期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 56, 期 9, 页码 5408-5423出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2018.2815613
关键词
Convolutional neural network (CNN); deep learning; hyperspectral image
类别
资金
- Shenzhen Science and Technology Program [JCYJ20160330163900579, JCYJ20170413105929681, JCYJ20170811160212033]
- RGC of the Hong Kong SAR [CityU 11502115, CityU 11525716]
- National Natural Science Foundation of China (NSFC) Basic Research Program [71671155]
- Shenzhen Municipal Science and Technology Innovation Fund [JCYJ20160229165300897]
- CityU Shenzhen Research Institute
- NSFC [61562027]
- Education Department of Jiangxi Province [GJJ170413]
Deep learning has achieved great successes in conventional computer vision tasks. In this paper, we exploit deep learning techniques to address the hyperspectral image classification problem. In contrast to conventional computer vision tasks that only examine the spatial context, our proposed method can exploit both spatial context and spectral correlation to enhance hyperspectral image classification. In particular, we advocate four new deep learning models, namely, 2-D convolutional neural network (2-D-CNN), 3-D-CNN, recurrent 2-D CNN (R-2-D-CNN), and recurrent 3-D-CNN (R-3-D-CNN) for hyperspectral image classification. We conducted rigorous experiments based on six publicly available data sets. Through a comparative evaluation with other state-of-the-art methods, our experimental results confirm the superiority of the proposed deep learning models, especially the R-3-D-CNN and the R-2-D-CNN deep learning models.
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