论文部分内容阅读
以吉林省汪清林业局为例,基于Landsat5-TM影像,充分利用遥感影像光谱信息,分别采用动态聚类法和组合监督分类法对该林区的森林类型进行分类,并对分类结果的精度进行比较分析。研究结果表明,利用组合监督分类的精度比动态聚类法分类的精度要高,总体分类精度高11%,其中针叶林、阔叶林、混交林和其他用地的分类精度分别高8%、11%、17%和10%。
Taking Wangqing Forestry Bureau of Jilin Province as an example, the forest type in this forest area was classified based on Landsat5-TM images and the spectral information of remote sensing images were used respectively. The classification of forest types was classified by dynamic clustering and combined supervised classification respectively. comparative analysis. The results show that the accuracy of classification using combination supervised classification is higher than that of dynamic cluster classification, and the overall classification accuracy is 11% higher. The classification accuracies of coniferous forest, broad-leaved forest, mixed forest and other land are 8% 11%, 17% and 10%.