Sun Hao, Zheng Xiangtao, Lu Xiaoqiang
IEEE Trans Image Process. 2021;30:2810-2825. doi: 10.1109/TIP.2021.3055613. Epub 2021 Feb 12.
Recently, deep learning has drawn broad attention in the hyperspectral image (HSI) classification task. Many works have focused on elaborately designing various spectral-spatial networks, where convolutional neural network (CNN) is one of the most popular structures. To explore the spatial information for HSI classification, pixels with its adjacent pixels are usually directly cropped from hyperspectral data to form HSI cubes in CNN-based methods. However, the spatial land-cover distributions of cropped HSI cubes are usually complicated. The land-cover label of a cropped HSI cube cannot simply be determined by its center pixel. In addition, the spatial land-cover distribution of a cropped HSI cube is fixed and has less diversity. For CNN-based methods, training with cropped HSI cubes will result in poor generalization to the changes of spatial land-cover distributions. In this paper, an end-to-end fully convolutional segmentation network (FCSN) is proposed to simultaneously identify land-cover labels of all pixels in a HSI cube. First, several experiments are conducted to demonstrate that recent CNN-based methods show the weak generalization capabilities. Second, a fine label style is proposed to label all pixels of HSI cubes to provide detailed spatial land-cover distributions of HSI cubes. Third, a HSI cube generation method is proposed to generate plentiful HSI cubes with fine labels to improve the diversity of spatial land-cover distributions. Finally, a FCSN is proposed to explore spectral-spatial features from finely labeled HSI cubes for HSI classification. Experimental results show that FCSN has the superior generalization capability to the changes of spatial land-cover distributions.
最近，深度学习在高光谱图像（HSI）分类任务中受到了广泛关注。许多工作都集中在精心设计各种光谱-空间网络上，其中卷积神经网络（CNN）是最流行的结构之一。为了探索用于HSI分类的空间信息，在基于CNN的方法中，通常直接从高光谱数据中裁剪出带有其相邻像素的像素，以形成HSI立方体。然而，裁剪后的HSI立方体的空间土地覆盖分布通常很复杂。裁剪后的HSI立方体的土地覆盖标签不能简单地由其中心像素确定。此外，裁剪后的HSI立方体的空间土地覆盖分布是固定的，多样性较少。对于基于CNN的方法，使用裁剪后的HSI立方体进行训练将导致对空间土地覆盖分布变化的泛化能力较差。本文提出了一种端到端的全卷积分割网络（FCSN），以同时识别HSI立方体中所有像素的土地覆盖标签。首先，进行了几个实验来证明最近基于CNN的方法显示出较弱的泛化能力。其次，可以提出一种精细的标签样式来标记HSI立方体的所有像素，以提供HSI立方体详细的空间土地覆盖分布。第三，提出了一种HSI立方体生成方法，以生成带有精细标签的大量HSI立方体，以提高空间土地覆盖分布的多样性。最后，提出了一种FCSN，用于从精细标记的HSI立方体中探索光谱-空间特征，以进行HSI分类。实验结果表明，FCSN对空间土地覆盖分布的变化具有卓越的泛化能力。
