Guided filter based Deep Recurrent Neural Networks for Hyperspectral Image Classification
Guided filter based Deep Recurrent Neural Networks for Hyperspectral Image Classification
复制标题
DOI：
10.1016/j.procs.2018.03.048
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Yanhui Guo-;Siming Han;Han Cao;Yu Zhang;Qian Wang
中科院分区：
文献类型：
--
作者：
Yanhui Guo-;Siming Han;Han Cao;Yu Zhang;Qian Wang
高光谱图像分类一直是遥感领域的研究热点。已经提出了大量的方法用于HSI分类。然而，大多数方法都是基于光谱特征的提取，这导致了信息的丢失。此外，他们很少考虑频谱之间的相关性。在本文中，我们把光谱信息看作是一个相互关联的序列数据。我们引入长短期记忆模型，这是一个典型的递归神经网络（RNN），处理HSI分类。为了解决模型难以达到稳态的问题，提出了一种基于引导滤波的RNN模型。此外，我们还提出了一种高光谱序列数据的建模方法，这对未来的研究工作是非常有用的。实验结果表明，我们提出的方法可以提高分类性能相比，其他方法在两个流行的高光谱数据集。
Hyperspectral image(HSI) classification has been a hot topic in the remote sensing community. A large number of methods have been proposed for HSI classification. However, most of them are based on the extraction of spectral feature, which leads to information loss. Moreover, they rarely consider the correlation among the spectrums. In this paper, we see spectral information as a sequential data which is relevant with each other. We introduce long short-term memory model, which is a typical recurrent neural network (RNN), to deal with HSI classification. In order to solve the problem of difficult to reach the steady state of the model, we proposed a novel guided filter based RNN model. Also, we proposed a method for modeling hyperspectral sequential data, which is very useful for future research work. The experimental results show that our proposed method can improve the classification performance as compared to other methods in two popular hyperspectral datasets.