期刊
INTERNATIONAL JOURNAL OF REMOTE SENSING
卷 36, 期 5, 页码 1307-1328出版社
TAYLOR & FRANCIS LTD
DOI: 10.1080/01431161.2015.1009652
关键词
-
资金
- National Science Foundation of China [61101168, 41371338]
- Basic and Frontier Research Programmes of Chongqing [cstc2013jcyjA40005]
- China Postdoctoral Science Foundation [2012M511906, 2013T60837, XM2012001]
- Science and Technology Project from the Land Resource and Housing Management Bureau of Chongqing [CQGT-KJ-2012028]
- Fundamental Research Funds for the Central Universities of China [106112013CDJZR125501, 1061120131204]
Graph-embedding (GE) algorithms have been widely used for dimensionality reduction (DR) of hyperspectral imagery (HSI), and k-nearest neighbour and is an element of-radius ball are usually used for graph construction in GE. However, the two approaches are sensitive to data noise and the optimum of k (or is an element of) is datum-dependent. In this paper, we propose a new supervised DR algorithm, called sparse discriminant learning (SDL), based on l(1)-graph for HSI classification. It constructs an inter-and an intra-manifold weight matrix that are computed from l(1)-graph, which is robust to data noise and the number of neighbours is adaptively selected to each sample. Then, the SDL algorithm seeks optimal projections with inter-and intra-manifold scatter, which can be formulated based on the modified sparse reconstruction weights. SDL not only reserves sparse reconstructive relations through l(1)-graph, but also enhances inter-manifold separability. Experiments on synthetic data and two real hyperspectral image data sets collected by AVIRIS and HDYICE sensors are performed to demonstrate the effectiveness of the SDL algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据