基于对象的QuickBird遥感图像多层次森林分类

被引:21
作者
陈旭 [1 ,2 ]
徐佐荣 [2 ]
余世孝 [2 ]
机构
[1] 西南林学院计算机信息与科学系
[2] 中山大学生命科学学院生态学系有害生物控制与资源利用国家重点实验室
关键词
对象; 多层次分类; 图像分割; 遥感;
D O I
暂无
中图分类号
TP79 [遥感技术的应用];
学科分类号
摘要
随着高空间分辨率、相对低光谱分辨率的新型遥感图像的出现和普及,基于像元、依赖于光谱信息特征的传统遥感分类方法已不能很好地适应新型数据的分类工作。通过应用面向对象的多层次分割分类方法对广东省黑石顶自然保护区的QuickBird遥感图像进行了分类尝试。分类结果显示相对于传统的基于像元的分类方法,基于对象的多层次方法具有更准确的分类结果、更明确的分类边界和更均一的内部同质性。
引用
收藏
页码:22 / 26+130 +130
页数:6
相关论文
共 7 条
  • [1] Detecting dominant landscape objects through multiple scales: An integration of object-specific methods and watershed segmentation[J] . Ola Hall,Geoffrey J. Hay,André Bouchard,Danielle J. Marceau.Landscape Ecology . 2004 (1)
  • [2] Forest inventory height update through the integration of lidar data with segmented Landsat imagery
    Wulder, MA
    Seemann, D
    [J]. CANADIAN JOURNAL OF REMOTE SENSING, 2003, 29 (05) : 536 - 543
  • [3] Stand delineation and composition estimation using semi-automated individual tree crown analysis
    Leckie, DG
    Gougeon, FA
    Walsworth, N
    Paradine, D
    [J]. REMOTE SENSING OF ENVIRONMENT, 2003, 85 (03) : 355 - 369
  • [4] Meso-scale landscape analysis based on landscape balance investigations: problems and hierarchical approaches for their resolution[J] . Uta Steinhardt,Martin Volk.Ecological Modelling . 2003 (3)
  • [5] A multiscale framework for landscape analysis: Object-specific analysis and upscaling[J] . G.J. Hay,D.J. Marceau,P. Dubé,A. Bouchard.Landscape Ecology . 2001 (6)
  • [6] Spatial thresholds, image-objects, and upscaling: A multiscale evaluation[J] . G.J. Hay,K.O. Niernann,D.G. Goodenough.Remote Sensing of Environment . 1997 (1)
  • [7] An object-specific image texture analysis of H-resolution forest imagery
    Hay, GJ
    Niemann, KO
    McLean, GF
    [J]. REMOTE SENSING OF ENVIRONMENT, 1996, 55 (02) : 108 - 122