An improved classification method for hyperspectral data based on spectral and morphological information
An improved classification method for hyperspectral data based on spectral and morphological information
复制标题
一种基于光谱和形态信息的改进高光谱数据分类方法
DOI：
10.1080/01431161.2010.510488
复制
发表时间：
2011-05
影响因子：
3.4
通讯作者：
Ma, Jianwen
中科院分区：
文献类型：
--
作者：
Li, Zuchuan;Li, Liwei;Zhang, Rui;Ma, Jianwen
将光谱和形态信息相结合对高光谱数据进行分类，与仅基于光谱或形态数据的方法相比具有相当大的优势。以前，提出了一种分类方法，级联扩展形态轮廓（EMP）和光谱信息到一个特征向量的图像的每个像素。虽然这种方法具有同时使用光谱和形态信息的优点，但它存在产生新的光谱成分（在原始图像中不存在）的风险。本文提出了一种基于扩展多元形态轮廓（EMMP）和光谱信息融合的改进分类方法。采用基于光谱纯度准则的矢量排序方法，克服了EMP产生新组分的问题。为了提高EMMP的效率，提出了一种特征选择算法。对美国航天局机载可见光-红外成像光谱仪传感器收集的超光谱数据集进行了实验。实验结果表明，EMMP方法能够有效地描述高光谱数据中的形态信息，分类精度上级优于前一种方法，但在时间消耗上不如前一种方法。
Combining spectral and morphological information to classify hyperspectral data offers a considerable advantage over methods based solely on spectral or morphological data. Previously, a classification method was proposed that concatenated extended morphological profile (EMP) and spectral information into one feature vector for each pixel of an image. Although this method has the merit of simultaneously using spectral and morphological information, it runs the risk of generating new spectral constituents (not present in the original image). In this letter, an improved classification method based on fusing extended multivariate morphological profile (EMMP) and spectral information was proposed. A new vector ordering method based on spectral purity-based criterion was adopted to overcome the problem of generating new constituents in EMP. A feature selection algorithm was employed to improve the efficiency of EMMP. Experiments were carried out on a hyperspectral data set collected by NASA's Airborne Visible-Infrared Imaging Spectrometer sensor. Experimental results showed that EMMP was effective at describing morphological information in hyperspectral data, and that this letter's method was superior to the previous method in terms of classification accuracy but inferior to the previous method in terms of time consumption.
登录
查看更多内容
DOI：
10.1155/asp.2005.2196
发表时间：
2005-08-11
期刊：
EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING
影响因子：
--
作者：
Jin, XY;Davis, CH
通讯作者：
Davis, CH
影响因子：
8
作者：
Aptoula, E.;Lefevre, S.
通讯作者：
Lefevre, S.
DOI：
10.1109/tgrs.2008.922034
发表时间：
2008-11-01
影响因子：
8.2
作者：
Fauvel, Mathieu;Benediktsson, Jon Atli;Sveinsson, Johannes R.
通讯作者：
Sveinsson, Johannes R.
DOI：
10.1109/tgrs.2002.802494
发表时间：
2002-09-01
影响因子：
8.2
作者：
Plaza, A;Martínez, P;Plaza, J
通讯作者：
Plaza, J
影响因子：
8.2
作者：
P. Zhong;Runsheng Wang
通讯作者：
P. Zhong;Runsheng Wang