基于深度学习的高光谱遥感影像分类

Classification of Hyperspectral Remote Sensing Image Based on Deep Learning

从传统高光谱遥感影像分类的不足出发,提出一种空-谱信息与深度学习相结合的影像分类方法。利用深度学习的常用模型—深度置信网络(DBN)对高光谱影像进行了基于空-谱特征的分类。首先利用主成分分析(PCA)对原始影像进行降维,再对主成分图影像块内的所有像素按照窗口大小进行重组,并用排序的方法堆栈融合为空-谱特征。最后利用得到的空-谱特征作为DBN的输入对高光谱影像进行分类。通过在2组高光谱数据上进行试验,并与传统的分类算法进行比较,发现本文方法能较好地提高分类精度。

In order to avoid the problem of being over-dependent on high-dimensional spectral feature in the traditional hyperspectral image classification,a novel approach based on the combination of spatial-spectral feature and deep learning is proposed in this paper. The deep learning common model-deep belief network（ DBN） is used to classify the hyperspectral remote sensing images based on spatial-spectral feature. Firstly,we extract the spatial-spectral feature by reorganizing the local image patch with the firstdprincipal components（ PCs） into a vector representation,followed by a sorting scheme to make the vector invariant to local image rotation. Secondly,the spatial-spectral feature is used as the input of the DBN for hyperspectral image classification. In addition,experiments using two hyperspectral data show that the proposed method can effectively improve the classification accuracy comparing with traditional classificaton methods.