...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Geoscience and Remote Sensing >Incorporating Metric Learning and Adversarial Network for Seasonal Invariant Change Detection
【24h】

Incorporating Metric Learning and Adversarial Network for Seasonal Invariant Change Detection

机译：结合公制学习和对抗性网络，以实现季节性不变变化检测

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

Change detection by comparing two bitemporal images is one of the most fundamental challenges for dynamic monitoring of the Earth surface. In this article, we propose a metric learning-based generative adversarial network (GAN) (MeGAN) to automatically explore seasonal invariant features for pseudochange suppressing and real change detection. To achieve this purpose, a seasonal invariant term is introduced to maximally suppress pseudochanges, whereas the MeGAN explores the transition patterns between adjacent images in a self-learning fashion. Different from the previous works on bitemporal imagery change detection, the proposed MeGAN have the following contributions: 1) it automatically explores change patterns from the complex bitemporal background without human intervention and 2) it aims to maximally exclude pseudochanges from the seasonal transition term and map out real changes efficiently. To our best knowledge, this is the first time we incorporate the seasonal transition term and GAN for change detection between bitemporal images. At last, to demonstrate the robustness of the proposed method, we included two data sets which are the Google Earth data and the Landsat data, for bitemporal change detection and evaluation. The experimental results indicated that the proposed method is able to perform change detection with precision can be as high as 81 & x0025; and 88 & x0025; for the Google Earth and Landsat data set, respectively.
机译：通过比较两个比特般图像来改变检测是对地球表面动态监测的最基本的挑战之一。在本文中，我们提出了一个基于度量的基于学习的生成对冲网络（GaN）（Megan）（Megan），以自动探索伪装抑制和实际变化检测的季节性不变功能。为达到此目的，引入了季节性不变术语以最大衡抑制伪倾向，而MEGAN以自学习方式探讨相邻图像之间的转换模式。与以前的作品不同于磅声图像变化检测，所提出的梅根有以下贡献：1）它自动探讨来自复杂的比特队背景的变化模式，没有人为干预，2）它旨在最大限地排除来自季节转变期和地图的伪函数真正的变化有效。为了我们最好的知识，这是我们第一次将季节转换术语和GaN纳入衡量标记之间的变化检测。最后，为了展示所提出的方法的稳健性，我们包括两个数据集，这些数据集是谷歌地球数据和LANDSAT数据，用于衡量标准检测和评估。实验结果表明，所提出的方法能够精确地进行变化检测，可以高达81＆x0025;和88＆x0025;对于谷歌地球和LANDSAT数据集。

著录项

  • 来源
  • 作者

    Zhao Wenzhi; Mou Lichao; Chen Jiage; Bo Yanchen; Emery William J.;

  • 作者单位

    Chinese Acad Sci Jointly Sponsored Beijing Normal Univ & Inst Remo State Key Lab Remote Sensing Sci Beijing 100875 Peoples R China|Beijing Normal Univ Fac Geog Sci Inst Remote Sensing Sci & Engn Beijing Engn Res Ctr Global Land Remote Sensing P Beijing 100875 Peoples R China;

    Tech Univ Munich TUM Signal Proc Earth Observat SiPEO D-80333 Munich Germany|Remote Sensing Technol Inst IMF German Aerosp Ctr DLR D-82234 Wessling Germany;

    Natl Geomat Ctr China Beijing 100830 Peoples R China;

    Chinese Acad Sci Jointly Sponsored Beijing Normal Univ & Inst Remo State Key Lab Remote Sensing Sci Beijing 100875 Peoples R China|Beijing Normal Univ Fac Geog Sci Inst Remote Sensing Sci & Engn Beijing Engn Res Ctr Global Land Remote Sensing P Beijing 100875 Peoples R China;

    Univ Colorado Colorado Ctr Astrodynam Res Boulder CO 80309 USA;

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

    Bitemporal images; change detection; metric learning; metric learning-based generative adversarial network (GAN) (MeGAN); pseudochanges;

    机译：磅扑的图像;改变检测;度量学习;公制学习的生成对策网络（GaN）（梅根）;伪;

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