| 利用SVM-CRF进行高光谱遥感数据分类 |
| |
| 引用本文： | 李祖传,马建文,张睿,李利伟.利用SVM-CRF进行高光谱遥感数据分类[J].武汉大学学报(信息科学版),2011(3):306-310. |
| |
| 作者姓名： | 李祖传 马建文 张睿 李利伟 |
| |
| 作者单位： | 中国科学院对地观测与数字地球科学中心;中国科学院研究生院;中国科学院遥感应用研究所; |
| |
| 基金项目： | 国家自然科学基金资助项目(40901234); 中国科学院知识创新工程青年人才领域前沿项目专项资助项目(O8S01100CX) |
| |
| 摘 要： | 提出了一种改进的随机场模型SVM-CRF,它以支持向量机作为条件随机场的一阶势能项,结合了支持向量机和条件随机场的优点。采用AVIRIS高光谱遥感数据进行实验,对SVM-CRF模型进行了分析,结果表明,在分类精度上SVM-CRF优于支持向量机和传统条件随机场模型。
|
| 关 键 词： | 支持向量机 条件随机场 高光谱数据 |
Classifying Hyperspectral Data Using Support Vector Machine Conditional Random Field |
| |
| LI Zuchuan, MA Jianwen ZHANG Rui, LI Liwei.Classifying Hyperspectral Data Using Support Vector Machine Conditional Random Field[J].Geomatics and Information Science of Wuhan University,2011(3):306-310. |
| |
| Authors: | LI Zuchuan MA Jianwen ZHANG Rui LI Liwei |
| |
| Institution: | LI Zuchuan1,2 MA Jianwen1 ZHANG Rui2,3 LI Liwei1 (1 Center for Earth Observation and Digital Earth,Chinese Academy of Sciences,9 Beiyitiao,Zhongguancun,Beijing 100190,China) (2 Graduate University of Chinese Academy of Sciences,A19 Yuquan Road,Beijing 100049,China) (3 Institute of Remote Sensing Applications,A20 Datun Road,Beijing 100101,China) |
| |
| Abstract: | With there problems at hands,an improved random field,support vector machine conditional random field(SVM-CRF) was proposed.It uses SVM as its unary potential,combining the merits of SVM and CRF.Experiments using AVIRIS hyperspectral data as input were carried out,and SVM-CRF was analyzed extensively.Experimental results show that SVM-CRF is superior to SVM and classic CRF in terms of classification accuracies. |
| |
| Keywords: | support vector machine conditional random field hyperspectral data |
| 本文献已被 CNKI 等数据库收录！ |
|
