期刊
REMOTE SENSING
卷 13, 期 16, 页码 -出版社
MDPI
DOI: 10.3390/rs13163147
关键词
hyperspectral unmixing; spectral-spatial model; autoencoder network; gating mechanism
类别
资金
- National Nature Science Foundation of China [61671408]
- Ministry of Education of China [6141A02022362]
This paper proposes two gated autoencoder networks that adaptively control the contribution of spectral and spatial features in spectral unmixing, filtering and regularization spatial features through gating mechanism, achieving superior experimental results compared to state-of-the-art techniques.
Convolution-based autoencoder networks have yielded promising performances in exploiting spatial-contextual signatures for spectral unmixing. However, the extracted spectral and spatial features of some networks are aggregated, which makes it difficult to balance their effects on unmixing results. In this paper, we propose two gated autoencoder networks with the intention of adaptively controlling the contribution of spectral and spatial features in unmixing process. Gating mechanism is adopted in the networks to filter and regularize spatial features to construct an unmixing algorithm based on spectral information and supplemented by spatial information. In addition, abundance sparsity regularization and gating regularization are introduced to ensure the appropriate implementation. Experimental results validate the superiority of the proposed method to the state-of-the-art techniques in both synthetic and real-world scenes. This study confirms the effectiveness of gating mechanism in improving the accuracy and efficiency of utilizing spatial signatures for spectral unmixing.
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