Feature selection of hyperspectral data through local correlation and SFFS for crop classification
Feature selection of hyperspectral data through local correlation and SFFS for crop classification
复制标题
DOI：
10.1109/igarss.2003.1293840
复制
发表时间：
2003-07
期刊：
影响因子：
--
通讯作者：
L. Gómez-Chova;J. Calpe-Maravilla;Gustau Camps-Valls;J. Martín-Guerrero;E. Soria-Olivas;J. Vila-Francés;L. Alonso;J. Moreno
中科院分区：
文献类型：
--
作者：
L. Gómez-Chova;J. Calpe-Maravilla;Gustau Camps-Valls;J. Martín-Guerrero;E. Soria-Olivas;J. Vila-Francés;L. Alonso;J. Moreno
在本文中，我们提出了一个程序，以减少高光谱数据的维数，同时保留相关信息的后验作物覆盖分类。高光谱图像处理的主要问题之一是涉及的数据量巨大。此外，模式识别方法对与高维特征空间相关联的问题（称为休斯维数灾难现象）敏感。我们提出了一种降维策略，消除冗余信息的本地相关性标准之间的连续谱带;和随后的选择最具鉴别力的功能的基础上的顺序浮点特征选择算法。该方法进行了测试，从同一地区的128波段HyMap光谱仪在DAISEX 99活动期间获得的六个高光谱图像的作物覆盖识别应用程序。在实验中，我们分析了依赖的维度和所采用的度量。使用高斯最大似然估计得到的结果提高了分类精度，并证实了所提出的方法的有效性。最后，我们分析了输入空间的选定波段，以获得有关问题的知识，并给出结果的物理解释。
In this paper, we propose a procedure to reduce dimensionality of hyperspectral data while preserving relevant information for posterior crop cover classification. One of the main problems with hyperspectral image processing is the huge amount of data involved. In addition, pattern recognition methods are sensitive to problems associated to high dimensionality feature spaces (referred to as Hughes phenomenon of curse of dimensionality). We propose a dimensionality reduction strategy that eliminates redundant information by means of local correlation criterion between contiguous spectral bands; and a subsequent selection of the most discriminative features based on a Sequential Float Feature Selection algorithm. This method is tested with a crop cover recognition application of six hyperspectral images from the same area acquired with the 128-bands HyMap spectrometer during the DAISEX99 campaign. In the experiments, we analyze the dependence on the dimension and employed metrics. The results obtained using the Gaussian Maximum Likelihood improve the classification accuracy and confirm the validity of the proposed approach. Finally, we analyze the selected bands of the input space on order to gain knowledge on the problem and to give a physical interpretation of the results.