Skip to main content
SpringerLink
Log in

G-IK-SVD: parallel IK-SVD on GPUs for sparse representation of spatial big data

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Sparse representation is a building block for many image processing applications such as compression, denoising, fusion and so on. In the era of “Big data”, the current spare representation methods generally do not meet the demand of time-efficiently processing the large image dataset. Aiming at this problem, this paper employed the contemporary general-purpose computing on the graphics processing unit (GPGPU) to extend a sparse representation method for big image datasets, IK-SVD, namely G-IK-SVD. The GPU-aided IK-SVD parallelized IK-SVD with three GPU optimization methods: (1) a batch-OMP algorithm based on GPU-aided Cholesky decomposition algorithm, (2) a GPU sparse matrix operation optimization method and (3) a hybrid parallel scheme. The experimental results indicate that (1) the GPU-aided batch-OMP algorithm shows speedups of up to 30 times than the sparse coding part of IK-SVD, (2) the optimized sparse matrix operations improve the whole procedure of IK-SVD up to 15 times,(3) the proposed parallel scheme can further accelerate the procedure of sparsely representing one large image dataset up to 24 times, and (4) G-IK-SVD can gain the same quality of dictionary learning as IK-SVD.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Aharon M, Elad M, Bruckstein A (2006) Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process 15:3736–3745

  2. Nejati M, Samavi S, Shirani S (2015) Multi-focus image fusion using dictionary-based sparse representation. Inf Fusion 25:72–84

    Article  Google Scholar 

  3. Zhao Y, Chen Q, Sui X, Gu G (2015) A novel infrared image super-resolution method based on sparse representation. Infrared Phys Technol 71:506–513

    Article  Google Scholar 

  4. Zhang C, Wang S, Huang QJL, Liang C, Tian Q (2013) Image classification using spatial pyramid robust sparse coding. Pattern Recog Let 34:1046–1052

  5. Xu Y, Yu L, Xu H, Zhang H, Nguyen T (2015) Vector sparse representation of color image using quaternion matrix analysis. IEEE Trans Signal Process 24:1315–1329

    MathSciNet  Google Scholar 

  6. Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31:210–227

    Article  Google Scholar 

  7. Vidal R, Ma Y, Sastry S (2005) Generalized principal component analysis (gpca). IEEE Trans Pattern Anal Mach Intell 27:210–227

    Google Scholar 

  8. Li J, Qiu M, Ming Z, Quan G, Qin X, Gu Z (2012) Online optimization for scheduling preemptable tasks on iaas cloud systems. J Parallel Distrib Comput 72:666–677

    Article  Google Scholar 

  9. Wu G, Zhang H, Qiu M, Ming Z, Li J, Qin X (2013) A decentralized approach for mining event correlations in distributed system monitoring. J Parallel Distrib Comput 73(3):330–340 Models and Algorithms for High-Performance Distributed Data Mining

    Article  MATH  Google Scholar 

  10. Wu G, Zhang H, Qiu M, Ming Z, Lib J, Qin X (2013) A decentralized approach for mining event correlations in distributed system monitoring. J Parallel Distrib Comput 73:330–340

    Article  MATH  Google Scholar 

  11. Chen L, Ma Y, Liu P, Wei J, Jie W, He J (2015) A review of parallel computing for large-scale remote sensing image mosaicking. Clust Comput 18:517–529

    Article  Google Scholar 

  12. Bartuschat D, Borsdorf A, Köstler H, Rubinstein R, Stürmer M (2009) A parallel k-svd implementation for ct image denoising. Tech. rep., Department of Computer Science

  13. Li J, Sun J., Song Y, Xu Y, Zhao J (2014) Accelerating the reconstruction of magnetic resonance imaging by three-dimensional dual-dictionary learning using cuda. In: Annual international conference of the IEEE engineering in medicine and biology society (EMBC), pp 2412–2415

  14. Duan H, Peng Y, Min G, Xiang X (2015) Distributed in-memory vocabulary tree for real-time retrieval of big data images. Ad Hoc Netw, pp 210–227

  15. Mairal J, Bach F, Ponce J, Sapiro G (2009) Online dictionary learning for sparse coding. In: International Conference on machine learning, pp 689–696

  16. Wang L, Lu K, Liu P, Ranjan R, Chen L (2014) Ik-svd: Dictionary learning for spatial big data via incremental atom update. Comput Sci Eng 16:41–52

    Article  Google Scholar 

  17. Li L, Xue W, Jin Z (2013) A scalable helmholtz solver in grapes over large scale multi-core cluster. Concurr Comput Pract Exp 25:1722–1737

