计算机应用 ›› 2019, Vol. 39 ›› Issue (2): 382-387.DOI: 10.11772/j.issn.1001-9081.2018061324

• 人工智能 • 上一篇    下一篇

改进的基于深度学习的遥感图像分类算法

王鑫1, 李可1, 徐明君1, 宁晨2   

  1. 1. 河海大学 计算机与信息学院, 南京 211100;
    2. 南京师范大学 物理科学与技术学院, 南京 210000
  • 收稿日期:2018-06-25 修回日期:2018-08-28 出版日期:2019-02-10 发布日期:2019-02-15
  • 通讯作者: 王鑫
  • 作者简介:王鑫(1981-),女,安徽阜阳人,副教授,博士,主要研究方向:图像处理、模式识别、计算机视觉、机器学习;李可(1996-),女,山西运城人,硕士研究生,主要研究方向:图像处理、模式识别;徐明君(1996-),女,安徽滁州人,硕士研究生,主要研究方向:图像处理分析;宁晨(1978-),男,安徽阜阳人,讲师,博士研究生,主要研究方向:图像处理、机器学习。
  • 基金资助:
    国家自然科学基金资助项目(61603124);教育部中央高校基本科研业务费专项资金资助项目(2018B16114);江苏省"六大人才高峰"高层次人才项目(XYDXX-007);江苏省"333高层次人才培养工程"资助项目。

Improved remote sensing image classification algorithm based on deep learning

WANG Xin1, LI Ke1, XU Mingjun1, NING Chen2   

  1. 1. College of Computer and Information, Hohai University, Nanjing Jiangsu 211100, China;
    2. School of Physics and Technology, Nanjing Normal University, Nanjing Jiangsu 210000, China
  • Received:2018-06-25 Revised:2018-08-28 Online:2019-02-10 Published:2019-02-15
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61603124), the Fundamental Research Funds for the Central Universities (2018B16114), the Six Talents Peak Project of Jiangsu Province (XYDXX-007), the 333 High-Level Talent Training Program of Jiangsu Province.

摘要: 针对传统的基于深度学习的遥感图像分类算法未能有效融合多种深度学习特征,且分类器性能欠佳的问题,提出一种改进的基于深度学习的高分辨率遥感图像分类算法。首先,设计并搭建一个七层卷积神经网络;其次,将高分辨率遥感图像样本输入到该网络中进行网络训练,得到最后两个全连接层输出作为遥感图像两种不同的高层特征;再次,针对该网络第五层池化层输出,采用主成分分析(PCA)进行降维,作为遥感图像的第三种高层特征;然后,将上述三种高层特征通过串联的形式进行融合,得到一种有效的基于深度学习的遥感图像特征;最后,设计了一种基于逻辑回归的遥感图像分类器,可以对遥感图像进行有效分类。与传统基于深度学习的遥感图像分类算法相比,所提算法分类准确率有较高提升。实验结果表明,该算法在分类准确率、误分类率和Kappa系数上表现优异,能实现良好的分类效果。

关键词: 高分辨率遥感图像, 图像分类, 深度学习, 主成分分析, 逻辑回归

Abstract: In order to solve the problem that the traditional deep learning based remote sensing image classification algorithms cannot effectively fuse multiple deep learning features and their classifiers have poor performance, an improved high-resolution remote sensing image classification algorithm based on deep learning was proposed. Firstly, a seven-layer convolutional neural network was designed and constructed. Secondly, the high-resolution remote sensing images were input into the network to train it, and the last two fully connected layer outputs were taken as two different high-level features for the remote sensing images. Thirdly, Principal Component Analysis (PCA) was applied to the output of the fifth pooling layer in the network, and the obtained dimensionality reduction result was taken as the third high-level features for the remote sensing images. Fourthly, the above three kinds of features were concatenated to get an effective deep learning based remote sensing image feature. Finally, a logical regression based classifier was designed for remote sensing image classification. Compared with the traditional deep learning algorithms, the accuracy of the proposed algorithm was increased. The experimental results show that the proposed algorithm performs excellent in terms of classification accuracy, misclassification rate and Kappa coefficient, and achieves good classification results.

Key words: high resolution remote sensing image, image classification, deep learning, Principal Component Analysis (PCA), logistic regression

中图分类号: