Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (4): 949-954.DOI: 10.11772/j.issn.1001-9081.2017092158

Previous Articles     Next Articles

Application of improved convolution neural network in remote sensing image classification

LIU Yutong, LI Zhiqing, YANG Xiaoling   

  1. Key Laboratory of Intelligent Computing & Information Processing, Ministry of Education(Xiangtan University), Xiangtan Hunan 411100, China
  • Received:2017-09-05 Revised:2017-11-30 Online:2018-04-10 Published:2018-04-09


刘雨桐, 李志清, 杨晓玲   

  1. 智能计算与信息处理教育部重点实验室(湘潭大学), 湖南 湘潭 411100
  • 通讯作者: 刘雨桐
  • 作者简介:刘雨桐(1992-),女,湖南岳阳人,硕士研究生,CCF会员,主要研究方向:人工智能、计算机视觉、神经网络、机器学习;李志清(1975-),男,湖南娄底人,副教授,博士,CCF会员,主要研究方向:人工智能、计算机视觉、神经网络、机器学习;杨晓玲(1992-),女(土家族),贵州铜仁人,硕士研究生,CCF会员,主要研究方向:计算机视觉、人工智能、图像标注。

Abstract: The sparse network structure for traditional Convolutional Neural Network (CNN) can not preserve the high efficiency of dense network-intensive computing and the empirical selection of the activation function in the experiment process, which leads to inaccurate results or high computational complexity. To solve above problems, an improved CNN method was proposed and applied in remote sensing images classification. Firstly, the multi-scale features of an image was extracted by using different scale convolution kernels of the Inception module, then the activation function of the hidden layer node was studied by using the Maxout model. Finally, the image was classified by the Softmax method. Experiments were conducted on the same US Land Use Classification Data Set 21(UCM_LandUse_21), and the experimental results showed that the accuracy of the proposed method was about 3.66% and 2.11% higher than that of the traditional CNN method and a Multi-Scale Deep CNN (MS_DCNN) respectively with the same number of convolution layers, and it was also more than 10% higher than that of visual dictionary methods based on low-level features and middle-level features. The proposed method has high classification efficiency and is suitable for image classification.

Key words: Convolutional Neural Network (CNN), Inception module, Maxout network, dropout operation, remote sensing image classification

摘要: 针对传统卷积神经网络(CNN)稀疏网络结构无法保留全连接网络密集计算的高效性和实验过程中激活函数的经验性选择造成结果不准确或计算量大的问题,提出一种改进卷积神经网络方法对遥感图像进行分类。首先,利用Inception模块的不同尺度卷积核提取图像多尺度特征,然后利用Maxout模型学习隐藏层节点的激活函数,最后通过Softmax方法对图像进行分类。在美国土地使用分类数据集(UCM_LandUse_21)上进行的实验结果表明,在卷积层数相同的情况下,所提方法比传统的CNN方法分类精度提高了约3.66%,比同样也基于多尺度深度卷积神经网络(MS_DCNN)方法分类精度提高了2.11%,比基于低层特征和中层特征的视觉词典等方法分类精度更是提高了10%以上。因此,所提方法具有较高的分类效率,适用于图像分类。

关键词: 卷积神经网络, Inception模块, Maxout网络, dropout操作, 遥感图像分类

CLC Number: