Abstract
The traditional super-resolution image reconstruction methods for optimization and implementation are designed for common processor (CPU). According to the parallel computing capability of GPU-CUDA, a fast super-resolution image reconstruction method is presented based on GPU-CUDA. Additionally, we proposed the MAP framework that can allocate sub-pixel displacement information of low-resolution images to the unified super-resolution image grid. On the basis of the parallel architecture and hardware characteristic of GPU, the acceleration method use CUDA programmable parallel framework to optimize the data storage structure, improve the efficiency of data access and reduce the complexity of the algorithm. The experiment expressed that we could get an over ten times speed effect by this method than traditional super-resolution image reconstruction methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Farsiu, S., Robinson, D., Elad, M., Milanfar, P.: Fast and Robust Multi-frame Super-resolution. IEEE Transactions on Image Processing 13(10), 1327–1344 (2004)
Schultz, R.R., Stevenson, R.L.: Extraction of high-resolution frames from video sequences. IEEE Transactions Image Processing 5(6), 996–1011 (1996)
Irani, M., Peleg, S.: Improving resolution by image registration. CVGIP 53(3), 231–239 (1991)
Elad, M., Feuer, A.: Super resolution restoration of an image sequence: adaptive filtering approach. IEEE Trans. Image Processing 8(3), 387–395 (1999)
Hardie, R.: A fast image super-resolution algorithm usingan adaptive Wiener filter. IEEE Trans. Image Processing 16(12), 2953–2964 (2007)
Park, S.C., Park, M.K., Kang, M.G.: Super-Resolution Image Reconstruction: A technical Overview. IEEE Signal Processing Magazine, 21–36 (May 2003)
Marcelo, V.W.Z., Fermin, S.V.B., Joceji, M.: Determining the regularization parameters for super-resolution problem. Signal Processing 88(12), 2890–2901 (2008)
Capel, D., Zisserman, A.: Super-resolution enhancement of text image sequences. In: Proceeding of the International Conference on Pattern Recognition, pp. 600–605. IEEE Computer Society, Barcelona (2000)
Farsiu, S., Robinson, M.D.: Fast and robust multiframe super resolution. IEEE Trans. on Image Processing 13(10), 1327–1344 (2004)
Li, X.L., Hu, Y.T., Gao, X.B., et al.: A mult-iframe image super-resolution method. Signal Processing 90(2), 405–414 (2010)
Ni, K., Nguyen, T.Q.: Image super-resolution using support vector regression. IEEE Transactions Image Processing 16(6), 1596–1610 (2007)
Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learninglow-level vision. International Journal of Computer Vision 40(1), 25–47 (2002)
Yang, J.C., Wright, J., Ma, Y., et al.: Image super-resolutionas sparser epresentation of raw image patches. In: CVPR, pp. 1–8. IEEE Computer Society Press, Anchorage (2008)
Lowe, D.G.: Object recognition from local scale-invariant features. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157 (1999)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(11), 1222–1239 (2001)
Boykov, Y., Veksler, O., Zabih, R.: Fast Approximate Energy Minimization via Graph Cuts. IEEE TPAMI 20(12), 1222–1239 (2001)
Tsai, R.Y., Huang, T.S.: Multiframe image restoration and registration. Advances in Computer Vision and Image Processing 1, 317–339 (1984)
Lertrattanapanich, S., Bose, N.K.: High resolution image formation from low resolution frames using delaunay triangulation. IEEE Transactions on Image Processing 11(12), 1427–1441 (2002)
Banham, M.R., Katsaggelos, A.K.: Digital image restoration. IEEE Signal Processing Magazine 14(2), 24–41 (1997)
Farsiu, S., Robinson, M.D., Elad, M., Milanfar, P.: Fast and robust multiframe super resolution. IEEE Transactions on Image Processing 13(10), 1327–1344 (2004)
Freeman, W.T., Jones, T.R., Paztor, E.C.: Example based superresolution. IEEE Computer Graphics and Applications 22(2), 56–65 (2002)
Sun, J., Zheng, N.N., Tao, H., Shum, H.Y.: Image hallucination with primal sketch priors. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), vol. 2, pp. 729–736 (June 2003)
Cang, H., Oung, D.Y.Y., Xiong, Y.: Super-resolution through neighbor embedding. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), vol. 1, pp. 275–282 (July 2004)
Freeman, W.T., Pasztor, E.C., Carmichael, O.T.: Learning lowlevel vision. International Journal of Computer Vision 40(1), 25–47 (2004)
Dai, S., Han, M., Xu, W., Wu, Y., Gong, Y.: Soft edge smoothness prior for alpha channel super resolution. In: IEEE Computer Vision and Pattern Recognition (CVPR 2007), pp. 1–8 (June 2007)
Yang, J., Wright, J., Ma, Y., Huang, T.: Image super-resolution as sparse representation of raw image patches. In: IEEE Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8 (August 2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Song, Z., Chen, Z., Shi, R. (2015). Fast MAP-Based Super-Resolution Image Reconstruction on GPU-CUDA. In: Bian, F., Xie, Y. (eds) Geo-Informatics in Resource Management and Sustainable Ecosystem. GRMSE 2014. Communications in Computer and Information Science, vol 482. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45737-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-662-45737-5_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45736-8
Online ISBN: 978-3-662-45737-5
eBook Packages: Computer ScienceComputer Science (R0)