文档视界 最新最全的文档下载
当前位置:文档视界 › 基于卷积神经网络的遥感图像分类研究

基于卷积神经网络的遥感图像分类研究

DOI : 10.11992/tis.201706078网络出版地址: https://www.docsj.com/doc/128757565.html,/kcms/detail/23.1538.TP.20180328.1448.010.html

基于卷积神经网络的遥感图像分类研究

李亚飞,董红斌

(哈尔滨工程大学 计算机科学与技术学院,黑龙江 哈尔滨 150001)

摘 要:遥感图像分类是模式识别技术在遥感领域的具体应用,针对遥感图像处理中的分类问题,提出了一种基于卷积神经网络(convolutional neural networks ,CNN)的遥感图像分类方法,并针对单源特征无法提供有效信息的问题,设计了一种多源多特征融合的方法,将遥感图像的光谱特征、纹理特征、空间结构特征等按空间维度以向量或矩阵的形式进行有效融合,以此训练CNN 模型。实验表明,多源多特征相融合能够加快模型收敛速度,有效提高遥感图像的分类精度;与其他分类方法相比,CNN 能够取得更高的分类精度,获得更优的分类效果。

关键词:遥感图像;地物分类;卷积神经网络;特征融合

中图分类号:TP301 文献标志码:A 文章编号:1673?4785(2018)04?0550?07

中文引用格式:李亚飞, 董红斌. 基于卷积神经网络的遥感图像分类研究[J]. 智能系统学报, 2018, 13(4): 550–556.

英文引用格式:LI Yafei, DONG Hongbin. Classification of remote-sensing image based on convolutional neural network[J]. CAAI transactions on intelligent systems, 2018, 13(4): 550–556.

Classification of remote-sensing image based on convolutional

neural network

LI Yafei ,DONG Hongbin

(College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China)

Abstract : The classification of remote-sensing images is a specific application of pattern recognition technology in the remote-sensing domain. In this paper, we propose a method for the classification of remote-sensing images based on convolutional neural networks (CNN). In addition, to address the difficulty of providing effective information regarding a single-source feature in convolutional neural networks, we propose a multi-source and multi-feature fusion method.We combine the spectral, texture, and spatial-structure features of remote-sensing images in the form of vectors or matrices according to their spatial dimensions, and train the CNN model using these combined features. The experiment-al results show that multi-source and multi-feature fusion can effectively improve the model convergence speed and classification accuracy, in comparison with traditional classification methods, and that the CNN method achieves higher classification accuracy and classification effect.

Keywords : remote-sensing image; classification of land cover; convolutional neural networks; feature fusion

遥感图像分类就是依据遥感数据的各种信

息,通过采用某种算法挖掘每类地物的独有特征

并将其分割为互不相交的子空间,进而将各个像

素划分到对应的子空间。但对于高分辨率的遥感

图像,地物的光谱特征越来越丰富,“同物异谱”

和“异物同谱”现象更加明显[1]。因此传统的参数化方法如最小距离分类法(minimum distance clas-sification ,MDC)[2]、极大似然分类法(maximum likelihood classification ,MLC)[3]等分类准确度降低。而非参数化方法如支持向量机[4]、人工神经网络(artificial neural network ,ANN)[5]、决策树(de-cision tree ,DT)[6]等在高分辨率遥感影像分类中得收稿日期:2017?06?26. 网络出版日期:2018?03?28.

基金项目:国家自然科学基金项目(61472095).

通信作者:董红斌. E-mail :donghongbin@https://www.docsj.com/doc/128757565.html, .第 13 卷第 4 期

智 能 系 统 学 报Vol.13 No.42018 年 8 月

CAAI Transactions on Intelligent Systems Aug. 2018

相关文档