面向对象的遥感图像分类方法研究

Study of Object-Oriented Based Remote Sensing Image Classification

影响遥感图像分类效果的主要因素之一是空间分辨率。通过融合多分辨率遥感图像,引入面向对象的思想,有效地克服了多光谱图像空间分辨率低的问题。该方法由图像分割和分类等一系列技术组成,首先用基于区域分割法则对正射校正SPOT图像进行分割,然后把它作为参考用最大似然法分类器和其他一些经验规则对TM图像进行分类。对土地覆盖图分类进行精度测试,取得了良好的应用效果。

A limitation in efficiently applying image classification is often represented by the spatial resolution of the image. By merging the multi resolution remote sensing image, importing the object oriented based idea, it effectively renewed the low resolution problem of multi-spectral images. This method was made up of a series of image segmentation and classification technique. First, the orthograph revised SPOT image was segmented by applying a region-based segmentation algorithm. Based this reference map, TM image was classified using the maximum likelihood classifier and additional empirical rules. Finally, the resulting land cover map was tested for accuracy and gained some effects.