首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于Quick Shift算法的高光谱影像分类
引用本文:祝鹏飞,冯伍法,张斌,包全福,槐慧临.基于Quick Shift算法的高光谱影像分类[J].测绘学院学报,2011(1).
作者姓名:祝鹏飞  冯伍法  张斌  包全福  槐慧临
作者单位:信息工程大学测绘学院;95806部队;91206部队;
基金项目:国家863计划资助项目(2006AA701309)
摘    要:论述了面向对象分类方法处理高光谱高空间分辨率影像的优势与流程;分析了快速漂移(Quick Shift)算法的原理,该算法在进行模式搜索时具有可控制模态选择和平衡过分割与欠分割的特点。将该算法应用于高光谱影像分割,可得到面向对象分类所需的较理想的同质影像对象。为提高影像分割的效率,提出了一种基于灰度共生矩阵的自适应核带宽确定方法,能够兼顾影像空间特征和光谱特征。最后采用最小距离分类法、支持向量机分类法与提出的分类方法进行了对比试验,实验结果表明了该方法的有效性。

关 键 词:面向对象分类  高光谱影像  快速漂移  灰度共生矩阵  自适应带宽  

Hyperspectral Imagery Classification Based on Quick Shift
ZHU Peng-fei,FENG Wu-fa,ZHANG Bin,BAO Quan-fu,HUAI Hui-lin.Hyperspectral Imagery Classification Based on Quick Shift[J].Journal of Institute of Surveying and Mapping,2011(1).
Authors:ZHU Peng-fei  FENG Wu-fa  ZHANG Bin  BAO Quan-fu    HUAI Hui-lin
Institution:ZHU Peng-fei1,FENG Wu-fa1,ZHANG Bin1,BAO Quan-fu1,2,HUAI Hui-lin3(1.Institute of Surveying and Mapping,Information Engineering University,Zhengzhou 450052,China,2.95806 Troops,Beijing 100076,3.91206 Troops,Qingdao 266108,China)
Abstract:The advantages and process of classifying hyperspectral imagery with high spatial resolution via object-oriented classification were expounded.The theory of Quick Shift was analyzed,which can control the mode selection and balance under-and over-fragmentation in mode seeking.The algorithm was applied to segment hyperspectral imagery to obtain the ideal homogeneity objects used in object-oriented classification.In order to improve the segment efficiency,an adaptive kernel bandwidth selection method based on ...
Keywords:object-oriented classification  hyperspectral imagery  Quick Shift  gray level co-occurrence matrix  adaptive bandwidth  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号