基于D-S理论的多特征遥感影像变化检测方法

Multi-feature Remote Sensing Image Change Detection Method Based on D-S Evidence Theory

针对当前遥感影像变化检测特征单一与几何配准要求较高的问题,提出了一种将证据理论融合到影像多特征变化检测之中的方法。利用检索窗口与匹配窗口计算前后时相影像的几种特征结构相似度,并运用D-S证据理论计算出基本概论赋值函数,完成对这些特征的融合。通过变化检测实验,发现该法能有效提高变化检测的精度,不失为一种变化检测有效方法。除此之外,该法对辐射校正精度要求不高,这一点明显优于传统的单一特征变化检测方法。

In order to solve the problem of the single feature and high requirements of geometric registration of remote sensing image during change detection,a new method based on evidence theory is proposed.The retrieval window and the matching window are used to calculate the similarity of the feature structure of the pre and post phase images,and the D-S evidence theory is used to calculate the basic probability assignment function to complete feature fusion.The change dectection experiment found that the method can effectively improve the accuracy of change detection,which is an effective method for change detection.In addition,this method does not require high accuracy of radiometric correction,which is obviously better than the traditional single feature change detection method.