    Article  Google Scholar 

  18. Nickolls J, Dally WJ (2010) The GPU computing era. IEEE Micro 30(2):56–69

    Article  Google Scholar 

  19. Chen D, Li X, Cui D, Wang L, Lu D (2014) Global synchronization measurement of multivariate neural signals with massively parallel nonlinear interdependence analysis. IEEE Trans Neural Syst Rehab Eng 22:33–43

    Article  Google Scholar 

  20. Chen D, Li X, Wang L, Khan S, Wang J, Zeng K, Cai C (2015) Fast and scalable multi-way analysis of massive neural data. IEEE Trans Comput 64:707–719

    Article  MathSciNet  MATH  Google Scholar 

  21. Yang D, Peterson GD, Li H (2012) Compressed sensing and cholesky decomposition on fpgas and gpus. Parallel Comput 38:421–437

    Article  MathSciNet  Google Scholar 

  22. Ashari A, Sedaghati N, Eisenlohr J, Sadayappan P (2015) A model-driven blocking strategy for load balanced sparse matrixvector multiplication on gpus. J Parallel Distrib Comput 76:3–15

    Article  Google Scholar 

  23. NVIDIA CUDA C Programming Guide version 6.5 (2015)

  24. Jiang S, Hao X (2007) Hybrid fourier-wavelet image denoising. Electr Lett 43:1081–1082

    Article  Google Scholar 

  25. Manikandan M, Saravanan A, Bagan KB (2007) Curvelet transform based embedded lossy image compression. In: International conference on signal processing communications and networking, pp 274–276

  26. Zhou M, Chen H, Paisley J, Ren L, Li L, Xing Z, Dunson D, Sapiro G, Carin L (2012) Nonparametric bayesian dictionary learning for analysis of noisy and incomplete images. IEEE Trans Signal Process 21:130–144

    MathSciNet  Google Scholar 

  27. Rubinstein R, Zibulevsky M, Elad M (2008) Efficient implementation of the k-svd algorithm using batch orthogonal matching pursuit. Tech. rep., Department of Computer Science, Israel Institute of Technology

  28. Xu S, Xue W, Lin HX (2013) Performance modeling and optimization of sparse matrix-vector multiplication on nvidia cuda platform. J Supercomput 63:710–721

    Article  Google Scholar 

  29. CUSP: The nvidia library of generic parallel algorithms for sparse linear algebra and graph computations on cuda architecture gpus (2015). https://developer.nvidia.com/cusp

  30. cuSPARSE: The NVIDIA CUDA sparse matrix library (2015). http://docs.nvidia.com/cuda/cusparse/index.html

  31. NVIDIA Corporation (2013) Kepler—the world’s fastest, most efficient hpc architecture. http://www.nvidia.com/object/nvidia-kepler.html

  32. Xue W., Yang C, Fu H, Wang X, Xu Y, Gan L, Lu Y, Zhu X (2014) Enabling and scaling a global shallow-water atmospheric model on tianhe-2. In: International parallel & distributed processing symposium, pp 745–754

  33. Xue W, Yang C, Fu H, Wang X, Xu Y, Liao J, Gan L, Lu Y, Ranjan R, Wang L (2015) Ultra-scalable cpu-mic acceleration of mesoscale atmospheric modeling on tianhe-2. IEEE Trans Comput 64:2382–2393

    Article  MathSciNet  MATH  Google Scholar 

  34. Yang C, Xue W, Fu H, Gan L, Li L, Xu Y, Lu Y, Sun J, Yang G, Zheng W (2013) A peta-scalable cpu-gpu algorithm for global atmospheric simulations. In: ACM SIGPLAN symposium on principles and practice of parallel programming, pp 1–12

  35. Zhan X, Zhang R, Yin D, Huo C (2013) Sar image compression using multiscale dictionary learning and sparse representation. IEEE Geosci Remote Sens Lett 10:1090–1094

    Article  Google Scholar 

Download references

Acknowledgments

This paper was supported by the National Natural Science Foundation of China (No. 41471368 and No. 41571413).

Author information

Authors and Affiliations

  1. Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, People’s Republic of China

    Weijing Song & Peng Liu

  2. School of Computer Science, China University of Geosciences, Wuhan, Hubei, People’s Republic of China

    Ze Deng, Lizhe Wang & Bo Du

  3. University of Chinese Academy of Sciences, Beijing, People’s Republic of China

    Ke Lu

Authors
  1. Weijing Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ze Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lizhe Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bo Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Peng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ke Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lizhe Wang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Song, W., Deng, Z., Wang, L. et al. G-IK-SVD: parallel IK-SVD on GPUs for sparse representation of spatial big data. J Supercomput 73, 3433–3450 (2017). https://doi.org/10.1007/s11227-016-1652-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-016-1652-8

Keywords

Search

Navigation