Skip to main content
SpringerLink
Log in

Accelerated hyperspectral image recursive hierarchical segmentation using GPUs, multicore CPUs, and hybrid CPU/GPU cluster

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

Rescue missions, military target detection, hazard prevention, and other time-critical remote-sensing applications require real-time or autonomous decision making and onboard processing capabilities. Thus, lightweight, small size, and low-power-consumption hardware is essential for onboard real-time processing systems. With the increasing need for dimensionality, size, and resolution of hyperspectral sensors, additional challenges are posed upon remote-sensing processing systems, and more capable computing architectures are needed. Graphical processing units (GPUs) emerged as promising architecture for light-weight high-performance computing. In this paper, we propose accelerated parallel solutions for the well-known recursive hierarchical segmentation (RHSEG) analysis algorithm, using a GPU, hybrid multicore CPU with GPU and hybrid multicore CPU/GPU clusters. RHSEG is a method developed by the National Aeronautics and Space Administration, which is designed to provide more useful classification information with related objects and regions across the hierarchy of output levels. The proposed solutions are built using the NVidia’s compute unified device architecture and Microsoft’s C++ Accelerated Massive Parallelism (C++ AMP) and are tested using NVidia GeForce hardware and Amazon Elastic Compute Cluster (EC2). The achieved speedups by parallel solutions compared with CPU sequential implementations are 21× for parallel single GPU and 240× for hybrid multinode computer clusters with 16 computing nodes. The energy consumption is reduced to 74 % when using a single GPU, compared to that for the equivalent parallel CPU cluster.

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
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Notes

  1. NASA JPL (http://www.jpl.nasa.gov).

References

  1. Plaza, A.J., Chang, C.: High performance computing in remote sensing. Taylor & Francis Group, BocaRaton (FL) (2007)

    Book  Google Scholar 

  2. Shippert, P.: Introduction to hyperspectral image analysis. Online J. Space Commun. 3 (2003)

  3. Asanovic, K., Bodik, R., Catanzaro, B.C., Gebis, J.J., Husbands, P., Keutzer, K., Patterson, D.A., Plishker, W.L., Shalf, J., Williams S.W., Yelick, K.A.: The landscape of parallel computing research: a view from Berkeley. In: Technical report No. UCB/EECS-2006-183, EECS Department. University of California, Berkeley (2006)

  4. Owens, J.D., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A.E., Purcell, T.J.: A Survey of general-purpose computation on graphics hardware. Comput. Graph. Forum 26(1), 80–113 (2007)

    Article  Google Scholar 

  5. Setoain, J., Prieto, M., Tenllado, C., Tirado, F.: GPU for parallel on-board hyperspectral image processing. Int. J. High Perform. Comput. Appl. 22(4), 424–437 (2008)

    Article  Google Scholar 

  6. Lu, D., Weng, Q.: A survey of image classification methods and techniques for improving classification performance. Int. J. of Remote Sens. 28(5), 823–870 (2007)

    Article  Google Scholar 

  7. Li, J., Bioucas-Dias, J.M., Plaza, A.: Spectral-spatial classification of hyperspectral data using loopy belief propagation and active learning. IEEE Trans. Geosci. Remote Sens. 51(2), 844–856 (2013)

    Article  Google Scholar 

  8. Xu, L., Li, J.: Bayesian classification of hyperspectral imagery based on probabilistic sparse representation and Markov Random Field. IEEE Geosci. Remote Sens. Lett. 11(4), 823–827 (2014)

    Article  Google Scholar 

  9. Blaschke, T.: Object based image analysis for remote sensing. ISPRS J. Photogramm. Remote Sens. 65(1), 2–16 (2010)

  10. Camps-Valls, G., Tuia, D., Bruzzone, L., Atli Benediktsson, J.: Advances in hyperspectral image classification: earth monitoring with statistical learning methods. IEEE Signal Process. Mag. 31(1), 45–54 (2014)

    Article  Google Scholar 

  11. Plaza, A., Benediktsson, J.A., Boardman, J.W., Brazile, J., Bruzzone, L., Camps-Valls, G., Chanussot, J., Fauvel, M., Gamba, P., Gualtieri, A., Marconcini, M., Tilton, J.C., Trianni, G.: Recent advances in techniques for hyperspectral image processing. Remote Sens. Environ. 113, 110–122 (2009)

    Article  Google Scholar 

  12. Bioucas-Dias, J.M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., Chanussot, J.: Hyperspectral unmixing overview: geometrical, statistical, and sparse regression-based approaches. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 5(2), 354–379 (2012)

    Article  Google Scholar 

  13. Tilton, J.C.: Method for recursive hierarchical segmentation by region growing and spectral clustering with a natural convergence criterion. Discl. Invent. New Technol. NASA Case No. GSC 14, 328–331 (2000)

    Google Scholar 

  14. Hossam, M. A., Ebied, H. M., Abdel-Aziz, M. H.: Hybrid cluster of multicore CPUs and GPUs for accelerating hyperspectral image hierarchical segmentation. In: 8th International conference on computer engineering and systems (ICCES’13), 262–267 (2013)

  15. Kirk, D.: NVIDIA CUDA software and GPU parallel computing architecture. In: 6th International symposium on memory management (ISMM ‘07), 103–104 (2007)

