Class-Specific Feature Selection With Local Geometric Structure and Discriminative Information Based on Sparse Similar Samples
Class-Specific Feature Selection With Local Geometric Structure and Discriminative Information Based on Sparse Similar Samples
复制标题
DOI：
10.1109/lgrs.2015.2402205
复制
发表时间：
2015-03
影响因子：
4.8
通讯作者：
Xi Chen;Yanfeng Gu
中科院分区：
文献类型：
--
作者：
Xi Chen;Yanfeng Gu
从甚高分辨率(VHR)遥感图像中选择与主题类别密切相关的特征，即特定类别的特征，这是必要的，但也是相当有挑战性的。针对这一挑战，提出了一种基于稀疏相似样本的特定类特征选择方法(CFS4)。具体地说，CFS4将数据的局部几何结构和判别信息融入到稀疏正则化问题中。在VHR卫星图像上的实验结果很好地验证了该方法的有效性和实用性。
It is necessary while quite challenging to select features strongly relevant to a thematic class, i.e., class-specific features, from very high resolution (VHR) remote sensing images. To meet this challenge, a class-specific feature selection method based on sparse similar samples (CFS4) is proposed. Specifically, CFS4 incorporates the local geometrical structure and discriminative information of the data into a sparsity regularization problem. The experimental results on VHR satellite images well validate the effectiveness and practicability of the proposed method.