，这引起了观察，即常用方法可以产生有限和上升的性能。为了解决这个问题，建议将新的数据增强方法命名为像素块对（PBP），以大大增加训练样本的数量。所提出的方法利用深度CNN来提取PBP特征，决策融合用于最终标签分配。实验结果表明，所提出的方法可以优于现有的方法。

著录项

来源
《IEEE Geoscience and Remote Sensing Letters》 |2019年第4期|593-597|共5页
作者
Li Wei; Chen Chen; Zhang Mengmeng; Li Hengchao; Du Qian;
展开▼
作者单位

Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China;

Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China;

Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China;

Southwest Jiaotong Univ Sichuan Prov Key Lab Informat Coding & Transmiss Chengdu 610031 Sichuan Peoples R China;

Mississippi State Univ Dept Elect & Comp Engn Starkville MS 39762 USA;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Convolutional neural network (CNN); data augmentation; hyperspectral imagery (HSI); pattern classification;

机译：卷积神经网络（CNN）;数据增强;高光谱图像（HSI）;模式分类;

相似文献

外文文献
中文文献
专利

1. Data Augmentation for Hyperspectral Image Classification With Deep CNN [J] . Li Wei, Chen Chen, Zhang Mengmeng, IEEE Geoscience and Remote Sensing Letters . 2019,第4期

机译：深度CNN用于高光谱图像分类的数据增强
2. CNN-Based Multilayer Spatial–Spectral Feature Fusion and Sample Augmentation With Local and Nonlocal Constraints for Hyperspectral Image Classification [J] . Feng Jie, Chen Jiantong, Liu Liguo, Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of . 2019,第4期

机译：基于CNN的多层空间光谱特征融合和具有局部和非局部约束的样本增强用于高光谱图像分类
3. CNN-Based Multilayer Spatial–Spectral Feature Fusion and Sample Augmentation With Local and Nonlocal Constraints for Hyperspectral Image Classification [J] . Feng Jie, Chen Jiantong, Liu Liguo, Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of . 2019,第4期

机译：基于CNN的多层空间光谱特征融合和采样增强与局部和非识别限制进行高光谱图像分类
4. CNN Hyperspectral Image Classification Using Training Sample Augmentation with Generative Adversarial Networks [C] . Victor-Emil Neagoe, Paul Diaconescu International Conference on Communications . 2020

机译：使用训练对抗网络和生成对抗网络对CNN高光谱图像进行分类
5. Streak Detection in Wide Field of View Images Using Deep Learning and Data Augmentation [D] . Varela, Luis. 2020

机译：使用深度学习和数据增强的宽视野图像中的条纹检测
6. Learning Deep Hierarchical Spatial–Spectral Features for Hyperspectral Image Classification Based on Residual 3D-2D CNN [O] . Fan Feng, Shuangting Wang, Chunyang Wang, 2019

机译：学习基于残差3D-2D CNN的深层空间光谱特征进行高光谱图像分类
7. Deep Collaborative Attention Network for Hyperspectral Image Classification by Combining 2-D CNN and 3-D CNN [O] . Hao Guo, Jianjun Liu, Jinlong Yang, 2020

机译：通过组合2-D CNN和3-D CNN，深度协作关注网络进行高光谱图像分类

Data Augmentation for Hyperspectral Image Classification With Deep CNN

摘要

著录项

相似文献

相关主题

期刊订阅