摘要
应用灰度共生矩阵的研究方法初步探讨了航片纹理图像与马尾松林测树因子之间的关系。根据最优建模结果,用角二阶矩这一纹理指标拟合得到的年龄模型最好,其相关系数的平方达到了0.556 6;用方差拟合得到的平均树高模型,其相关系数的平方为0.501 4;方差与郁闭度的相关程度不高,其相关系数平方仅为0.391 4。另外通过实验还发现,灰度等级越高,窗口越大,其纹理图像与测树因子之间的关系越显著。
Relationship was analyzed by Gray Level Co-occurrence Matrix(GLCM) between texture features of aerial photographes and tree measuring factors of Pinus massoniana forest.The best modeling resulted that relationship between the angular second moment value and tree age was the most significant,whose R2 attained 0.5566,and R2 between the variance value and the average tree height reached 0.5014,while the correlation between the variance value and canopy density was not evident,with the R2 only 0.3914.Meanwhile,the experiment demonstrated that higher the gray level was,larger the moving window size,more significant the relationship between texture features and tree measuring factors.
出处
《浙江林业科技》
北大核心
2010年第3期68-71,共4页
Journal of Zhejiang Forestry Science and Technology
基金
国家自然科学基金项目"基于面向类技术的高分辨率遥感图像森林信息提取方法研究"(30771725)
关键词
灰度共生矩阵
纹理指标
测树因子
线性回归
Gray Level Co-occurrence Matrix(GLCM)
texture features
tree measuring factors
liner regression