...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International journal of remote sensing >Integrating change magnitude maps of spectrally enhanced multi-features for land cover change detection
【24h】

Integrating change magnitude maps of spectrally enhanced multi-features for land cover change detection

机译：集成频谱增强多个功能的变化幅度图，用于陆地覆盖变化检测

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

Constructing a change magnitude map (CMM) is a key component of binary change detection. Recently, integrating multiple features to obtain a comprehensive CMM has become a popular research topic. However, the current integration approaches mainly utilize simple spectral CMMs that are derived based on a single spectral change index (e.g. image difference, Euclidean distance, and change vector analysis), which is not sufficient for addressing complex land cover changes. In this study, we propose a spectrally enhanced multi-feature fusion (SeMF) method with CMM integration for effective change detection. Seven commonly used spectral change indices are analysed from the aspects of the spectral value and spectral shape; two of these indices are selected to construct the optimal spectral-based CMM, which is more efficient, robust and stable than the single spectral change indices. The rotation-invariant local binary patterns (RiLBP) and Canny methods are further used for CMM generation via the textural and shape features, respectively. These three types of CMMs are adaptively assigned weights by using an information entropy-based fusion strategy and ultimately integrated into a comprehensive CMM. Two groups of experiments with Landsat 8 Operational Land Imager (OLI) and Gaofen (GF)-1 images are designed to verify the effectiveness of the SeMF method. The experimental results indicate that the SeMF method is superior to both spectral feature-based and multi-feature-based change detection methods.
机译：构建变化幅度图（CMM）是二进制变化检测的关键组件。最近，整合多个功能以获得全面的CMM已成为一个流行的研究主题。然而，目前的集成方法主要利用基于单个光谱变化指数导出的简单光谱CMM（例如，图像差，欧几里德距离和改变向量分析），这不足以解决复杂的陆地覆盖变化。在这项研究中，我们提出了一种具有CMM集成的光谱增强的多特征融合（SEMF）方法，以进行有效变化检测。从光谱值和光谱形状的各方面分析七种常用的光谱变化指标;选择其中的两个指数以构建基于最佳的基于频谱的CMM，其比单频谱变化索引更有效，坚固且稳定。旋转不变的局部二进制图案（RILBP）和Canny方法分别通过纹理和形状特征进一步用于CMM生成。通过使用基于信息熵的融合策略并最终集成到全面的CMM中，这三种类型的CMMS被自适应地分配了权重。与Landsat 8运行陆地成像器（OLI）和高芬（GF）-1图像的两组实验旨在验证SEMF方法的有效性。实验结果表明，SEMF方法优于基于光谱特征和基于多特征的变化检测方法。

著录项

  • 来源
    《International journal of remote sensing》 |2021年第12期|4284-4308|共25页
  • 作者

    Xing Huaqiao; Zhu Linye; Hou Dongyang; Zhang Tao;

  • 作者单位

    Shandong Jianzhu Univ Sch Surveying & Geoinformat Jinan Peoples R China;

    Shandong Jianzhu Univ Sch Surveying & Geoinformat Jinan Peoples R China;

    Cent South Univ Sch Geosci & Infophys Changsha Peoples R China;

    Minist Nat Resources Peoples Republ China Land Satellite Remote Sensing Applicat Ctr Beijing Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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