Abstract
The high computational cost of the techniques for segmentation and classification of hyperspectral images makes them good candidates for parallel processing, in particular, for computing on Graphics Processing Units (GPUs). In this paper an efficient projection on the GPUs for the spectral–spatial classification of hyperspectral images using the Compute Unified Device Architecture (CUDA) for NVIDIA devices is presented. A watershed transform is applied after reducing the hyperspectral image to one band through the calculation of a morphological gradient, while the spectral classification is carried out by Support Vector Machine (SVMs). The results are combined with an adaptive majority vote. The different computational stages are concatenated in a pipeline that minimizes the data transfer between the main memory of the host computer and the global memory of the graphics device to maximize the computational throughput. The memory hierarchy and the thousands of threads available in this architecture are efficiently exploited. It is possible to study different data partitioning strategies and thread block arrangements in order to promote concurrent execution of a large number of threads. The objective is to efficiently exploit commodity hardware with the aim of achieving real-time execution for on-board processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See CUBLAS at https://developer.nvidia.com/cublas
- 2.
Hyperspectral Remote Sensing Scenes available at http://www.ehu.es/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes
References
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, S110–S122 (2009)
van der Meer, F.D., van der Werff, H.M., van Ruitenbeek, F.J., Hecker, C.A., Bakker, W.H., Noomen, M.F., van der Meijde, M., Carranza, E.J.M., de Smeth, J.B., Woldai, T.: Multi- and hyperspectral geologic remote sensing: A review. Int. J. Appl. Earth Observ. Geoinform. 14(11), 112–128 (2012)
Gualtieri, J.A., Cromp, R.F.: Support vector machines for hyperspectral remote sensing classification. Proc. SPIE 3584, 221–232 (1998)
Jia, X., Richards, J.A., Ricken, D.E.: Remote Sensing Digital Image Analysis: An Introduction. Springer Verlag, Berlin (1999)
Varshney, P. K., Arora, M. K. (eds.).: Advanced Image Processing Techniques for Remotely Sensed Hyperspectral Data. Springer Verlag, Berlin (2004)
Fauvel, M., Chanussot, J., Benediktsson, J.A., Sveinsson, J.R.: Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles. IEEE Trans. Geosci. Remote Sens. 46(10), 3804–3814 (2008)
Tarabalka, Y., Benediktsson, J.A. and Chanussot, J.: Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques. Geosci. Remote Sens. IEEE Trans. 47(8) , 2973–2987 (2009)
Tarabalka, Y., Chanussot, J., Benediktsson, J.A.: Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recogn. 43(7), 2367–2379 (2010)
Fauvel, M.: Spectral and spatial methods for the classification of urban remote sensing data, Ph.D. Dissertation, Grenoble Institute of Technology, Grenoble (2007)
Farag, A.A., Mohamed, R.M., El-Baz, A.: A unified framework for MAP estimation in remote sensing image segmentation. Geosci. Remote Sens. IEEE Trans. 43(7), 1617–1634 (2005)
Couprie, C., Grady, L., Najman, L., Talbot, H.: Power watershed: a unifying graph-based optimization framework. Pattern Anal. Mach. Intell. IEEE Trans. 33(7), 1384–1399 (2011)
Tarabalka, Y., Benediktsson, J.A. and Chanussot, J.: Classification of hyperspectral data using support vector machines and adaptive neighborhoods. In: Proceedings of 6th EARSeL SIG IS, Workshop (2009)
Bernard, K., Tarabalka, Y., Angulo, J., Chanussot, J., Benediktsson, J.A.: Spectral spatial classification of hyperspectral data based on a stochastic minimum spanning forest approach. Image Process. IEEE Trans. 21(4), 2008–2021 (2012)
Vincent, L., Soille, P.: Watersheds in digital spaces: an eficient algorithm based on immersion simulations. IEEE Trans. Pattern Anal. Mach. Intell. 13, 583–598 (1991)
Plaza, A., Plaza, J., Vegas, H.: Improving the performance of hyperspectral image and signal processing algorithms using parallel, distributed speciallized hardware-based systems. J. Signal Proces. Syst. 61(3), 293–315 (2010)
González, C., Sánchez, S., Paz, A., Resano, J., Mozos, D., Plaza, A.: Use of FPGA or GPU-based architectures for remotely sensed hyperspectral image processing. Integr. VLSI J. 46(2), 89–103 (2013)
Tarabalka, Y., Haavardsholm, T.V., Kåsen, I., Skauli, T.: Real-time anomaly detection in hyperspectral images using multivariate normal mixture models and GPU processing. J. Real Time Image Process. 4(3), 287–300 (2009)
Heras, D. B., Argüello, F., Gómez, J. L., Becerra, J. A., Duro, R. J.: Towards real-time hyperspectral image processing, a GP-GPU implementation of target identification. In: 2011 IEEE 6th Internatioonal Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS), vol. 1 pp. 316–321 (2011)
Priego, B., Souto, D., Bellas, F., Duro, R.J.: Unsupervised segmentation of hyperspectral images through evolved cellular automata. Adv. Knowl. Based Intell. Inform. Eng. Syst. 243, 2160–2169 (2012)
Quesada-Barriuso, P., Argüello, F., Heras, D.B.: Efficient segmentation of hyperspectral images on commodity GPUs. Adv. Knowl. Based Intell. Inform. Eng. Syst. 243, 2130–2139 (2012)
