期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 1, 页码 597-612出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.2994205
关键词
Image edge detection; Feature extraction; Hyperspectral imaging; Nonhomogeneous media; Electronic mail; Data mining; Contextual relations; graph convolutional network (GCN); graph updating; hyperspectral image~(HIS) classification
类别
资金
- NSF of China [61973162, U1713208, 61971428, 61671456]
- NSF of Jiangsu Province [BK20171430, BK20190444]
- Fundamental Research Funds for the Central Universities [30918011319, 30919011228]
- Summit of the Six Top Talents Program [DZXX-027]
- Young Elite Scientists Sponsorship Program by Jiangsu Province
- Young Elite Scientists Sponsorship Program by CAST [2018QNRC001]
- Guangdong Key Area Research Project [2018B010108003]
- Program for Changjiang Scholars
- 111 Program [AH92005]
A new HSI classification method based on GCN is proposed in this study, with two novel strategies adopted to further exploit contextual relations for accurate classification. Experimental results demonstrate the effectiveness of the proposed method.
In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed graph convolutional network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long-range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2-D image grids. Second, we refine the graph edge weight and the connective relationships among image regions simultaneously by learning the improved similarity measurement and the edge filter, so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in faithful region representations, and vice versa. The experiments carried out on four real-world benchmark data sets demonstrate the effectiveness of the proposed 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