Abstract
Super Resolution (SR) refers to the reconstruction of a high resolution image from one or more low resolution images for the same scene. The reconstruction process is considered an inverse problem to the observation model. In this paper the SR problem is formulated by using Support Vector Regression (SVR). SVR is a very expensive computationally algorithm, thus it could be accelerated by using the computational power of a Graphics Processing Unit (GPU). The proposed parallel SVR has been implemented using NVidia’s compute device unified architecture (CUDA). An experiment has been done for a real satellite image. The experimental result demonstrates the speedup of the presented GPU implementation and compared with the serial CPU implementation and state-of-the-art techniques. The speedup of the presented SVR GPU-based implementation is up to approximately 50 times faster than the corresponding optimized CPU.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Yang, J., Huang, T.: Image super-resolution: Historical overview and future challenges. Super-Resolution Imaging, pp. 1–24. CRC Press (2010)
Kang, L.-W., et al.: Self-learning-based single image super-resolution of a highly compressed image. In: 5th International Workshop on Multimedia Signal Processing (MMSP) (2013)
Candocia, F.M., Principe, J.C.: Super resolution of images with learned multiple reconstruction kernels. In: Guan, L., Kung, S.Y., Larsen, J. (eds.) Multimedia Image and Video Processing, pp. 219–243. CRC Press, New York (2000)
van Ouwerkerk, J.D.: Image super-resolution survey. Image and Vision Computing 24, 1039–1052 (2000)
Miravet, C., Rodriguez, F.B.: A two-step neural-network based algorithm for fast image super-resolution. Image and Vision Computing 25, 1449–1473 (2007)
Mountrakis, G., Im, J., Ogole, C.: Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing 66, 247–259 (2011)
An, L., Bhanu, B.: Improved Image Super-Resolution by Support Vector Regression. In: International Joint Conference on Neural Networks, San Jose, California, USA, July 31-August 5 (2011)
Ho, T., Zeng, B.: Super-resolution images by support vector regression on edge pixels. In: International Symposium on Intelligent Signal Processing and Communication Systems, November 28-December 1, pp. 674–677 (2007)
Smolaandand, A.J., Schölkopf, B.: A tutorial on support vector regression. Statistics and Computing 14, 199–222 (2004)
Li, D., Simske, S.: Example Based Single-frame Image Super-resolution by Support Vector Regression. Journal of Pattern Recognition Research 1, 104–118 (2010)
Ni, K.S., Nguyen, T.Q.: Image Super resolution Using Support Vector Regression. IEEE Transactions on Image Processing 16(6) (June 2007)
Karl, S.N., Kumar, S., Vasconcelos, N., Nguyen, T.Q.: Single image super resolution based on support vector regression. In: ICASSP (2006)
Drucker, H., Burges, J.C., Kaufman, L., Smola, A., Vapnik, V.: Support Vector Regression Machines. In: Advances in Neural Information Processing Systems, NIPS 1996, vol. 9, pp. 155–161. MIT Press (1997)
Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines (2001), http://www.csie.ntu.edu.tw/~cjlin/
Fan, R.E., Chen, P.H., Lin, C.J.: Working set selection using second order information for training SVM. Journal of Machine Learning Research 6, 1889–1918 (2005)
Hua, T.L., Liu, L.X., Kai, S.Z., Yang, W.Y.: GPU Acceleration of Interior Point Methods in Large Scale SVM Training.12th IEEE International Conference on Security and Privacy in Computing and Communications (TrustCom), pp. 863–870 (2013)
Do, T.N., Nguyen, V.H., Poulet, F.: A Fast Parallel SVM Algorithm for Massive Classification Tasks. Sciences Communications 14, 419–428 (2008)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing 13(4), 600–612 (2004)
Achard, F., Malingreau, J.P., Phulpin, T., Saint, G., Saugier, B., Segun, B., Madjar, D.V.: The Vegetation Instrument on Board SPOT-4 - A Mission for Global Monitoring of the Continental Biosphere. LERTS brochure, Toulouse (1990)
Zhao, H., Yu, J.: A Modified SMO Algorithm for SVM Regression and its Application in Quality Prediction of HP-LDPE. In: Wang, L., Chen, K., S. Ong, Y. (eds.) ICNC 2005. LNCS, vol. 3610, pp. 630–639. Springer, Heidelberg (2005)
Hu, X., Peng, S., Hwang, W.L.: Learning adaptive interpolation kernels for fast single-image super resolution. Signal Image and Video Processing, 1077–1086 (2014)
Purkait, P., Pal, N.R., Chanda, B.: A Fuzzy-Rule-Based Approach for Single Frame Super Resolution. IEEE Transactions on Image Processing 23(5), 2277–2290 (2014)
Chen, J., Yanez, J.N., Achim, A.: Bayesian Video Super-resolution with Heavy Tailed Prior Models. IEEE Transactions on Circuits and Systems for Video Technology 99, 1–1 (2014)
CULA (GPU-Accelerated LAPACK), http://www.culatools.com/
Hassanien, A.E., Suraj, Z., Slezak, D., Lingras, P.: Rough computing: Theories, technologies and applications. IGI Publishing Hershey, PA (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Moustafa, M., Ebied, H.M., Helmy, A., Nazamy, T.M., Tolba, M.F. (2014). Satellite Super Resolution Image Reconstruction Based on Parallel Support Vector Regression. In: Hassanien, A.E., Tolba, M.F., Taher Azar, A. (eds) Advanced Machine Learning Technologies and Applications. AMLTA 2014. Communications in Computer and Information Science, vol 488. Springer, Cham. https://doi.org/10.1007/978-3-319-13461-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-13461-1_22
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13460-4
Online ISBN: 978-3-319-13461-1
eBook Packages: Computer ScienceComputer Science (R0)