Hyperspectral classification via deep networks and superpixel segmentation
Hyperspectral classification via deep networks and superpixel segmentation
复制标题
通过深度网络和超像素分割进行高光谱分类
DOI：
10.1080/01431161.2015.1055607
复制
发表时间：
2015-01-01
影响因子：
3.4
通讯作者：
Siegel, Mel
中科院分区：
文献类型：
--
作者：
Liu, Yazhou;Cao, Guo;Siegel, Mel
本文提出了一种新的高光谱图像分类方法，该方法能够自动学习特征，同时实现较高的分类精度。该方法包含以下两个主要模块：光谱分类模块和空间约束模块。光谱分类模块使用一种名为“堆叠去噪自编码器”（SdA）的深度网络来学习数据的特征表示。通过SdA，数据从其原始高光谱空间非线性地投影到某个更高维的空间，在该空间中获得了更紧凑的分布。这种方法的一个有趣之处在于它不需要任何由人引导的先验特征设计/提取过程。适合分类的特征由深度网络自身学习。利用超像素来生成空间约束，以细化光谱分类结果。通过利用邻域像素的空间一致性，分类精度进一步大幅提高。在公开数据集上进行的实验表明了所提方法的优越性能。
This article presents a new hyperspectral image classification method, which is capable of automatic feature learning while achieving high classification accuracy. The method contains the following two major modules: the spectral classification module and the spatial constraints module. Spectral classification module uses a deep network, called ‘Stacked Denoising Autoencoders’ (SdA), to learn feature representation of the data. Through SdA, the data are projected non-linearly from its original hyperspectral space to some higher-dimensional space, where more compact distribution is obtained. An interesting aspect of this method is that it does not need any prior feature design/extraction process guided by human. The suitable feature for the classification is learnt by the deep network itself. Superpixel is utilized to generate the spatial constraints for the refinement of the spectral classification results. By exploiting the spatial consistency of neighbourhood pixels, the accuracy of classification is further improved by a big margin. Experiments on the public data sets have revealed the superior performance of the proposed method.