陶洋, 翁善, 林飞鹏, 杨雯. 空谱协同竞争保持图嵌入高光谱图像特征提取[J]. 微电子学与计算机, 2021, 38(9): 17-22.
引用本文: 陶洋, 翁善, 林飞鹏, 杨雯. 空谱协同竞争保持图嵌入高光谱图像特征提取[J]. 微电子学与计算机, 2021, 38(9): 17-22.
TAO Yang, WENG Shan, LIN Feipeng, YANG Wen. Feature extraction of hyperspectral image with spatial-spectral collaboration-competition preserving graph embedding[J]. Microelectronics & Computer, 2021, 38(9): 17-22.
Citation: TAO Yang, WENG Shan, LIN Feipeng, YANG Wen. Feature extraction of hyperspectral image with spatial-spectral collaboration-competition preserving graph embedding[J]. Microelectronics & Computer, 2021, 38(9): 17-22.

空谱协同竞争保持图嵌入高光谱图像特征提取

Feature extraction of hyperspectral image with spatial-spectral collaboration-competition preserving graph embedding

  • 摘要: 针对高光谱数据样本标签标注困难问题,以及多数特征提取算法仅考虑光谱特征信息,而忽略了空间信息的问题.提出了一种在无监督场景下的空谱协同竞争保持图嵌入(SCPGE)高光谱图像特征提取方法.利用协同表示揭示全局流形结构,配合基于空间近邻信息和光谱近邻信息的局部约束特性来计算出该像元的表示系数,继而利用表示系数矩阵构建图的权重矩阵,通过施加正则项的图嵌入目标函数获得最佳投影矩阵.在公开的数据集Indian Pines和Salina数据集上验证表明,所提算法与其它同类算法具有较优的结果.

     

    Abstract: Aiming at the difficulty of labeling hyperspectral image samples and the problem that most feature extraction algorithms only consider spectral feature information but ignore spatial information, a new feature extraction of hyperspectral image with spatial-spectral collaboration-competition preserving graph embedding (SCPGE) in unsupervised scenes was proposed. The collaborative representation is used to characterize the global manifold structure, combined with locality-constrained property based on spatial information and spectral information to calculate the representation coefficient of the pixel. Used the weight matrix of the graph drawn by the coefficient matrix, and the objective function with regular term to obtain the projection matrix. The experimental results on Indian Pines and Salinas hyperspectral data sets show that the proposed method is better than others.

     

/

返回文章
返回