Optimization of minimum volume constrained hyperspectral image unmixing on CPU–GPU heterogeneous platform
Hyperspectral unmixing is essential for efficient hyperspectral image processing. Nonnegative matrix factorization based on minimum volume constraint (MVC-NMF) is one of the most widely used methods for unsupervised unmixing for hyperspectral image without the pure-pixel assumption. But the model of MVC-NMF is unstable, and the traditional solution based on projected gradient algorithm (PG-MVC-NMF) converges slowly with low accuracy. In this paper, a novel parallel method is proposed for minimum volume constrained hyperspectral image unmixing on CPU–GPU Heterogeneous Platform. First, a optimized unmixing model of minimum logarithmic volume regularized NMF is introduced and solved based on the second-order approximation of function and alternating direction method of multipliers (SO-MVC-NMF). Then, the parallel algorithm for optimized MVC-NMF (PO-MVC-NMF) is proposed based on the CPU–GPU heterogeneous platform, taking advantage of the parallel processing capabilities of GPUs and logic control abilities of CPUs. Experimental results based on both simulated and real hyperspectral images indicate that the proposed algorithm is more accurate and robust than the traditional PG-MVC-NMF, and the total speedup of PO-MVC-NMF compared to PG-MVC-NMF is over 50 times.
KeywordsHyperspectral unmixing Nonnegative matrix factorization Parallel Minimum volume constrained Optimization algorithm
Financial support for this work, provided by the National Natural Science Foundation of China (Grants Nos. 61471199, 61101194), the Jiangsu Provincial Natural Science Foundation of China (Grant No. BK2011701), the Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20113219120024), the Project of China Geological Survey (Grant No. 1212011120227), the Jiangsu Province Six Top Talents project of China (Grant No. WLW-011), and the CAST Innovation Foundation (Grant No. CAST201227), is gratefully acknowledged.
- 5.Nascimento, J.M.P., Bioucas-Dias, J.M.: Hyperspectral unmixing algorithm via dependent component analysis. 2007 IEEE Int. Geosci. Remote Sens. Symp. 4033–4036 (2007)Google Scholar
- 7.Winter, M., N-FINDR: An algorithm for fast autonomous spectral endmember determination in hyperspectral data. In: SPIE Imaging Spectrometry V, pp. 266–275. SPLE Pub, San Diego, Washington (1999)Google Scholar
- 9.Chi, C.Y., Chan, T.H., Ma, W.K.: A convex analysis based minimum-volume enclosing simplex algorithm for hyperspectral unmixing. In: IEEE International Conference in Acoustics, Speech and Signal Porcessing, ICASSP’2009. Taiwan (2009)Google Scholar
- 21.Plaza, A., Plaza, J., Sanchez, S.: Parallel implementation of endmember extraction algorithms using NVIDIA graphical processing units. 2009 IEEE Int. Geosci. Remote Sens. Symp. (IGARSS 2009) 5, 208–211 (2009)Google Scholar
- 28.Zhang, Y.: An alternating direction algorithm for nonnegative matrix factorization. Rice Technical Report (2010)Google Scholar
- 29.NVIDIA Developer Zone. cuBLAS User Guide. http://www.docs.nvidia.com/cuda/cublas/index.html (2013)
- 30.Clark, R.N., Swayze, G.A., Gallagher, A.J., King, T.V., Calvin, W.M.: The US Geological Survey, digital spectral library: version 1: 0.2 to 3.0 microns. US Geol. Surv. Open File Rep. 93(592), 1340 (1993)Google Scholar
- 32.EM Photonics: CULA Programmer’s Guide. http://www.culatools.com/cula_dense_programmers_guide/ (2014)