| 高光谱影像概率分类向量机分类方法研究 |
| |
| 引用本文： | 薛志祥,余旭初,张鹏强,谭熊,魏祥坡.高光谱影像概率分类向量机分类方法研究[J].测绘科学技术学报,2016(4):426-430. |
| |
| 作者姓名： | 薛志祥 余旭初 张鹏强 谭熊 魏祥坡 |
| |
| 作者单位： | 1. 信息工程大学，河南 郑州 450001; 地理信息工程国家重点实验室，陕西 西安 710054;2. 信息工程大学,河南 郑州,450001 |
| |
| 基金项目： | 地理信息工程国家重点实验室开放研究基金项目(SKLGIE2015-M-3-1;SKLGIE2015-M-3-2)，国家测绘地理信息局重点实验室经费项目( KLSMTA-201603)。 |
| |
| 摘 要： | 从分析基于支持向量机和相关向量机的高光谱影像分类方法的优势和不足出发,将基于概率分类向量机的方法用于高光谱影像分类试验。在贝叶斯理论框架下,概率分类向量机为基函数权值引入截断Gauss先验概率分布,使得不同类别的基函数权值具有不同符号的先验分布,并利用EM算法进行参数推断,得到足够稀疏的概率模型,弥补了相关向量机选取错误类别的样本作为相关向量的不足,从而有效地提高了模型的分类精度和稳定性。OMIS和PHI影像分类试验表明,概率分类向量机能够很好地应用在高光谱影像分类。
|
| 关 键 词： | 高光谱影像 稀疏分类 贝叶斯模型 概率分类向量机 相关向量机 |
Research on Probabilistic Classification Vector Machines for Hyperspectral Imagery Classification |
| |
| XUE Zhixiang,YU Xuchu,ZHANG Pengqiang,TAN Xiong,WEI Xiangpo.Research on Probabilistic Classification Vector Machines for Hyperspectral Imagery Classification[J].Journal of Zhengzhou Institute of Surveying and Mapping,2016(4):426-430. |
| |
| Authors: | XUE Zhixiang YU Xuchu ZHANG Pengqiang TAN Xiong WEI Xiangpo |
| |
| Abstract: | Though the support vector machine and relevance vector machine have been successfully applied in hy-perspectral imagery classification, they also have several limitations. In this paper, a hyperspectral imagery classi-fication method based on the probabilistic classification vector machines is proposed. In the Bayesian framework, a signed and truncated Gaussian prior is adopted over every weight in the probabilistic classification vector machines, where the sign of prior is determined by the class label, and the EM algorithm has been adopted for the parametric inference to obtain a sparse model. This algorithm can solve the problem that the relevance vector machine is based on some untrustful vectors, which influences the accuracy and stability of the model. The experiments on the OMIS and PHI images are performed, and the results show the advantages of the hyperspectral imagery classification method based on probabilistic classification vector machines. |
| |
| Keywords: | hyperspectral imagery sparse classification Bayesian model probabilistic classification vector ma-chines relevance vector machine |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
