| 关联向量机在高光谱影像分类中的应用 |
| |
| 引用本文： | 董超,赵慧洁.关联向量机在高光谱影像分类中的应用[J].遥感学报,2010,14(6):1279-1284. |
| |
| 作者姓名： | 董超 赵慧洁 |
| |
| 作者单位： | 北京航空航天大学,仪器科学与光电工程学院,教育部精密光机电一体化技术实验室,北京,100191 |
| |
| 基金项目： | 863 计划重点项目(编号: 2008AA121102)和中国地质调查局项目(编号: 1212010816033)。 |
| |
| 摘 要： | 将关联向量机应用于高光谱影像分类, 实现高维空间中训练样本不足时分类器的精确建模。从稀疏贝叶
斯理论出发, 分析关联向量机原理, 探讨一对多、一对一和两种直接的多分类方法。实验环节比较了各种多分类方
法, 并从精度、稀疏性两方面将关联向量机与支持向量机等经典算法比较。实验结果表明, 两种直接的多分类方法
内存占用大、效率低; 一对多精度最高, 但效率较低; 一对一计算效率最高, 精度与一对多近似。关联向量机精度
不如支持向量机, 但解更稀疏, 测试样本较多时实时性好, 适合处理大场景高光谱影像的分类问题。
|
| 关 键 词： | 遥感 分类 关联向量机 高光谱 |
| 收稿时间： | 2009/11/9 0:00:00 |
| 修稿时间： | 2010/5/16 0:00:00 |
Hyperspectral image classification and application based on\nrelevance vector machine |
| |
| DONG Chao and ZHAO Huijie.Hyperspectral image classification and application based on\nrelevance vector machine[J].Journal of Remote Sensing,2010,14(6):1279-1284. |
| |
| Authors: | DONG Chao and ZHAO Huijie |
| |
| Institution: | Precision Opto-mechatronics Technology, Key Laboratory of Education Ministry, School of Instrument Science and Opto-electronics
Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China;Precision Opto-mechatronics Technology, Key Laboratory of Education Ministry, School of Instrument Science and Opto-electronics
Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China |
| |
| Abstract: | The relevance vector machine (RVM) is used to process the hyperspectral image in this paper to estimate the
classifiers precisely in the high dimensional space with limited training samples. The detail of RVM is firstly discussed based on
the sparse Bayesian theory. Then four multi-class strategies are analyzed, including One-vs-All (OAA), One-vs-One (OAO) and
two direct multi-class strategies. In the experiments, the multi-class strategies are compared and RVM is further compared with
several classical classifiers, including the support vector machine (SVM). The experiments show that two direct multi-class
strategies occupy too much memory space with low efficiency. OAA has the highest precision, but is low in efficiency. OAO is
the best in efficiency and the precision approximates to OAA. Compared with SVM, RVM is low in precision, but sparser than
SVM. The sparse property is important when the test set is large, which makes RVM suitable for classifying the large-scale
hyperspectral image. |
| |
| Keywords: | remote sensing classification relevance vector machine hyperspectral |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《遥感学报》浏览原始摘要信息 |
| 点击此处可从《遥感学报》下载免费的PDF全文 |
|
