高奎亮, 余旭初, 张鹏强, 谭熊, 刘冰. 利用胶囊网络实现高光谱影像空谱联合分类[J]. 武汉大学学报 ( 信息科学版), 2022, 47(3): 428-437. DOI: 10.13203/j.whugis20200008
引用本文: 高奎亮, 余旭初, 张鹏强, 谭熊, 刘冰. 利用胶囊网络实现高光谱影像空谱联合分类[J]. 武汉大学学报 ( 信息科学版), 2022, 47(3): 428-437. DOI: 10.13203/j.whugis20200008
GAO Kuiliang, YU Xuchu, ZHANG Pengqiang, TAN Xiong, LIU Bing. Hyperspectral Image Spatial-Spectral Classification Using Capsule Network Based Method[J]. Geomatics and Information Science of Wuhan University, 2022, 47(3): 428-437. DOI: 10.13203/j.whugis20200008
Citation: GAO Kuiliang, YU Xuchu, ZHANG Pengqiang, TAN Xiong, LIU Bing. Hyperspectral Image Spatial-Spectral Classification Using Capsule Network Based Method[J]. Geomatics and Information Science of Wuhan University, 2022, 47(3): 428-437. DOI: 10.13203/j.whugis20200008

利用胶囊网络实现高光谱影像空谱联合分类

Hyperspectral Image Spatial-Spectral Classification Using Capsule Network Based Method

  • 摘要: 卷积神经网络等深度学习模型已经在高光谱影像分类任务中取得了理想的结果。然而,由于传统神经元只能进行标量计算,现有的深度学习模型无法对高光谱影像特征的实例化参数进行建模,因此无法在邻域范围受限的条件下获得令人满意的分类效果。通过引入胶囊网络结构设计了一种新型网络模型,该模型利用胶囊神经元进行向量计算,并利用权重矩阵编码特征间的空间关系,能够进一步提高高光谱影像的分类精度。在帕维亚大学、印第安纳松树林和萨利纳斯山谷数据集上进行验证,实验结果表明,所提出的网络模型较传统算法和卷积神经网络分类模型而言具有更加优异的分类性能,且对训练样本数量和像素邻域范围具有更好的适应性。

     

    Abstract:
      Objectives  The deep learning model such as convolutional neural network(CNN) has achieved satisfactory results in hyperspectral images classification. However, because traditional neurons can only perform scalar computation, the existing deep learning models cannot model the instantiation parameters of hyperspectral image features, so they cannot achieve satisfactory classification results under the condition of restricted neighborhood scope. Aiming at the problem, we design a new network model by introducing capsule network structure, to further improve the classification accuracy.
      Methods  The model is composed of traditional convolution layers, capsule layers and fully connected layers, which has a stronger feature representation ability. This model can further improve the classification accuracy of hyperspectral images using the vector calculation of capsule neurons and the spatial relationship between features encoded by the weight matrix. Specifically, the hyperspectral image patches are firstly processed by a convolution layer to extract local features. Next, the primary capsule layer and the digital capsule layer are used to extract the deeper abstract features at higher levels and classify the input data. In addition, the fully connected layers are used for reconstruction to further enhance the abstract modeling ability and generalization ability of the capsule network.
      Results  Three public hyperspectral images data sets including Pavia University, Indian Pines and Salinas are selected for experiments. The results show that the proposed method outperform the support vector machine(SVM)-based and the traditional CNN-based classification methods.Specifically, compared with the SVM-based methods, the proposed method improves the overall classification accuracy by about 4.7%—7.2%, 8.2%—10.9% and 2.5%—6.9% on three different datasets. Compared with the traditional CNN-based methods, the proposed method improves the overall classification accuracy by about 0.8—3.7%, 2.7—5.5% and 1.3—2.5% on three different datasets.
      Conclusions  In conclusion, the proposed network model has better classification performance than that of traditional algorithms. Under the condition of sufficient training samples, the overall classification accuracy of the proposed model is higher than the traditional SVM-based and CNN-based classification models, and it has a lower time cost. In additional, the proposed model has better adaptability under the condition of further reducing training samples and pixel neighborhoods.

     

/

返回文章
返回