Pixel-Level Image Fusion Based on Programmable GPU

Abstract:

A novel algorithm which is image fusion based on GPU is proposed. The fused rule is regional energy. In recent years, the power of the computing of GPU has been greatly improved, which results that using it for the general-purpose computing has a rapid development. The essay researches on implementing the oriental field algorithm on GPU, including selecting GPU memories and dividing blocks and threads of GPU kernel functions. The results of experiment on the GPU of NVIDIA GTX560 are given, which shows that our proposed algorithm can be applied to the field of image fusion. Experiment shows the proposed algorithm has faster calcu-lation velocity and higher evaluation accuracy. The speed of the parallel algorithm is 200 times faster than that of the CPU-based implementation. Meanwhile the mutual information and Q^AB/F parameters are higher than that of the CPU-based algorithm.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 3872-3876
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.3872
• Online since: August 2013
• Authors: Hong Li, Gao Feng Tang, Fen Xia Wu, Cong E Tan
• Keywords: Graphic Processing Unit (GPU), Image Fusion, Local Feature

References

[1] S. Daneshvar, H. Ghassemian, MRI and PET image fusion by combining IHS and retina-inspired models, , Information Fusion, vol. 11, pp.114-123, Feb (2010).

DOI: 10.1016/j.inffus.2009.05.003

[2] Z. Zhang, R. S. Blum. A categorization of multiscale decomposition based image fusion schemes with a performance studey for a digital camera application, , Proceedings of the IEEE, vol. 87, pp.1315-1326, Aug (1999).

DOI: 10.1109/5.775414

[3] P. T. Burt, E. H. Andelson, The Laplacian pyramid as a compact image code, , IEEE Transactions on Communications, vol. 31, p.532–540, Apr (1983).

DOI: 10.1109/tcom.1983.1095851

[4] V. S. Petrovic and C. S. Xydeas, Gradient-based multiresolution image fusion, IEEE Trans. Image Process, vol. 13, pp.228-237, Feb (2004).

DOI: 10.1109/tip.2004.823821

[5] G. Pajares, J. Cruz, A wavelet-based fusion tutorial, Pattern Recognition, vol. 37, pp.1855-1872, Sep (2004).

DOI: 10.1016/j.patcog.2004.03.010

[6] M. Beaulieu, S. Foucher, L. Gagnon, Multi-spectral image resolution refinement using stationary wavelet transform, in: Proceedings of the International Geoscience and Remote Sensing Symposium, , p.4032–4034, (1989).

DOI: 10.1109/igarss.2003.1295352

[7] J. J. Lewis, R. J. O'Callaghan, S. G. Nikolov, D. R. Bull, C. N. Canagarajah, Region-based image fusion using complex wavelets, in: Proceedings of the 7th International Conference on Image Fusion, p.555–562, (2004).

DOI: 10.1016/j.inffus.2005.09.006

[8] Chen, J. P. Zhang, Y. Zhang, Remote sensing image fusion based on ridgelet transform, in: Proceedings of International Conference on Geoscience and Remote Sensing Symposium, , 2005, p.1150–1153.

DOI: 10.1109/igarss.2005.1525320

[9] L. Tessens, A. Ledda, A. Pizurica, W. Philips, Extending the depth of field in microscopy through curvelet-based frequency-adaptive image fusion, in: Proceedings of the International Conference on Acoustics, Speech and Signal Processing, , pp. I-861–I-864, (2007).

DOI: 10.1109/icassp.2007.366044

[10] L. D. Cunha, J. P. Zhou, The nonsubsampled contourlet transform: theory, design, and applications, IEEE Transactions on Image Processing, vol. 15, p.3089–3101, Oct (2006).

DOI: 10.1109/tip.2006.877507

[11] YU Wen-guang, WANG Wei-ping , Hou Hong-tao, LI Qun. Parallel Agent-based simulation on multi-core CPU and GPU heterogeneous platforms, Systems Engineering and Electronics, vol. 34, pp.1716-1722, Aug (2012).

[12] NVIDA, CUDA C Programming Guide 3. 2[EB/OL]. http: /developer. download. nvi dia. com/ computer/cuda/3_2/toolkit/ docs/CUDA_C_Programming_Guide. pdf.

DOI: 10.1017/9781108855273.018

[13] NVIDA CUDA [EB/OL]. http: /www. nvidia. com/object/cuda_home_ new. html.

[14] Harish P, Narayanan P J. Accelerating large graph algorithms on the GPU using DUDA [c], " pp.197-208, Dec 2007[Pro. 14th Int'l Conf. High Performance Computing(HiPC, 07)].

DOI: 10.1007/978-3-540-77220-0_21

[15] Katz G J, Kider J T, Jr. All-pairs shortest-paths for large graphs on the GPU[C], [Proc. of the 23rd ACM].

[16] DI Peng, HU Chang-jun, LI Jian-jiang. Efficient method for histogram generation on GPU, , Computer Science, vol. 39, pp.304-307, Mar (2012).