基于像素比值的面向对象分类后遥感变化检测方法

An Object-oriented Post-classification Remote Sensing Change Detection after the Pixel Ratio

结合基于像素的变化检测和面向对象分类后变化检测方法的各自特点,提出首先由改进后小窗口像素均值比值法确定一个发生变化的最小范围,然后在这个确定的最小范围的基础上进行面向对象分类后比较,最终确定分类图斑类型信息变化的方法。通过对北京房山区2002年、2006年两期SPOT5影像进行实验分析,评价结果表明本方法大大降低了传统变化检测方法因对未发生变化区域分类产生的误差传递的影响,从而提高了检测结果的精度。

In this paper,a change detection approach integrating the pixel-based change detection and the object-oriented post-classification change detection is introduced.The change region is found firstly through a pixel ration method based on minimum mean;then the object-based post-classification comparison method can be utilized in this change region. Therefore,the land change status will be determined.Two SPOT5 images respectively in 2002 and 2006 were tested in this paper.The result shown that this method can improve the accuracy of the change detection,because only the change region can be detected in this approach.