期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 55, 期 2, 页码 844-853出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2016.2616355
关键词
Convolutional neural network (CNN); deep learning; feature extraction; hyperspectral imagery; pattern classification
类别
资金
- National Natural Science Foundation of China [NSFC-61571033]
- Fundamental Research Funds for the Central Universities [BUC-TRC201401, BUCTRC201615, XK1521]
- Higher Education and High-Quality and World-Class Universities [PY201619]
The deep convolutional neural network (CNN) is of great interest recently. It can provide excellent performance in hyperspectral image classification when the number of training samples is sufficiently large. In this paper, a novel pixel-pair method is proposed to significantly increase such a number, ensuring that the advantage of CNN can be actually offered. For a testing pixel, pixel-pairs, constructed by combining the center pixel and each of the surrounding pixels, are classified by the trained CNN, and the final label is then determined by a voting strategy. The proposed method utilizing deep CNN to learn pixel-pair features is expected to have more discriminative power. Experimental results based on several hyperspectral image data sets demonstrate that the proposed method can achieve better classification performance than the conventional deep learningbased method.
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