摘要
为了进一步提高高光谱图像的分类精度,提出一种基于局部高斯混合特征提取的分类(LGMFEC)方法。LGMFEC方法首先基于高光谱图像的空间结构为每个样本构建局部邻域集合,然后从局部邻域集合中提取高斯混合特征来充分表征空间-光谱信息及相关变化信息,最后将局部高斯混合特征融入包含黎曼核函数的支持向量机(SVM)分类器中,从而完成分类任务。三组通用高光谱数据集的实验结果表明,LGMFEC方法的分类性能在较大程度上优于几种先进的分类方法,尤其在训练样本较少的情况下的优势更为明显。
In order to further improve the classification accuracy of hyperspectral images, a classification method based on local Gaussian mixture feature extraction(LGMFEC) is proposed. The LGMFEC method first constructs a local neighborhood set for each sample based on the spatial structure of the hyperspectral image, and then extracts Gaussian mixture features from the local neighborhood set to fully characterize the spatial-spectral information and the related change information between them, and finally the local Gaussian mixture features are integrated into a support vector machine(SVM) classifier containing a Riemann kernel function to complete the classification task. The experimental results of three sets of general hyperspectral datasets show that the classification performance of the LGMFEC method is better than several advanced classification methods to a large extent, especially when there are fewer training samples.
作者
李丹
孔繁锵
朱德燕
Li Dan;Kong Fanqiang;Zhu Deyan(Key Laboratory of Space Photoelectric Detection and Perception,Ministry of Industry and Information Techmology,Nanjing University of Aeronautics and Astronautics,Nanjing,Jiangsu 210016,China;College of Astronautics,Nanjing Unirersity of Aeromautics and Astronautics,Nanjing,Jiangsu 210016,China)
出处
《光学学报》
EI
CAS
CSCD
北大核心
2021年第6期72-83,共12页
Acta Optica Sinica
基金
国家自然科学基金青年科学基金(61801214)
南京航空航天大学空间光电探测与感知工业和信息化部重点实验室开放课题资助(NJ2020021-03)
中央高校基本科研业务费资助(NJ2020021)。
关键词
图像处理
高光谱图像
分类
特征提取
高斯混合模型
image processing
hyperspectral image
classification
feature extraction
Gaussian mixture model
