摘要
高光谱遥感数据波段多、数据量大的优点同样给数据处理带来了极大的困难,通过对已有常见波段选择方法的研究,发现其无法同时满足所选择波段相关性小、所含信息量大且光谱可分性好等要求。针对以上问题,本文提出了一种新的方法,综合使用了子空间划分、自适应波段选择和光谱可分性距离等方法,得到最优波段组合。
The advantages of hyperspectral remote sensing data which are many bands and huge amount of data,have also brought much difficulty to data processing.After the research of the existed methods of band selection,to satisfy the three needs simultaneously would not come true,that are lower relevance of bands,large amount of information,and better separability of spectrals.To solve the above problems,this article proposed a new method to obtain the best band combination,which integratedly used subspace partition,adaptive band selection and spectral separability distance method and so on.
出处
《测绘与空间地理信息》
2010年第3期137-139,共3页
Geomatics & Spatial Information Technology
关键词
高光谱遥感
波段选择
子空间划分
自适应波段选择
光谱可分性距离
hyperspectral remote sensing
band selection
subspace partition
adaptive band selection
spectral divisibility distance
