文献类型：期刊文献

中文题名：基于遗传和蚁群组合算法优化的遥感图像分割

英文题名：Segmentation of Remote Sensing Image Based on a Combination of Genetic Algorithm and Ant Colony Algorithm

作者：刘朔[1,3] 武红敢[2] 温庆可[1,3]

第一作者：刘朔

通信作者：Liu, S.

机构：[1]中国科学院遥感应用研究所,北京市100101;[2]中国林业科学研究院资源信息研究所,北京市100091;[3]中国科学院研究生院,北京市100039

年份：2009

卷号：34

期号：6

起止页码：679-683

中文期刊名：武汉大学学报：信息科学版

外文期刊名：Wuhan Daxue Xuebao (Xinxi Kexue Ban)/ Geomatics and Information Science of Wuhan University

收录：CSTPCD;;EI(收录号：20092712163715);Scopus(收录号：2-s2.0-67649212614);北大核心:【北大核心2008】；CSCD:【CSCD2011_2012】；

基金：国家863计划资助项目(2007AA12Z181)

语种：中文

中文关键词：遥感图像分割;小生境遗传算法;蚁群算法;三维熵;模糊聚类

外文关键词：segmentation of remote sensing images niche genetic algorithms ant colony algorithms three-dimensional entropy; fuzzy clustering

分类号：P237.4

摘要：将遗传算法和蚁群算法组合对模糊聚类进行优化,巧妙地对图像的像素特征和空间特征进行提取,利用这些特征作为聚类依据,将图像的多个特征结合到智能计算中,充分利用了遗传算法和蚁群算法各自的优势和特点,既提高了图像分割的准确性,又加快了分割过程的速度。实验结果表明,遗传算法和蚁群组合算法优化的模糊聚类是一种性能良好的遥感图像分割方法。
We combine genetic algorithm （GA） with ant colony algorithm （ACA）, which is introduced to optimize fuzzy cluster. Both pixel features and spatial features are extracted subtly, which are all used as cluster basis in intelligent computation. Niche genetic algorithm is used to optimize the course of looking for multiple optimal cluster centers. ACA is used to optimize the course of fuzzy clusters. In this way, the accuracy of image segmentation is im- proved greatly, and the course of image segmentation is accelerated as well. Experimental results show that the method proposed this paper is an efficient approach to segmentation of remote sensing image.