《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (5): 1431-1439.DOI: 10.11772/j.issn.1001-9081.2021030464

• 人工智能 • 上一篇    下一篇

基于有效通道注意力的遥感图像场景分类

屈震, 李堃婷, 冯志玺()   

  1. 西安电子科技大学 人工智能学院,西安 710071
  • 收稿日期:2021-03-26 修回日期:2021-07-16 接受日期:2021-07-16 发布日期:2022-06-11 出版日期:2022-05-10
  • 通讯作者: 冯志玺
  • 作者简介:屈震(2000—),男,陕西榆林人,主要研究方向:机器学习、遥感图像处理
    李堃婷(2000—),女,辽宁昌图人,主要研究方向:机器学习、遥感图像处理
    冯志玺(1989—),男,甘肃武威人,副教授,博士,CCF会员,主要研究方向:智能信号与图像处理。 zxfeng@xidian.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(61836009)

Remote sensing image scene classification based on effective channel attention

Zhen QU, Kunting LI, Zhixi FENG()   

  1. School of Artificial Intelligence,Xidian University,Xi’an Shaanxi 710071,China
  • Received:2021-03-26 Revised:2021-07-16 Accepted:2021-07-16 Online:2022-06-11 Published:2022-05-10
  • Contact: Zhixi FENG
  • About author:QU Zhen, born in 2000. His research interests include machinelearning,remote sensing image processing.
    LI Kunting, born in 2000. Her research interests include machinelearning,remote sensing image processing.
    FENG Zhixi, born in 1989,Ph. D.,associate professor. Hisresearch interests include intelligent signal and image processing.
  • Supported by:
    National Natural Science Foundation of China(61836009)

摘要:

针对基于人工设计特征的方法不能提取高层次遥感图像信息以及以往利用VGGNet、ResNet等卷积神经网络(CNN)无法关注到遥感图像中显著分类特征的问题,提出了一种基于有效通道注意力(ECA)机制的遥感图像场景分类新模型——ECA-ResNeXt-8-SVM。为了建立高效模型,一方面,设计了嵌入ECA模块的深度特征提取网络ECA-ResNeXt-8,通过端到端的学习使网络更关注分类特征明显的通道;另一方面,利用支持向量机(SVM)代替全连接层作为已提取到的深度特征的分类器,从而进一步提高模型的分类准确率与泛化能力。该模型在实验数据集UC Merced Land-Use上的分类准确率达到95.81%,相较于使用SE-ResNeXt50与ResNeXt50网络,分别提高了6%与18%,且在分类准确率为75%时所提模型的训练时间比上述两个网络分别减少了82%与81%。实验结果表明,所提模型能够有效地减少模型的收敛时间并提升遥感图像场景分类的准确率。

关键词: 遥感图像场景分类, 有效通道注意力机制, 支持向量机, 深度学习, 卷积神经网络

Abstract:

The methods based on artificially designed features cannot extract high-level information from remote sensing images and previously used Convolutional Neural Network (CNN) such as VGGNet and ResNet cannot focus on distinguishable classification features in remote sensing images. In order to solve the problems, a novel method called ECA-ResNeXt-8-SVM was proposed based on Effective Channel Attention (ECA) mechanism for remote sensing image scene classification. In order to build an effective model, a deep feature extraction network called ECA-ResNeXt-8 embedded with the ECA module was designed, and the end-to-end learning was used to make network lay emphasis on channels with distinguishable classification features. At the same time, Support Vector Machine (SVM) was utilized to replace the fully connected layer as the classifier of the extracted deep features, which helped to improve the classification accuracy and generalization ability of model. On the experimental dataset UC Merced Land-Use, the classification accuracy of the proposed model reaches 95.81%, which is increased by 6% and 18% compared to SE-ResNeXt50 and ResNeXt50 networks respectively. When the classification accuracy is 75%, the proposed model has the training time reduced by 82% and 81% compared to the two above networks respectively. Experimental results show that the proposed model can reduce the convergence time of model effectively and improve the classification accuracy for remote sensing image scene.

Key words: remote sensing image scene classification, Efficient Channel Attention (ECA) mechanism, Support Vector Machine (SVM), deep learning, Convolutional Neural Network (CNN)

中图分类号: