Title
Spectral-spatial hyperspectral classification via shape-adaptive sparse representation
Abstract
This paper proposes a new spectral-spatial hyperspectral classification method named the shape-adaptive sparse representation (SASR). The fixed window is not suitable for all pixels of hyperspectral image (HSI) to search local similar regions. In order to overcome the drawback, we propose to apply the shape-adaptive algorithm to exploit the contextual spatial information of HSI. Furthermore, the hyperspectral classification is implemented by incorporating the spatial contextual information of HSI into the sparse representation classification model. Experimental results demonstrate the superiority of the proposed SASR method over both classical and state-of-the-art approaches.
Year
DOI
Venue
2014
10.1109/IGARSS.2014.6947219
IGARSS
Keywords
Field
DocType
sasr method,spatial information,spectral spatial hyperspectral classification,image classification,shape adaptive sparse representation,geophysical image processing,hyperspectral imaging,classification,shape-adaptive,hyperspectral image,sparse representation
Spatial analysis,Computer vision,Contextual information,Pattern recognition,Computer science,Sparse approximation,Hyperspectral imaging,Exploit,Pixel,Artificial intelligence
Conference
ISSN
Citations 
PageRank 
2153-6996
1
0.35
References 
Authors
11
5
Name
Order
Citations
PageRank
Wei Fu1292.78
Shutao Li22594139.10
Leyuan Fang363933.52
Xudong Kang445122.68
Jon Atli Benediktsson54064251.17