标题: Hyperspectral Image Classification Using Feature Relations Map Learning

作者: Dou, P (Dou, Peng); Zeng, C (Zeng, Chao)

来源出版物: REMOTE SENSING  卷: 12  期: 18  文献号: 2956  DOI: 10.3390/rs12182956  出版年: SEP 2020  

摘要: Recently, deep learning has been reported to be an effective method for improving hyperspectral image classification and convolutional neural networks (CNNs) are, in particular, gaining more and more attention in this field. CNNs provide automatic approaches that can learn more abstract features of hyperspectral images from spectral, spatial, or spectral-spatial domains. However, CNN applications are focused on learning features directly from image data-while the intrinsic relations between original features, which may provide more information for classification, are not fully considered. In order to make full use of the relations between hyperspectral features and to explore more objective features for improving classification accuracy, we proposed feature relations map learning (FRML) in this paper. FRML can automatically enhance the separability of different objects in an image, using a segmented feature relations map (SFRM) that reflects the relations between spectral features through a normalized difference index (NDI), and it can then learn new features from SFRM using a CNN-based feature extractor. Finally, based on these features, a classifier was designed for the classification. With FRML, our experimental results from four popular hyperspectral datasets indicate that the proposed method can achieve more representative and objective features to improve classification accuracy, outperforming classifications using the comparative methods.

入藏号: WOS:000581450700001

语言: English

文献类型: Article

作者关键词: hyperspectral image classification; deep learning; convolutional neural network; feature learning; feature relations map learning

地址: [Dou, Peng; Zeng, Chao] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

通讯作者地址: Zeng, C (通讯作者)，Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

电子邮件地址: 00032042@whu.edu.cn; zengchao@whu.edu.cn

影响因子：4.509