基于ETM＋影像融合的土地覆盖分类研究

摘要

借助ERDAS软件,运用遥感数据融合技术对四川省蓬安县进行基于ETM＋融合影像的土地覆盖分类初步研究。研究中采用相同的训练样本区及最大似然法分类方法,对融合前后影像分别进行土地覆盖分类,通过对分类影像的Pro-ducers Accuracy,Users Accuracy,Kappa Accuracy三者的精度数据对比分析,得出乘积法融合法和立方卷积重采样法相对更为可取。%Supported by the ERDAS software,the research applies data fusion technique to study land cover initiative classification based on the ETM＋fused image for Peng＇an county in Sichuan.Making use of the identical training sample area and the maximum likelihood classification method to make land cover classification with the nine sheets of image fused and one sheet of image non-fused.Through contrasting and analyzing the Producers Accuracy,the Users Accuracy,and the Kappa Accuracy,the multiplicative fusion method and the cubic convolution resampling technique are relative better.