首页 >  2009, Vol. 13, Issue (3) : 445-457

摘要

全文摘要次数: 3885 全文下载次数: 68
引用本文:

DOI:

10.11834/jrs.20090308

收稿日期:

2007-09-19

修改日期:

2007-11-13

PDF Free   HTML   EndNote   BibTeX
改进的P-SVM支持向量机与遥感数据分类
1.中国科学院 遥感应用研究所, 北京 100101;2.中国科学院 研究生院, 北京 100049
摘要:

本文介绍了将P-SVM算法引入多光谱/高分辨率遥感数据的分类, 并且展示了卫星ASTER和航空ADS40数字影像分类的技术过程和结果验证。结果表明:P-SVM方法的分类精度不低于SVM, 并减少了时耗。

Improved support vector machine and classification for remotely sensed data
Abstract:

In this paper, the P-SVM algorithm was introduced into multi-spectral/high-spatial resolution remotely sensed data classification and it is applied to classification of ASTER satellite data and ADS40 aerial digital data. The experiments indicate that the P-SVM is at least competitive with the standard SVM algorithm in classification accuracy of remotely sensed data and the time needed is less.

本文暂时没有被引用!

欢迎关注学报微信

遥感学报交流群