| MRF和GM模型高光谱图像地物标记 |
| |
| 引用本文： | 黄廷祝,黄秀琴,蒋泽云.MRF和GM模型高光谱图像地物标记[J].电子科技大学学报(社会科学版),2008(5). |
| |
| 作者姓名： | 黄廷祝 黄秀琴 蒋泽云 |
| |
| 作者单位： | 电子科技大学应用数学学院; |
| |
| 基金项目： | 国家自然科学基金(60375012) |
| |
| 摘 要： | 利用马尔可夫随机场和高斯混合模型构造了一种对高光谱图像进行地物标记的新方法。该方法利用PCA降维后的高光谱图像及其差分图像的先验信息建立高光谱图像的随机模型,并把最大后验估计作为地物标记优化的评判标准,用模拟退火算法实现地物标记。实验结果显示该算法是一种精确、高效、稳定的图形标记算法。
|
| 关 键 词： | 高斯混合模型 高光谱图像 标记 马尔可夫随机场 |
Hyperspectral Image Labeling Using MRF and GM Models |
| |
| HUANG Ting-zhu,HUANG Xiu-qin, JIANG Ze-yun.Hyperspectral Image Labeling Using MRF and GM Models[J].Journal of University of Electronic Science and Technology of China(Social Sciences Edition),2008(5). |
| |
| Authors: | HUANG Ting-zhu HUANG Xiu-qin JIANG Ze-yun |
| |
| Institution: | HUANG Ting-zhu,HUANG Xiu-qin,, JIANG Ze-yun (School of Applied Mathmatics,University of Electronic Science , Technology of China Chengdu 610054) |
| |
| Abstract: | Based on Markov Random Fields (MRF) and Gaussian Mixture (GM) models,a new method to label surface features using hyperspectral imaging is presented. The dimension of the hyperspectral image is reduced by PCA,and the stochastic model is built based on prior of the dimension-reduced images and its difference images. Then the maximum posteriori is designed as the optimal criterion and the final labels are obtained by the simulated annealing algorithm. Experimental results show that this method is accurate,eff... |
| |
| Keywords: | Gaussian mixture model (GMM) hyperspectral image labeling Markov random field |
| 本文献已被 CNKI 等数据库收录！ |
