面向对象特征融合的高分辨率遥感图像变化检测方法  

Object-oriented change detection method based on features fusion for high-resolution remote sensing image

作　　者：王文杰[1] 赵忠明[1] 朱海青[1] 

机构地区：[1]中国科学院遥感应用研究所图像室,北京100101

出　　处：《计算机应用研究》2009年第8期3149-3151,共3页Application Research of Computers

基　　金：国家"十一五"科技支撑计划重大资助项目(2006BAJ05A06)

摘　　要：针对高分辨率遥感图像变化检测的难点和传统像元级变化检测方法的局限性,提出了基于面向对象的思想,利用分割后图像对象的光谱特征、纹理特征、形状特征分别进行变化检测,然后将不同对象特征检测结果进行融合得到最终结果。实验表明了本方法比传统的像素级方法对高分辨率遥感图像变化检测有较强的优势。To address the limitations of traditional pixel-level change detection methods and the difficulties of change detection of high resolution remote sensing images, based on object-oriented thinking ,this paper presented a novel way to use the spectral features, texture features, shape features of the segment objects to do change detection, and then made fusion of the change detection results of the different features to get the final result. Experiments show that the method has a stronger advan- tage than the traditional pixel-level method for high-resolution remote sensing image change detection.

关 键 词：面向对象 图像分割 尺度 光谱特征 纹理特征 形状特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]