作　　者： ; ; ;

机构地区： 复旦大学信息科学与工程学院电子工程系

出　　处： 《数据采集与处理》 2011年第4期395-401,共7页

摘　　要： 提出一种基于模糊C均值聚类(Fuzzy C-means,FCM)和邻域分析的多通道遥感图像变化检测方法。通常的多通道遥感图像变化检测方法将变化信息从多个波段压缩到一个波段,损失了遥感图像的波段信息。本文将多波段变化信息用FCM方法来实现多通道遥感图像的变化检测。但由于FCM有对孤立点敏感的特点,该方法容易受噪声的影响。本文在FCM的基础上,又提出了一种结合图像空间邻域信息的多通道遥感图像变化检测方法,改进了FCM对孤立点敏感的问题。实验结果表明,相对于其他变化检测方法及FCM方法,所提出的基于FCM和邻域分析的多通道遥感图像变化检测方法能较好地消除遥感图像中变化检测中噪声的影响,具有很好的变化检测性能。 An unsupervised change detection method based on fuzzy C-means （FCM） clustering and neighborhood analysis is proposed. Usual change detection methods compress the change information into one-dimension change image, resulting in the loss of original multispectral information. Hence, the FCM method is introduced into the change detection problem of multichannel remote sensing images. However, the FCM method is sensitive to the isolated point, and its clustering result can be influenced by noise. Based on the FCM method, a new method combining FCM with neighborhood analysis is also proposed for unsupervised change detection in multichannel remote sensing images. Experimental results demonstrate that the proposed method can remove the influence of noise from the FCM algorithm and detect change information accurately.

关 键 词： 变化检测 模糊 均值聚类 邻域信息 多通道遥感图像

领　　域： [自动化与计算机技术] [自动化与计算机技术]