A Per-Segment Approach to Improving Aspen Mapping from High-Resolution Remote Sensing Imagery
A Per-Segment Approach to Improving Aspen Mapping from High-Resolution Remote Sensing Imagery
复制标题
DOI：
10.1093/jof/101.4.29
复制
发表时间：
2003-06
影响因子：
2.3
通讯作者：
O. Heyman;G. Gaston;A. J. Kimerling;J. Campbell
中科院分区：
文献类型：
--
作者：
O. Heyman;G. Gaston;A. J. Kimerling;J. Campbell
俄勒冈州中部冬季山脊上的杨树林分是用逐段的方法从遥感图像中绘制的。根据色调和饱和度对一幅1米长的彩色红外(CIR)图像进行分割，生成杨树候选图像，然后根据图像段内多分辨率纹理和光谱反射率的平均值对候选图像进行分类，以显示杨木覆盖范围。对于杨树分布的三大类，总体准确率为88%，K-HAT统计量为82%。这种分类方法为从高分辨率卫星图像中更详细地绘制杨树提供了希望。
Aspen (Populus tremuloides) stands on Winter Ridge in central Oregon were mapped from remote sensing imagery utilizing a per-segment approach. A 1-meter color infrared (CIR) image was segmented based on its hue and saturation values to generate aspen “candidates,” which were then classified to show aspen coverage according to the mean values of multiresolution texture and spectral reflectance within the segments. With three broad categories for aspen distribution, overall accuracy was 88 percent, with K-hat statistics of 82 percent. The classification method holds promise for more detailed mapping of aspen from fine-resolution satellite imagery.