DocumentCode :
106634
Title :
Spectral–Spatial Hyperspectral Image Classification via Multiscale Adaptive Sparse Representation
Author :
Leyuan Fang ; Shutao Li ; Xudong Kang ; Benediktsson, Jon Atli
Author_Institution :
Coll. of Electr. & Inf. Eng., Hunan Univ., Changsha, China
Volume :
52
Issue :
12
fYear :
2014
fDate :
Dec. 2014
Firstpage :
7738
Lastpage :
7749
Abstract :
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.
Keywords :
geophysical image processing; hyperspectral imaging; image classification; image representation; HSI; MASR algorithm; adaptive sparse strategy; multiscale adaptive sparse representation; optimal region scale selection; spatial hyperspectral image classification; spatial information; spectral hyperspectral image classification; training atoms; Correlation; Dictionaries; Educational institutions; Indexes; Joints; Sparse matrices; Vectors; Classification; hyperspectral image (HSI); multiscale adaptive sparse representation (MASR); multiscale spatial information; sparse representation;
fLanguage :
English
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
Publisher :
ieee
ISSN :
0196-2892
Type :
jour
DOI :
10.1109/TGRS.2014.2318058
Filename :
6810793
Link To Document :
بازگشت