摘要
针对支持向量机用于高光谱遥感影像分类存在的分类精度不高、参数选择困难等问题,提出一种再生核Hilbert空间的小波核。其可以逼近任意非线性函数,能够有效改进参数估计的效果,进而实现基于再生核Hilbert空间的小波核函数支持向量机(小波支持向量机)。并选取北京昌平地区的国产高光谱数据operational modular imaging spec-trometer II(OMIS II)和意大利Pavia大学ROSIS高光谱数据进行试验。结果表明,应用Coiflet小波核函数时能获得较高分类精度。
Some limitations exist in hyperspectral remote sensing image classification by SVM(support vector machine),such as unsatisfactory classification accuracy,difficult kernel parameter selection process and depen-dence on artificial tricks.In order to solve those problems,the wavelet SVM(WSVM) was proposed based on the investigation to SVM theory,reproducing kernel Hilbert space(RKHS) and the wavelet analysis.The wavelet kernel in RKHS can approximate arbitrary nonlinear functions and effectively handle the impacts of parameter selection.By experimenting the proposed algorithm with hyperspectral image captured by operational modular imaging spectrometer II(OMIS II) data from China and ROSIS data from Italy.The experimental results shown that Coiflet wavelet kernel function was the more effective wavelet in terms of classificiatoin accuracy improvement.
出处
《测绘学报》
EI
CSCD
北大核心
2011年第2期142-147,共6页
Acta Geodaetica et Cartographica Sinica
基金
国家自然科学基金(40401038)
国家863计划(2007AA12Z162)
高等学校博士学科点专项科研基金(20070290516)
江苏省普通高校研究生科研创新计划(CX08B_112Z)
中央高校基本科研业务费专项资金(2010QNA18)
关键词
高光谱遥感
小波支持向量机
再生核HILBERT空间
hyperspectral remote sensing
wavelet support vector machine(WSVM)
reproducing kernel Hilbert space