融合影像纹理、光谱与地形特征的森林冠顶高反演模型

融合影像纹理、光谱与地形特征的森林冠顶高反演模型

高凯旋, 焦海明, 王新闯

Inversion model of forest canopy height based on image texture,spectral and topographic features

GAO Kaixuan, JIAO Haiming, WANG Xinchuang

表2 纹理参数

Tab.2 Texture parameters

序号	纹理特征	公式^①
1	均值(ME)	$ME = \overset{N - 1}{\sum_{i, j = 0}} i P_{i, j}$
2	方差(VA)	$VA = \overset{N - 1}{\sum_{i, j = 0}} i P_{i, j} {(i - ME)}^{2}$
3	对比度(CO)	$CO = \overset{N - 1}{\sum_{i, j = 0}} i P_{i, j} {(i - j)}^{2}$
4	相关性(CC)	$CC = \overset{N - 1}{\sum_{i, j = 0}} i P_{i, j} [\frac{(i - ME) (j - ME)}{\sqrt[]{V A_{i} V A_{j}}}]$
5	同质性(HO)	$HO = \overset{N - 1}{\sum_{i, j = 0}} i \frac{P_{i, j}}{1 + {(i - j)}^{2}}$
6	异质性(DI)	$DI = \overset{N - 1}{\sum_{i, j = 0}} i P_{i, j} \|i - j\|$
7	熵(EN)	$EN = \overset{N - 1}{\sum_{i, j = 0}} i P_{i, j} (- \ln P_{i, j})$
8	角二阶距(SM)	$SM = \overset{N - 1}{\sum_{i, j = 0}} i {P_{i, j}}^{2}$