| 面向高光谱图像分类的半监督空谱判别分析 |
| |
| 引用本文： | 侯榜焕,王锟,姚敏立,贾维敏,王榕.面向高光谱图像分类的半监督空谱判别分析[J].测绘学报,2017,46(9):1098-1106. |
| |
| 作者姓名： | 侯榜焕 王锟 姚敏立 贾维敏 王榕 |
| |
| 作者单位： | 1. 火箭军工程大学信息工程系, 陕西 西安 710025;2. 国家计算机网络应急技术处理协调中心, 北京 100029 |
| |
| 基金项目： | 国家自然科学基金青年科学基金，中国博士后科学基金(2014M562636)The Young Scientists Fund of the National Natural Science Foundation of China，The China Postdoctoral Science Foundation |
| |
| 摘 要： | 为充分利用高光谱图像蕴藏的空间信息提升分类精度,提出了面向高光谱图像分类的半监督空谱判别分析(S3 DA)算法。考虑高光谱图像数据集的空间一致性,首先利用少量标记样本定义类内散度矩阵,保存数据集同类像元的光谱近邻结构;再利用无标记样本定义空间近邻像元散度矩阵,揭示像元间的空间近邻结构和地物的空间分布结构信息。S3 DA既保持数据集在光谱域的可分性,又保存了无标记样本蕴藏的空间域近邻结构,增强了同类像元和空间近邻像元在投影子空间的聚集性,从而提升分类性能。在PaviaU和Indian Pines数据集的试验表明,总体分类精度分别达到81.50%和71.77%。与传统的光谱方法比较,该算法能有效提升高光谱图像数据集的地物分类精度。
|
| 关 键 词： | 高光谱图像分类 特征提取 判别分析 空谱联合 半监督学习 空间近邻 |
| 收稿时间： | 2017-03-20 |
| 修稿时间： | 2017-07-24 |
Semi-supervised Spati al-spectral Discriminant Analysis for Hyperspectral Image Classification |
| |
| HOU Banghuan,WANG Kun,YAO Minli,JIA Weimin,WANG Rong.Semi-supervised Spati al-spectral Discriminant Analysis for Hyperspectral Image Classification[J].Acta Geodaetica et Cartographica Sinica,2017,46(9):1098-1106. |
| |
| Authors: | HOU Banghuan WANG Kun YAO Minli JIA Weimin WANG Rong |
| |
| Institution: | 1. Department of Information Engineering, Rocket Force Engineering University, Xi'an 710025, China;2. National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing 100029, China |
| |
| Abstract: | In order to make full use of the spatial information embedded in the hyperspectral image to improve the cl assification accuracy , a semi-supervised spati al-spectral discriminant analysis (S3 DA ) algorithmfor hyperspectral image classification is proposed .According to the spatial consistency property of hyperspectral image ,the intra-class scatter matrix infered from a little labeled samples preserves the spectral similarity of the same class pixels ,while the spatial local pixel scatter matrix defined by the unlabeled spatial neighbors uncovers the spatial-domain local pixel neighborhood structures and the ground objects detailed distribution .The S3DA method not only maintains the spectral-domain separability of the data set ,but also preserves the spatial-domain local pixel neighborhood structure ,which promotes the compactness of the same class pixels or the spatial neighbor pixels in the projected subspace and enhances the classification performance .The overall classification accuracies respectively reach 815.0% and 717.7% on the PaviaU and Indian Pines data sets .Compared with the traditional spectral methods ,the proposed method can effectively improve ground objects classification accuracy . |
| |
| Keywords: | hyperspectral image classification feature extraction discriminant analysis spatial-spectral semi-supervised learning spatial neighbors |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《测绘学报》浏览原始摘要信息 |
| 点击此处可从《测绘学报》下载免费的PDF全文 |
|
