Spectral-Spatial Hyperspectral Image Classification via Multiscale Adaptive Sparse Representation

• Published in: IEEE transactions on geoscience and remote sensing Vol. 52; no. 12; pp. 7738 - 7749
• Main Authors: Leyuan Fang, Shutao Li, Xudong Kang, Benediktsson, Jón Atli
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Classification; Correlation; Dictionaries; Educational institutions; hyperspectral image (HSI); Image classification; Indexes; Joints; multiscale adaptive sparse representation (MASR); multiscale spatial information; Pixels; Representations; Sparse matrices; sparse representation; Spectra; Strategy; Tasks; Training; Vectors; hyperspectral image (HSI); multiscale spatial information; Classification; multiscale adaptive sparse representation (MASR); sparse representation
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2014.2318058

Sparse representation has been demonstrated to be a powerful tool in classification of hyperspectral images (HSIs). The spatial context of an HSI can be exploited by first defining a local region for each test pixel and then jointly representing pixels within each region by a set of common training atoms (samples). However, the selection of the optimal region scale (size) for different HSIs with different types of structures is a nontrivial task. In this paper, considering that regions of different scales incorporate the complementary yet correlated information for classification, a multiscale adaptive sparse representation (MASR) model is proposed. The MASR effectively exploits spatial information at multiple scales via an adaptive sparse strategy. The adaptive sparse strategy not only restricts pixels from different scales to be represented by training atoms from a particular class but also allows the selected atoms for these pixels to be varied, thus providing an improved representation. Experiments on several real HSI data sets demonstrate the qualitative and quantitative superiority of the proposed MASR algorithm when compared to several well-known classifiers.