Christophe, E., Michel, J., Inglada, J.: Remote sensing processing: from multicore to GPU. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 4(3), 643–652 (2011)
Bernabé, S., Plaza, A., Reddy Marpu, P., Benediktsson, J.A.: A new parallel tool for classification of remotely sensed imagery. Comput. Geosci. 46, 208–218 (2012)
NVIDIA Corporation: NVIDIA CUDA C Programming Guide 4.2, Santa Clara (2011)
NVIDIA Corporation: NVIDIA’s Next Generation CUDA Compute Architecture: Kepler GK110 Whitepaper (2012)
NVIDIA Corporation: CUDA C Best Practices Guide (2012)
Gege, P., Beran, D., Mooshuber, W., Schulz, J. and Van Der Piepen, H.: System analysis and performance of the new version of the imaging spectrometer rosis, in Proceedings of the First EARSeL Workshop on Imaging Spectroscopy. University of Zurich Remote Sensing Laboratories, pp. 29–35 (1998)
Green, R.O., Eastwood, M.L., Sarture, C.M., Chrien, T.G., Aronsson, M., Chippendale, B.J., Faust, J.A., Pavri, B.E., Chovit, C.J., Solis, M.S., Olah, M.R., Williams, O.: Imaging spectroscopy and the airborne visible/infrared imaging spectrometer (AVIRIS). Remote Sens. Environ. 65(3), 227–248 (1998)
Camps-Valls, G., Bruzzone, L.: Kernel-based methods for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 43(6), 1351–1362 (2005)
Evans, A. and Liu, X.: A morphological gradient approach to color edge detection. Image Process IEEE Trans. 15(6), 1454–1463 (2006)
Roerdink, J.B.T.M., Meijster, A.: The watershed transform: definitions, algorithms and parallelization strategies. Fund. Inform. 41(1–2), 187–228 (2000)
Meyer, F.: Topographic distance and watershed lines. Math. Morphol. Appl. Signal Process. 38(1), 113–125 (1994)
Galilée, B., Mamalet, F., Renaudin, M., Coulon, P.Y.: Parallel asynchronous watershed algorithm-architecture. IEEE Trans. Paral. Distrib. Syst. 18(1), 44–56 (2007)
Nehaniv, C.L.: Evolution in asynchronous cellular automata. In: Proceedings of the 8th International Conference on Artificial life, MIT Press, pp. 65–73 (2003)
Quesada-Barriuso, P., Heras, D.B. and Argüello, F.: Efficient GPU asynchronous implementation of a watershed algorithm based on cellular automata. In: Proceedings of IEEE International Symposium on Parallel and Distributed Processing with Applications, pp. 79–86 (2012)
Boyer, R.S., Moore, J.S.: MJRTY - a fast majority vote algorithm, In: Boyer, R. S. (ed.) Automated Reasoning 1 Automated Reasoning Series, Springer, Netherlands, pp. 105–117 (1991)
Santos, A., Araújo, A., Menotti, D.: Combining multiple approaches for accuracy improvement in remote sensed hyperspectral images classification.In: Workshop of Thesis and Dissertations - XXV Conference on Graphics, Patterns and Images, pp. 54–59 (2012)
Balasalle, J., López, M.A., Rutherford, M.J.: Optimizing memory access patterns for cellular automata on GPUs. In: Hwu W. W. (ed.) GPU Computing Gems, Jade Edition. Morgan Kaufmann Publishers Inc., San Francisco, pp. 67–75 (2012)
Athanasopoulos, A., Dimou, A., Mezaris, V. and Kompatsiaris, I.: GPU acceleration for support vector machines, In: Proceedings of 12th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2011), Delft (2011)
Carpenter, A.: CUSVM: a CUDA implementation of support vector classification and regression, patternsonscreen (2009)
Catanzaro, B., Sundaram, N. and Keutzer, K.: Fast support vector machine training and classification on graphics processors. In: Proceedings of the 25th International Conference on Machine learning - ICML’08, pp. 104–111 (2008)
Herrero-López, S., Williams, J. R. and Sanchez, A.: Parallel multiclass classification using SVMs on GPUs. In: Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units, ACM, pp. 2–11 (2010)
Li, Q., Salman, R., Test, E., Strack, R., Kecman, V.: GPUSVM: a comprehensive CUDA based support vector machine package. Central Eur. J. Comput. Sci. 1(4), 387–405 (2011)
Harris, M.: Optimizing parallel reduction in CUDA. NVIDIA Developer Technology, (2007)
Hawick, K.A., Leist, A., Playne, D.P.: Parallel graph component labelling with GPUs and CUDA. Parallel Comput. 36(12), 655–678 (2010)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27 (2011)
Hsu, C.-W., Lin, C.-J.: A comparison of methods for multiclass support vector machines. IEEE Trans. Neural Netw. 13(2), 415–425 (2002)
Acknowledgments
This work was supported in part by the Ministry of Science and Innovation, Government of Spain, cofounded by the FEDER funds of European Union, under contract TIN 2010-17541, and by Xunta de Galicia, Program for Consolidation of Competitive Research Groups ref. 2010/28. Pablo acknowledges financial support from the Ministry of Science and Innovation, Government of Spain, under a MICINN-FPI grant.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Quesada-Barriuso, P., Argüello, F., Heras, D.B. (2014). Computing Efficiently Spectral-Spatial Classification of Hyperspectral Images on Commodity GPUs. In: Tweedale, J., Jain, L. (eds) Recent Advances in Knowledge-based Paradigms and Applications. Advances in Intelligent Systems and Computing, vol 234. Springer, Cham. https://doi.org/10.1007/978-3-319-01649-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-01649-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-01648-1
Online ISBN: 978-3-319-01649-8
eBook Packages: EngineeringEngineering (R0)