论文部分内容阅读
以渭干河-库车河三角洲绿洲为例,探讨了干旱区盐生植被红柳覆盖的盐渍地信息的提取方法。利用TM卫星图像数据,分析了研究区主要地物的光谱特征及其波段间的相互运算,从而分析不同地物之间的可分性。研究表明:K-L-3(第三主成分)是提取重度盐渍地信息的最佳波段,TM1是区分红柳覆盖区(轻、中度)盐渍地信息的最佳波段,提取盐渍地信息时混分的水体信息可以通过MNDWI(改进归一化差异水体指数)设定一定的阈值予以剔除,混分的植被信息可以通过NDVI设定一定的阈值予以剔除。根据以上分析,建立决策树模型,在各节点设计不同的分类器,最后得到盐渍地信息的提取结果。然后进行精度评价,结果表明,该方法的总体提取效果较好,是干旱区监测盐渍地变化的有效手段。
Taking the Weigan-Kuqa River delta oasis as an example, the extraction method of saline-land information covered by Salix psammophila in arid area was discussed. By using TM satellite image data, the spectral features of the main features in the study area and the mutual operation between the bands are analyzed to analyze the separability between different features. The results show that KL-3 (the third principal component) is the best band for extracting salty soil information, TM1 is the best band for discriminating salinized soil from the area covered by Salix The mixed water information can be removed by setting a certain threshold by MNDWI (Improved Normalized Difference Water Index), and the mixed vegetation information can be removed by setting a certain threshold by NDVI. Based on the above analysis, a decision tree model is established, different classifiers are designed at each node, and finally the extraction results of salty ground information are obtained. The accuracy of the method is then evaluated. The results show that the overall extraction efficiency of the method is good, which is an effective means of monitoring the change of saline land in arid areas.