首页 | 本学科首页   官方微博 | 高级检索  
     

基于多随机场遥感图像分割
引用本文:张翔,田金文,李峰. 基于多随机场遥感图像分割[J]. 华中科技大学学报(自然科学版), 2003, 31(8): 24-26
作者姓名:张翔  田金文  李峰
作者单位:华中科技大学图像识别与人工智能研究所图像信息处理与智能控制教育部重点实验室
基金项目:国家高技术研究发展计划资助项目 (86 3 2 0 0 2AA1 330 1 0 )
摘    要:结合二维Wold分解技术来对遥感图像进行分割,将图像分解为确定性随机场和纯不确定性随机场,通过调整它们之间的比例关系,来加强纹理边缘,从而改善马尔可夫标记场模型对纹理边缘过平滑的现象.实验对城区目标进行提取,结果表明本方法的有效性优于纯马尔可夫随机场所采取的分割方法.

关 键 词:遥感图像 马尔可夫随机场 纹理分割 Wold分解
文章编号:1671-4512(2003)08-0024-03
修稿时间:2002-11-06

Segmentation of remote sensing image based on multirandom field
Zhang Xiang Tian Jinwen Li Feng Zhang Xiang Doctoral Candidate, Institute for Pattern Recognition and Artificial Intelligence,Huazhong Univ. of Sci. , Tech.,Wuhan ,China.. Segmentation of remote sensing image based on multirandom field[J]. JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE, 2003, 31(8): 24-26
Authors:Zhang Xiang Tian Jinwen Li Feng Zhang Xiang Doctoral Candidate   Institute for Pattern Recognition  Artificial Intelligence  Huazhong Univ. of Sci. & Tech.  Wuhan   China.
Affiliation:Zhang Xiang Tian Jinwen Li Feng Zhang Xiang Doctoral Candidate, Institute for Pattern Recognition and Artificial Intelligence,Huazhong Univ. of Sci. & Tech.,Wuhan 430074,China.
Abstract:The remote sensing image was segmented by 2 d Wold decomposition. The decomposition includes deterministic random field and pure indeterministic one. The latter was regarded as Markov random field model. By this decomposition, the construction of image was adjusted to have better segmentation compact. Result of segmentation was presented and compared.
Keywords:remote sensing image  Markov random field  texture segmentation  Wold decomposition
本文献已被 CNKI 维普 万方数据 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