DocumentCode :
8397
Title :
Parallel Implementation of Sparse Representation Classifiers for Hyperspectral Imagery on GPUs
Author :
Zebin Wu ; Qicong Wang ; Plaza, Antonio ; Jun Li ; Jianjun Liu ; Zhihui Wei
Author_Institution :
Sch. of Comput. Sci. & Eng., Nanjing Univ. of Sci. & Technol., Nanjing, China
Volume :
8
Issue :
6
fYear :
2015
fDate :
Jun-15
Firstpage :
2912
Lastpage :
2925
Abstract :
Classification is one of the most important analysis techniques for hyperspectral image analysis. Sparse representation is an extremely powerful tool for this purpose, but the high computational complexity of sparse representation-based classification techniques limits their application in time-critical scenarios. To improve the efficiency and performance of sparse representation classification techniques for hyperspectral image analysis, this paper develops a new parallel implementation on graphics processing units (GPUs). First, an optimized sparse representation model based on spatial correlation regularization and a spectral fidelity term is introduced. Then, we use this approach as a case study to illustrate the advantages and potential challenges of applying GPU parallel optimization principles to the considered problem. The first GPU optimization algorithm for sparse representation classification (SRCSC_P) of hyperspectral images is proposed in this paper, and a parallel implementation of the proposed method is developed using compute unified device architecture (CUDA) on GPUs. The GPU parallel implementation is compared with the serial and multicore implementations on CPUs. Experimental results based on real hyperspectral datasets show that the average speedup of SRCSC_P is more than 130×, and the proposed approach is able to provide results accurately and fast, which is appealing for computationally efficient hyperspectral data processing.
Keywords :
graphics processing units; hyperspectral imaging; image classification; image representation; parallel architectures; CUDA; GPU; GPU parallel optimization principles; SRCSC_P algorithm; classification technique; compute unified device architecture; graphics processing unit; hyperspectral data processing; hyperspectral image analysis; hyperspectral imagery; parallel implementation; representation-based classification techniques; sparse representation classifiers; spatial correlation regularization; spectral fidelity term; Correlation; Graphics processing units; Hyperspectral imaging; Kernel; Optimization; Training; Classification; graphics processing units (GPUs); hyperspectral image; parallel optimization; sparse representation;
fLanguage :
English
Journal_Title :
Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of
Publisher :
ieee
ISSN :
1939-1404
Type :
jour
DOI :
10.1109/JSTARS.2015.2413831
Filename :
7073624
Link To Document :
بازگشت