...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Polar biology >Transferability and the effect of colour calibration during multi-image classification of Arctic vegetation change
【24h】

Transferability and the effect of colour calibration during multi-image classification of Arctic vegetation change

机译：北极植被变化多图像分类期间颜色校准的可转换性和效果

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

Mapping changes in vegetation cover is essential for understanding the consequences of climate change on Arctic ecosystems. Classification of ultra-high spatial-resolution (UHR, 1cm) imagery can provide estimates of vegetation cover across space and time. The challenge of this approach is to assure comparability of classification across many images taken at different illumination conditions and locations. With warming, vegetation at higher elevation is expected to resemble current vegetation at lower elevation. To investigate the value of classification of UHR imagery for monitoring vegetation change, we collected visible and near-infrared images from 108 plots with hand-held cameras along an altitudinal gradient in Greenland and examined the classification accuracy of shrub cover on independent images (i.e. classification transferability). We implemented several models to examine if colour calibration improves transferability based on an in-image calibration target. The classifier was trained on different number of images to find the minimum training subset size. With a training set of20% of the images the overall accuracy levelled off at about 81% and 68% on the non-calibrated training and validation images, respectively. Colour calibration improved the accuracy on training images (1-4%) while it only improved the classifier transferability significantly for training sets 20%. Linear calibration only based on the target's grey series improved transferability most. Reasonable transferability of Arctic shrub cover classification can be obtained based only on spectral data and about 20% of all images. This is promising for vegetation monitoring through multi-image classification of UHR imagery acquired with hand-held cameras or Unmanned Aerial Systems.
机译：植被封面的映射变化对于了解气候变化对北极生态系统的后果至关重要。超高空间分辨率（UHR，<1CM）图像的分类可以提供跨空间和时间植被覆盖的估计。这种方法的挑战是确保在不同照明条件和位置拍摄的许多图像中分类的可比性。随着变暖的，预计升高的植被将在较低的高度下类似植被。探讨UHR图像分类的价值用于监测植被变化，我们从格陵兰岛的一般梯度与手持式相机收集的可见和近红外图像，并在独立图像上检查了灌木覆盖的分类精度（即分类可转移性）。我们实现了几种模型来检查颜色校准是否提高了基于In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-In-Table。分类器培训在不同数量的图像上，以找到最小训练子集大小。在非校准训练和验证图像中，培训OHE20％的图像的整体精度均为约81％和68％。颜色校准提高了训练图像的准确性（1-4％），而仅在训练集<20％的情况下显着提高了分类器可转换性。线性校准仅基于目标的灰色系列最高的转移性。只能基于频谱数据和大约20％的图像的北极灌木覆盖分类的合理可转移性。这是通过用手持式相机或无人机的空中系统获得的UHR图像的多图像分类来实现植被监测。

著录项

  • 来源
    《Polar biology》 |2019年第7期|1227-1239|共13页
  • 作者

    Kolyaie Samira; Treier Urs Albert; Watmough Gary Richard; Madsen Bjarke; Bocher Peder Klith; Psomas Achilleas; Bosch Ruedi; Normand Signe;

  • 作者单位

    Aarhus Univ Ctr Biodivers Dynam Changing World Dept Biosci Sect Ecoinformat & Biodivers Ny Munkegade 116 DK-8000 Aarhus C Denmark;

    Aarhus Univ Ctr Biodivers Dynam Changing World Dept Biosci Sect Ecoinformat & Biodivers Ny Munkegade 116 DK-8000 Aarhus C Denmark|Swiss Fed Res Inst WSL Remote Sensing Grp Zurcherstr 111 CH-8903 Birmensdorf Switzerland|Aarhus Univ Arctic Res Ctr Dept Biosci Ny Munkegade 116 DK-8000 Aarhus C Denmark;

    Aarhus Univ Ctr Biodivers Dynam Changing World Dept Biosci Sect Ecoinformat & Biodivers Ny Munkegade 116 DK-8000 Aarhus C Denmark|Univ Edinburgh Sch Geosci Edinburgh EH8 9XP Midlothian Scotland;

    Aarhus Univ Ctr Biodivers Dynam Changing World Dept Biosci Sect Ecoinformat & Biodivers Ny Munkegade 116 DK-8000 Aarhus C Denmark;

    Aarhus Univ Ctr Biodivers Dynam Changing World Dept Biosci Sect Ecoinformat & Biodivers Ny Munkegade 116 DK-8000 Aarhus C Denmark;

    Swiss Fed Res Inst WSL Remote Sensing Grp Zurcherstr 111 CH-8903 Birmensdorf Switzerland;

    Swiss Fed Res Inst WSL Remote Sensing Grp Zurcherstr 111 CH-8903 Birmensdorf Switzerland;

    Aarhus Univ Ctr Biodivers Dynam Changing World Dept Biosci Sect Ecoinformat & Biodivers Ny Munkegade 116 DK-8000 Aarhus C Denmark|Aarhus Univ Arctic Res Ctr Dept Biosci Ny Munkegade 116 DK-8000 Aarhus C Denmark|Swiss Fed Res Inst WSL Landscape Dynam Grp Zurcherstr 111 CH-8903 Birmensdorf Switzerland;

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

    Arctic tundra; Climate change; Colour calibration; Standardization; Spectral data; Classification transferability;

    机译：北极苔原;气候变化;颜色校准;标准化;光谱数据;分类可转移性;

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