...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of >Patch-Sorted Deep Feature Learning for High Resolution SAR Image Classification
【24h】

Patch-Sorted Deep Feature Learning for High Resolution SAR Image Classification

机译：修补程序深度特征学习用于高分辨率SAR图像分类

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Synthetic aperture radar (SAR) image classification is a fundamental process for SAR image understanding and interpretation. The traditional SAR classification methods extract shallow and handcrafted features, which cannot subtly depict the abundant modal information in high resolution SAR image. Inspired by deep learning, an effective feature learning tool, a novel method called patch-sorted deep neural network (PSDNN) to implement unsupervised discriminative feature learning is proposed. First, the randomly selected patches are measured and sorted by the meticulously designed patch-sorted strategy, which adopts instance-based prototypes learning. Then the sorted patches are delivered to a well-designed dual-sparse autoencoder to obtain desired weights in each layer. Convolutional neural network is followed to extract high-level spatial and structural features. At last, the features are fed to a linear support vector machine to generate predicted labels. The experimental results in three broad SAR images of different satellites confirm the effectiveness and generalization of our method. Compared with three traditional feature descriptors and four unsupervised deep feature descriptors, the features learned in PSDNN appear powerful discrimination and the PSDNN achieves desired classification accuracy and a good visual appearance.
机译：合成孔径雷达（SAR）图像分类是SAR图像理解和解释的基本过程。传统的SAR分类方法提取的是浅层和手工特征，无法精细地描述高分辨率SAR图像中丰富的模态信息。受到深度学习的启发，提出了一种有效的特征学习工具，一种称为补丁排序深度神经网络（PSDNN）的新方法，可以实现无监督的判别式特征学习。首先，通过精心设计的补丁分类策略对随机选择的补丁进行测量和分类，该策略采用基于实例的原型学习。然后将分类的小块传送到设计良好的双稀疏自动编码器，以在每一层中获得所需的权重。遵循卷积神经网络来提取高级空间和结构特征。最后，将特征馈入线性支持向量机以生成预测标签。在不同卫星的三个宽SAR图像中的实验结果证实了我们方法的有效性和推广性。与三个传统特征描述符和四个无监督的深层特征描述符相比，在PSDNN中学习到的特征表现出强大的辨别力，并且PSDNN获得了所需的分类精度和良好的视觉外观。

著录项

  • 来源
  • 作者

    Zhongle Ren; Biao Hou; Zaidao Wen; Licheng Jiao;

  • 作者单位

    Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, Shaanxi Province, China;

    Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, Shaanxi Province, China;

    Shaanxi Province, China;

    Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, International Research Center for Intelligent Perception and Computation, Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi'an, Shaanxi Province, China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Feature extraction; Synthetic aperture radar; Training; Prototypes; Image resolution; Neural networks; Transforms;

    机译：特征提取;合成孔径雷达;训练;原型;图像分辨率;神经网络;变换;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号