作　　者： ; ; ; ; ;

机构地区： 西南林业大学

出　　处： 《光谱学与光谱分析》 2011年第1期177-183,共7页

摘　　要： 均值漂移算法是一种特征空间分析方法,广泛应用于自然场景影像和医学影像分割中。但算法较高的计算复杂度成为其在具有海量特性的遥感影像中应用的瓶颈。文章将均值漂移算法拓展到小波域,提出了一种小波域均值漂移快速分割算法。多光谱遥感影像和仿真影像的实验表明:在获得相当的分割结果的前提下,相比单尺度均值漂移算法,提出的分割算法能够提高处理速度5～7倍。 Mean Shift algorithm is a robust approach toward feature space analysis and it has been used wildly for natural scene image and medical image segmentation. However, high computational complexity of the algorithm has constrained its application in remote sensing images with massive information. A fast image segmentation algorithm is presented by extending traditional mean shift method to wavelet domain. In order to evaluate the effectiveness of the proposed algorithm, multispectral remote sensing image and synthetic image are utilized. The results show that the proposed algorithm can improve the speed 5-7 times compared to the traditional MS method in the premise of segmentation quality assurance.

关 键 词： 影像分割 均值漂移 小波变换

领　　域： [自动化与计算机技术] [自动化与计算机技术]