| 基于自适应参数估计的多时相遥感图像变化检测 |
| |
| 引用本文： | 钟家强,王润生.基于自适应参数估计的多时相遥感图像变化检测[J].测绘学报,2005,34(4):331-336. |
| |
| 作者姓名： | 钟家强 王润生 |
| |
| 作者单位： | 国防科学技术大学,ATR重点实验室,湖南,长沙,410073;国防科学技术大学,ATR重点实验室,湖南,长沙,410073 |
| |
| 摘 要： | 提出一种基于自适应参数估计实现多时相遥感图像的变化检测算法.首先应用分层Markov随机场模型建立多时相差分图像的统计模型;然后通过非监督的迭代自适应参数估计实现差分图像的分类,从而检测出变化的像元.在每次参数估计过程中,先将上次估计出的参数用于最大后验估计实现差分图像的分类,然后根据分类结果再对参数进行修正,并将修正后的参数用于下一次迭代分类,如此循环迭代,能够自适应地完成差分图像的参数估计与分类.
|
| 关 键 词： | 变化检测 自适应参数估计 EM 分层Markov随机场 |
| 文章编号： | 1001-1595（2005）04-0331-06 |
| 收稿时间： | 03 21 2005 12:00AM |
| 修稿时间： | 2005-03-212005-06-09 |
Multitemporal Remote Sensing Image Change Detection Based on Adaptive Parameter Estimation |
| |
| ZHONG Jia-qiang,WANG Run-Sheng.Multitemporal Remote Sensing Image Change Detection Based on Adaptive Parameter Estimation[J].Acta Geodaetica et Cartographica Sinica,2005,34(4):331-336. |
| |
| Authors: | ZHONG Jia-qiang WANG Run-Sheng |
| |
| Institution: | A TR National Laboratory, National University of Defense Technology, Changsha 410073, China |
| |
| Abstract: | An image change detection algorithm based on adaptive parameter estimation for multi-temporal remote sensing is proposed in this paper.Firstly,hierarchical Markov Random Fields(HMRF) model is used to combine both statistical and contextual property of difference image.Secondly,an unsupervised iterative adaptive parameter estimation method is used for difference image classification and changed pixels detection.In each iterative of parameter estimation,parameter obtained by last iterative is used for difference image MAP classification at first.Then,it is adjusted according to the result of the MAP classification.In such cycles iterative,parameter estimation and difference image classification can be performed adaptively. |
| |
| Keywords: | change detection adaptive parameter estimation EM hierarchical MRF |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
