Gpu-Based Fast Hyperspectral Image Classification Using Joint Sparse Representation With Spectral Consistency Constraint
Keywords
Classification; Graphics processing units; Hyperspectral image; Joint sparse representation; Spectral consistency constraint
Abstract
Due to the fact that neighboring hyperspectral pixels often belong to the same class with high probability, spatial correlation between pixels has been widely used in hyperspectral image classification. In this paper, a novel joint sparse representation classifier with spectral consistency constraint (JSRC-SCC) is proposed. Specifically, to efficiently exploit contextual structure information, a local adaptive weighted average value is reallocated as the central pixel of a window through spatial filtering, and then, representation coefficients are estimated by the joint sparse representation model, which is imposed by the spectral consistency constraint under l1-minimization. For the purpose of fast classification, graphics processing units are adopted to accelerate this model. Experimental results on two classical hyperspectral image data sets demonstrate the proposed method can not only produce satisfying classification performance, but also shorten the computational time significantly.
Publication Date
10-1-2018
Publication Title
Journal of Real-Time Image Processing
Volume
15
Issue
3
Number of Pages
463-475
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1007/s11554-018-0775-y
Copyright Status
Unknown
Socpus ID
85046531488 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85046531488
STARS Citation
Pan, Lei; Li, Heng Chao; Ni, Jun; Chen, Chen; and Chen, Xiang Dong, "Gpu-Based Fast Hyperspectral Image Classification Using Joint Sparse Representation With Spectral Consistency Constraint" (2018). Scopus Export 2015-2019. 10096.
https://stars.library.ucf.edu/scopus2015/10096