...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Discrete and Continuous Dynamical Systems,Series S >AN AUTOMATED SEGMENTATION OF NATURA 2000 HABITATS FROM SENTINEL-2 OPTICAL DATA
【24h】

AN AUTOMATED SEGMENTATION OF NATURA 2000 HABITATS FROM SENTINEL-2 OPTICAL DATA

机译：来自Sentinel-2光学数据的Natura 2000栖息地的自动分割

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

In this paper, we present a mathematical model and numericalmethod designed for the segmentation of satellite images, namely to obtainin an automated way borders of Natura 2000 habitats from Sentinel-2 opticaldata. The segmentation model is based on the evolving closed plane curveapproach in the Lagrangian formulation including the efficient treatment oftopological changes. The model contains the term expanding the curve in itsouter normal direction up to the region of habitat boundary edges, the termattracting the curve accurately to the edges and the smoothing term given bythe inuence of local curvature. For the numerical solution, we use the ow-ing finite volume method discretizing the arising advection-diffusion intrinsicpartial differential equation including the asymptotically uniform tangentialredistribution of curve grid points. We present segmentation results for satel-lite data from a selected area of Western Slovakia (Zahorie) where the so-calledriparian forests represent the important European Natura 2000 habitat. Theautomatic segmentation results are compared with the semi-automatic segmen-tation performed by the botany expert and with the GPS tracks obtained inthe field. The comparisons show the ability of our numerical model to segmentthe habitat areas with the accuracy comparable to the pixel resolution of theSentinel-2 optical data.
机译：在本文中，我们提出了一个数学模型和数值设计用于分割卫星图像的方法，即获得以自动化的方式来自Sentinel-2光学的Natura 2000栖息地的边界数据。分割模型基于不断变化的闭合平面曲线拉格朗日配方中的方法，包括有效的治疗方法拓扑变化。该模型包含在其上扩展曲线的术语外部正常方向直达栖息地边界边界，术语准确吸引曲线到边缘和平滑术语给出in.局部曲率的影响。对于数字解决方案，我们使用ow有限体积法离散地引发的平流扩散内在局部微分方程，包括渐近均匀的切向曲线网格点的再分配。我们呈现SATEL-的分段结果 - 来自西部斯洛伐克（Zahorie）的选定区域的Lite数据，所谓的河岸森林代表了重要的欧洲Natura 2000栖息地。这将自动分割结果与半自动segmen进行比较 - 由植物学专家和获得的GPS轨道执行场。比较显示了我们数值模型到段的能力栖息地区域具有与像素分辨率相媲美的准确性Sentinel-2光学数据。

著录项

  • 来源
  • 作者

    KAROL MIKULA; JOZEF URBAN; MICHAL KOLLAR; MARTIN AMBROZ; IVAN JAROLMEK; JOZEF SIBK; MARIA SIBKOVA;

  • 作者单位

    Department of Mathematics Slovak University of TechnologyRadlinskeho 11 810 05 Bratislava SlovakiaAlgoritmy:SK s.r.o. Sulekova 6 811 06 Bratislava Slovakia;

    Department of Mathematics Slovak University of TechnologyRadlinskeho 11 810 05 Bratislava SlovakiaAlgoritmy:SK s.r.o. Sulekova 6 811 06 Bratislava Slovakia;

    Department of Mathematics Slovak University of TechnologyRadlinskeho 11 810 05 Bratislava SlovakiaAlgoritmy:SK s.r.o. Sulekova 6 811 06 Bratislava Slovakia;

    Department of Mathematics Slovak University of TechnologyRadlinskeho 11 810 05 Bratislava SlovakiaAlgoritmy:SK s.r.o. Sulekova 6 811 06 Bratislava Slovakia;

    Institute of Botany Slovak Academy of SciencesDubravska cesta 9 845 23 Bratislava Slovakia;

    Institute of Botany Slovak Academy of SciencesDubravska cesta 9 845 23 Bratislava Slovakia;

    Institute of Botany Slovak Academy of SciencesDubravska cesta 9 845 23 Bratislava Slovakia;

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

    Image segmentation; curve evolution; numerical method; Natura 2000; satellite images; Sentinel-2;

    机译：图像分割;曲线演变;数值方法;Natura 2000;卫星图像;Sentinel-2;

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