不同监督分类器对土地利用分类精度的影响

摘要

In order to improve the classification accuracy and classification effect of land use types,the main urban area of Tangshan city as the case area was studied.Based on the supervised classification system, using landsat remote sensing images,land use types in the study area were classified,and the accuracy was compared by using the four most commonly used classical classifiers,such as parallelepiped,minimum distance,mahalanobis distance and maximum likelihood.The results show that the maximum likelihood classification effect is the best in this experiment.The research results can provide reference for supervising the selection of classifiers and land use classification.%为提高土地利用类型遥感分类精度和分类效果,该项研究以唐山市主城区为案例区,利用landsat遥感影像,基于监督分类体系,分别采用平行六面体、最小距离、马氏距离和最大似然4种最常用的经典分类器,对研究区土地利用类型进行遥感分类并进行精度对比分析.结果表明,最大似然分类效果在本实验中效果最好.研究可为监督分类中分类器的选择和土地利用分类提供参考.