摘要
选取了几种经典的自动阈值选取算法对高分辨率遥感图像林区目标进行分割实验,并引入错分类误差、形状测度、均匀测度、最终测量精度和运算速度作为算法评判准则,客观、定量地比较了各种算法对高分辨率遥感图像林区目标的分割性能,所得结论对林区目标分割方法的选取具有一定的指导作用。
Several classic automatic threshold-selecting algorithms were selected for segmenting forest regions in high-resolution remote sensing image.As evaluation criteria of algorithms,misclassification error,shape measure,uniformity measure,relative ultimate measurement accuracy and running time were implemented to compare segmentation performance of each algorithm objectively and quantitatively.The conclusion can play a guidance role in automatic threshold-selecting methods to extract forest regions in high-resolution remote sensing image.
出处
《计算机应用》
CSCD
北大核心
2010年第A12期3269-3273,共5页
journal of Computer Applications
基金
国家自然科学基金资助项目(40771141)
国家973计划项目(2009CB421105)
北京林业大学科技创新计划资助项目(BLYX200936)
关键词
高分辨率遥感图像
图像分割
自动阈值选取
评判准则
林区
high-resolution remote sensing image
image segmentation
automatic threshold-selecting
evaluation criterion
forest region
