面向对象的成都平原多源遥感影像分割尺度研究

要对高分辨率遥感影像进行分类,采用面向对象的遥感影像分析技术比传统的面向像元的遥感影像分析技术优越。要使用面向对象的遥感影像分析技术,关键的第一步是要对遥感影像进行分割,以便得到一系列与地物有密切联系的影像对象。分割的准确性与分割的尺度选择有关。本文针对成都平原高分辨率卫星影像分割尺度选择进行试验和研究,采用不同尺度对试验区不同分辨率遥感影像进行影像分割,并比较分割结果,得出成都平原高分辨率遥感影像数据分割最佳尺度与影像对象亮度均值标准差最大值所对应的分割尺度一致;并且遥感影像空间分辨率越高,最佳分割尺度越大,反之亦然。

Research on segmentation scale of multi-resources remotely sensed data in Chengdup lain

To classify the high-resolution remotely sensed data,the method applying the object-oriented image analysis is better than that of applying the traditional pixel-oriented analysis.The first key step is the image segmentation to applying the object-oriented analysis.The results of segmentation are obtaining a series of objects which relates to the real objects.The veracity of the segmentation relates to the selected segmentation scale.This thesis is study on the selection of segmentation scale of the high-re...