期刊
IEEE ACCESS
卷 6, 期 -, 页码 18582-18591出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2018.2820043
关键词
K-nearest neighbor; guided filter; spectral-spatial hyperspectral image classification
资金
- Natural Science Research Plan in Shaanxi Province [2016MJ4016]
- National Natural Science Foundation of China [61501287]
- Fundamental Research Funds for the Central Universities of Shaanxi Normal University [GK201703058]
Explosive growth of applications in hyperspectral image (HSI) has made HSI classification a hot topic in the remote sensing community. The key to improve classification accuracy is how to make full use of the spectral and spatial information. We combine k-nearest neighbor (KNN) algorithm with guided filter which can extract spatial context information and denoise the classification results by edge-preserving filtering. To solve the problem of dimension disaster, we also take dimensionality reduction into account for HSI classification. To verify the feasibility of our proposed methods, we evaluate the performance over four widely used hyperspectral data sets. The experimental results show that with only 5% of samples, our method obtained better performance than improved support vector machine and KNN methods.
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