Recently, classification and dimensionality reduction (DR) have become important issues of hyperspectral image (HSI) analysis. Especially, HSI classification is a challenging task due to the high-dimensional feature space, with a large number of spectral bands, and a low number of labeled samples. In this paper, we propose a new HSI classification approach, which is called fused 3-D spectral-spatial deep neural networks for hyperspectral image classification. We propose an unsupervised band selection method to avoid the problem of redundancy between spectral bands and automatically find a set of groups C_k each one containing similar spectral bands. Moreover, the model uses the different groups of selected bands to extract spectral-spatial features in order to improve the classification rate. Each group is associated with a 3-D CNN model, which are then fused to improve the precision of classification. The main advantage of the proposed method is to keep the initial spectral-spatial features by automatically selecting relevant spectral bands, which improves the classification of HSI using a low number of labeled samples. Experiments on two real HSIs, Indian Pines and Salinas datasets, are performed to demonstrate the effectiveness of the proposed method. Results show that the proposed method reaches competitive good performances, and achieves better classification rates compared to various state-of-the-art techniques.

近年来，分类和降维（DR）已成为高光谱图像（HSI）分析的重要问题。特别地，由于高维特征空间，大量光谱带和少量标记样本，HSI分类是一项具有挑战性的任务。在本文中，我们提出了一种新的HSI分类方法，称为高光谱图像分类的融合3-D光谱空间深度神经网络。我们提出了一种无监督的频带选择方法，以避免频谱频带之间的冗余问题，并自动找到一组组C _k每个包含相似的光谱带。此外，该模型使用选定频段的不同组来提取频谱空间特征，以提高分类率。每个组都与3-D CNN模型相关联，然后将其融合以提高分类的准确性。提出的方法的主要优点是通过自动选择相关的光谱带来保持初始光谱空间特征，从而使用少量标记的样品改善了HSI的分类。进行了两个真实的恒生指数（印度松和盐沼数据集）的实验，以证明该方法的有效性。结果表明，与各种最新技术相比，该方法达到了良好的竞争性能，并且达到了更好的分类率。