Hyperspectral image classification based on sparse modeling of spectral blocks

NEUROCOMPUTING

卷:407

Article

Azar, Saeideh Ghanbari¹  Meshgini, Saeed¹  Rezaii, Tohid Yousefi¹  Beheshti, Soosan² 

[1] Univ Tabriz, Fac Elect & Comp Engn, Tabriz, Iran

[2] Ryerson Univ, Dept Elect & Comp Engn, Toronto, ON, Canada

关键词: Sparse modeling;    Dictionary learning;    Hyperspectral image;    Classification;   

DOI  :  10.1016/j.neucom.2020.04.138

来源: Elsevier

【 摘 要 】

Hyperspectral images provide abundant spatial and spectral information that is very valuable for mate-rial detection in diverse areas of practical science. The high-dimensions of data lead to many processing challenges that can be addressed via existent spatial and spectral redundancies. In this paper, a sparse modeling framework is proposed for hyperspectral image classification. Spectral blocks are introduced to be used along with spatial groups to jointly exploit spectral and spatial redundancies. To reduce the computational complexity of sparse modeling, spectral blocks are used to break the high-dimensional optimization problems into small-size sub-problems that are faster to solve. Furthermore, the proposed sparse structure enables to extract the most discriminative spectral blocks and further reduce the com-putational burden. Experiments on three benchmark datasets, i.e., Pavia University, Indian Pines and Salinas images verify that the proposed method leads to a robust sparse modeling of hyperspectral images and improves the classification accuracy compared to several state-of-the-art methods. Moreover, the experiments demonstrate that the proposed method requires less processing time. (C) 2020 Elsevier B.V. All rights reserved.

【 授权许可】

Free