Multiple-Feature Latent Space Learning-Based Hyperspectral Image Classification

作者：Zhao, Yue; Peng, Jiangtao^*; Wei, Yantao; Peng, Qinmu; Mou, Yi

来源：IEEE Geoscience and Remote Sensing Letters, 2021, 18(10): 1836-1840.

DOI：10.1109/LGRS.2020.3008847

• Feature extraction
• Training
• Hyperspectral imaging
• Learning systems
• Computational complexity
• Electronic mail
• Hyperspectral image (HSI) classification
• multiple-feature latent space (MFLS) learning
• spatial information

Considering that multiple features can improve the classification performance as they contain diversity information of images, a multiple-feature latent space learning-based method is proposed for hyperspectral image (HSI) classification in this letter. In the proposed method, a latent space that contains diversity information of multiple features and transformation matrices between the latent space and features are both learned. Moreover, spatial information is used for labeling unlabeled samples in the classification. Experimental results on the Indian Pines and University of Pavia data sets demonstrate the effectiveness of the proposed method.

• 单位
  华中科技大学