  16. Gregory, K., Miller, A.: C++ Amp: accelerated massive parallelism with Microsoft Visual C++. Microsoft Press Series, Microsoft GmbH (2012)

    Google Scholar 

  17. Qt Project Documentation. http://www.qt-project.org/doc/qt-4.8/

  18. Amazon Elastic Compute cloud EC2. http://www.aws.amazon.com/ec2/

  19. Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. (CSUR) J. 31(3), 264–323 (1999)

    Article  Google Scholar 

  20. Beucher, S., Lantuéjoul, C.: Use of watersheds in contour detection. International Workshop on Image Processing, Real-Time edge and motion detection/estimation, CCETT/INSA/IRISA, IRISA Report no. 132, 2.1–2.12 (1979)

  21. Tarabalka, Y., Chanussot, J., Benediktsson, J.A.: Segmentation and Classification of hyperspectral images using watershed transformation. Pattern Recognit. J. 43(7), 2367–2379 (2010)

    Article  MATH  Google Scholar 

  22. Moreno, R., Graña, M.: Segmentation of hyperspectral images by tuned chromatic watershed, recent advances in knowledge-based paradigms and applications. Springer Int. Publ. 234, 103–113 (2014)

    Google Scholar 

  23. Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vision 59(2), 167–181 (2004)

    Article  Google Scholar 

  24. Fauvel, M., Tarabalka, Y., Benediktsson, J.A., Chanussot, J., Tilton, J.C.: Advances in spectral-spatial classification of hyperspectral images. Proc. IEEE 101(3), 652–675 (2013)

    Article  Google Scholar 

  25. Ball, G.H., Hall, D.J.: ISODATA: a novel method of data analysis and classification, Tech. Rep. Stanford University, Stanford CA (1965)

    Google Scholar 

  26. Plaza, A.J.: Parallel spatial-spectral processing of hyperspectral images. Comput. Intel. Remote Sens. SCI 133, 163–192 (2008)

    Google Scholar 

  27. Deb, S., Sinha, S.: Comparative improvement of image segmentation performance with graph based method over watershed transform image segmentation, distributed computing and internet technology. Springer Int. Publ. 8337, 322–332 (2014)

    Google Scholar 

  28. Beucher, S.: Watershed, hierarchical segmentation and waterfall algorithm. The second international conference on Mathematical Morphology and its Applications to Image Processing, 69–76 (1994)

  29. Tarabalka, Y., Chanussot, J., Benediktsson, J.A.: Segmentation and classification of hyperspectral images using minimum spanning forest grown from automatically selected markers. IEEE Trans. Syst. Man Cybern. B Cybern. 40(5), 1267–1279 (2010)

    Article  MATH  Google Scholar 

  30. Plaza, A., Valencia, D., Plaza, J., Martinez, P.: Commodity cluster-based parallel processing of hyperspectral imagery, plaza, valencia. J. Parallel Distrib. Comput. 66, 345–358 (2006)

    Article  MATH  Google Scholar 

  31. Lai, C., Huang, M., Shi, X., You H.: Accelerating geospatial applications on hybrid architectures. In: Proceedings of 15th IEEE International Conference on High Performance Computing and Communications (HPCC 2013), 1545–1552 (2013)

  32. Kenneland supercomputer. http://www.keeneland.gatech.edu/

  33. Yang, S., Dong J., Yuan, B.: An efficient parallel ISODATA algorithm based on Kepler GPUs. In: International Joint Conference on Neural Networks (2014)

  34. Becker, D.J., Sterling, T., Savarese, D., Dorband, J.E., Ranawake, U.A., Packer, C.V.: BEOWULF: a parallel workstation for scientific computation. In: Proceedings of International Conference on Parallel Processing (ICPP) (1995)

  35. Tilton, J.C.: Image segmentation by region growing and spectral clustering with a natural convergence criterion. In: International Geoscience and Remote Sensing Symposium (IGARSS 98), pp 1766–1768. Seattle, WA (1998)

  36. Beaulieu, J.M., Goldberg, M.: Hierarchy in picture segmentation: a stepwise optimization approach. IEEE Trans. Pattern Anal. Mach. Intell. 11(2), 150–163 (1989)

    Article  Google Scholar 

  37. Khronos Group OpenCL. Available: http://www.khronos.org/opencl/

  38. Reflective Optics System Imaging Spectrometer, ROSIS. http://www.opairs.aero/rosis_en.html

Download references

Author information

Authors and Affiliations

  1. Basic Sciences Department, Faculty of Computer and Information Sciences, Ain Shams University, Abbasia, Cairo, 11566, Egypt

    M. A. Hossam & M. H. Abdel-Aziz

  2. Scientific Computing Department, Faculty of Computer and Information Sciences, Ain Shams University, Abbasia, Cairo, 11566, Egypt

    H. M. Ebied & M. F. Tolba

Authors
  1. M. A. Hossam
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. H. M. Ebied
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. H. Abdel-Aziz
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. M. F. Tolba
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to H. M. Ebied.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hossam, M.A., Ebied, H.M., Abdel-Aziz, M.H. et al. Accelerated hyperspectral image recursive hierarchical segmentation using GPUs, multicore CPUs, and hybrid CPU/GPU cluster. J Real-Time Image Proc 14, 413–432 (2018). https://doi.org/10.1007/s11554-014-0464-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-014-0464-4

Keywords

Search

Navigation