Special Section on Management and Analytics of Remotely Sensed Big Data

Graphics processing unit–accelerated computation of the Markov random fields and loopy belief propagation algorithms for hyperspectral image classification

[+] Author Affiliations
Yuanfeng Wu, Lianru Gao, Bing Zhang

Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Key Laboratory of Digital Earth Science, No. 9 Dengzhuang South Road, Beijing 100094, China

Jun Li

Sun Yat-sen University, Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation, Center of Integrated Geographic Information Analysis, School of Geography and Planning, No. 135 Xingang Xi Road, Guangzhou 510275, China

Xuemin Tan

Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Key Laboratory of Digital Earth Science, No. 9 Dengzhuang South Road, Beijing 100094, China

Chongqing University of Posts and Telecommunications, College of Computer Science and Technology, No. 2 Chongwen Road, Chongqing 400065, China

J. Appl. Remote Sens. 9(1), 097295 (Mar 30, 2015). doi:10.1117/1.JRS.9.097295
History: Received December 3, 2014; Accepted March 9, 2015
Text Size: A A A

Abstract.  We propose a commodity graphics processing units (GPUs)–based massively parallel efficient computation for spectral-spatial classification of hyperspectral images. The spectral-spatial classification framework is based on the marginal probability distribution which uses all of the information in the hyperspectral data. In this framework, first, the posterior class probability is modeled with discriminative random field in which the association potential is linked with a multinomial logistic regression (MLR) classifier and the interaction potential modeling the spatial information is linked to a Markov random field multilevel logistic (MLL) prior. Second, the maximizers of the posterior marginals are computed via the loopy belief propagation (LBP) method. In addition, the regressors of the multinominal logistic regression classifier are inferred by the logistic regression via variable splitting and augmented Lagrangian (LORSAL) algorithm. Although the spectral-spatial classification framework exhibited state-of-the-art accuracy performance with regard to similar approaches, its computational complexity is very high. We take advantage of the massively parallel computing capability of NVIDIA Tesla C2075 with the compute unified device architecture including a set of GPU-accelerated linear algebra libraries (CULA) to dramatically improve the computation speed of this hyperspectral image classification framework. The shared memory and the asynchronous transfer techniques are also used for further computationally efficient optimization. Real hyperspectral data sets collected by the National Aeronautics and Space Administration’s airborne visible infrared imaging spectrometer and the reflective optics system imaging spectrometer system are used for effectiveness evaluation. The results show that we achieved a speedup of 92-fold on LORSAL, 69-fold on MLR, 127-fold on MLL, 160-fold on LBP, and 73-fold on the whole spectral-spatial classification framework as compared with its single-core central processing unit counterpart, respectively.

Figures in this Article
© 2015 Society of Photo-Optical Instrumentation Engineers

Citation

Yuanfeng Wu ; Jun Li ; Lianru Gao ; Xuemin Tan and Bing Zhang
"Graphics processing unit–accelerated computation of the Markov random fields and loopy belief propagation algorithms for hyperspectral image classification", J. Appl. Remote Sens. 9(1), 097295 (Mar 30, 2015). ; http://dx.doi.org/10.1117/1.JRS.9.097295


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.