| 顾及特征优化的全极化SAR图像SVM分类 |
| |
| 引用本文： | 巫兆聪,欧阳群东,李芳芳. 顾及特征优化的全极化SAR图像SVM分类[J]. 测绘科学, 2013, 38(3): 115-117,139 |
| |
| 作者姓名： | 巫兆聪 欧阳群东 李芳芳 |
| |
| 作者单位： | 1. 武汉大学遥感信息工程学院,武汉,430079
2. 国防科技大学C4ISR技术国防科技重点实验室,长沙,410073 |
| |
| 基金项目： | 国家863计划资助项目，国家自然科学基金资助项目 |
| |
| 摘 要： | 以支持向量数和相关性分析为评估依据,结合序列前进搜寻策略,本文提出一种顾及特征优化的改进SVM分类方法,并将其应用于全极化SAR图像监督分类。真实数据的实验结果表明,该方法不仅具有小样本情况下的良好泛化性能,而且能以更少的特征个数,在更广泛的SVM参数取值范围内获得更高的分类精度。
|
| 关 键 词： | 极化SAR 特征优化 监督分类 支持向量机 |
A SVM-based classification method for fully polarimetric SAR imagery considering feature optimization |
| |
| WU Zhao-cong,OUYANG Qun-dong,LI Fang-fang. A SVM-based classification method for fully polarimetric SAR imagery considering feature optimization[J]. Science of Surveying and Mapping, 2013, 38(3): 115-117,139 |
| |
| Authors: | WU Zhao-cong OUYANG Qun-dong LI Fang-fang |
| |
| Affiliation: | ②(①School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 430079,China;②Key Lab of C4ISR Technology of National Defense Science and Technology,National Univ.of Defense Technology,Changsha 410073,China) |
| |
| Abstract: | An improved SVM classification method for fully polarimetric SAR imagery concerned with feature optimization was proposed in this paper,which is based on the assessment of support vector number and correlation analysis,and combining with SFS search strategy.Experimental results showed that the proposed method could not only retain good generalization with limited samples,but also obtain higher classification accuracy with less number of features in a wider range of SVM parameters. |
| |
| Keywords: | polarimetric Synthetic Aperture Radar feature optimization supervised classification Support Vector Machine |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
