论文部分内容阅读
对ETM+影像进行多种算法融合实验,除应用ERDAS软件现有的融合方法(PCA、MLT)外,还利用IDL语言编程实现了SFIM、HPF、MB等融合算法,通过多次修改SFIM、HPF、MB融合算法中滤波器窗口的大小、滤波算子的实验,达到既不产生噪声又增强了图像纹理信息的融合效果。对融合后的影像进行了相同地物样本、不同分类方法的监督分类。以2002年内蒙古土地利用遥感调查数据为评价标准(内蒙古自治区遥感与地理信息系统重点实验室提供),用总体精度(overall accuracy)、kappa系数两种评价指数综合反映各种融合算法与各种分类方法结合的分类精度,并对各种分类方法及融合算法予以评价。
In addition to using the existing fusion method (PCA, MLT) of ERDAS software, a fusion algorithm of SFIM, HPF, MB and so on is implemented by using IDL language programming. A number of algorithms such as SFIM, HPF, MB fusion algorithm in the filter window size, the filter operator experiments to achieve both no noise but also enhance the image texture information fusion effect. The fusion of the image of the same object samples, different classification methods of supervision and classification. Based on the data of remote sensing survey of land use in Inner Mongolia in 2002 (provided by Key Laboratory of Remote Sensing and Geographic Information System of Inner Mongolia Autonomous Region), the overall accuracy and the kappa coefficient are used to evaluate the performance of the fusion algorithms and various classification Method combined with classification accuracy, and to evaluate a variety of classification methods and fusion algorithms.