No Access

IMAGE REGISTRATION AND FUSION SYSTEM BASED ON GPU

SEUNG-HUN YOO

Department of Electronics and Computer Engineering, Korea University, Anam-Dong 5-ga, Seongbuk-Gu, Seoul, Korea

Search for more papers by this author

and

CHANG-SUNG JEONG

Department of Electronics and Computer Engineering, Korea University, Anam-Dong 5-ga, Seongbuk-Gu, Seoul, Korea

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0218126610006049Cited by:0 (Source: Crossref)

Abstract

Graphics processing unit (GPU) has surfaced as a high-quality platform for computer vision-related systems. In this paper, we propose a straightforward system consisting of a registration and a fusion method over GPU, which generates good results at high speed, compared to non-GPU-based systems. Our GPU-accelerated system utilizes existing methods through converting the methods into the GPU-based platform. The registration method uses point correspondences to find a registering transformation estimated with the incremental parameters in a coarse-to-fine way, while the fusion algorithm uses multi-scale methods to fuse the results from the registration stage. We evaluate performance with the same methods that are executed over both CPU-only and GPU-mounted environment. The experiment results present convincing evidences of the efficiency of our system, which is tested on a few pairs of aerial images taken by electro-optical and infrared sensors to provide visual information of a scene for environmental observatories.

Keywords:

References

M. I. Smith and J. P. Heather, A review of image fusion technology in 2005, Proc. SPIE 5782 (2005) pp. 29–45. Google Scholar
R. S. Blum and Z. Liu , Multi-Sensor Image Fusion and Its Applications , eds. R. S. Blum and Z. Liu ( Taylor & Francis , New York , 2005 ) . Google Scholar
A. Ardeshir Goshtasby and S. Nikolov, Inform. Fusion 8, 114 (2007). Web of Science, Google Scholar
Y. Zhenget al., Inform. Fusion 8, 177 (2007), DOI: 10.1016/j.inffus.2005.04.003. Web of Science, Google Scholar
A. Ardeshir Goshtasby , 2D and 3D Image Registration: For Medical, Remote Sensing, and Industrial Applications ( Wiley & Sons , Hoboken , 2005 ) . Google Scholar
B. Zitová and J. Flusser, Image Vis. Comput. 21, 977 (2003). Web of Science, Google Scholar
S. H. Changet al., Pattern Recogn. 30, 311 (1997), DOI: 10.1016/S0031-3203(96)00076-3. Web of Science, Google Scholar
M. Irani and P. Anandan, Robust multi-sensor image alignment, Proc. Int. Conf. Comput. Vis. (1998) pp. 959–966. Google Scholar
A. Goshtasby and G. Stockman, IEEE Trans. Syst. Man Cybern. SMC-15, 631 (1985). Web of Science, Google Scholar
Y. Xiong and F. Quek, Automatic aerial image registration without correspondence, IEEE Int. Conf. Comput. Vis. Syst. (2006) pp. 25–32. Google Scholar
G. Stockman, S. Kopstein and S. Benett, IEEE Trans. Pattern Anal. Mach. Intell. 4, 229 (1992). Web of Science, Google Scholar
C. Shekhar, V. Govindu and R. Chellappa, Pattern Recogn. 32, 39 (1999), DOI: 10.1016/S0031-3203(98)00089-2. Web of Science, Google Scholar
G. Borgefors, IEEE Trans. Pattern Anal. Mach. Intell. 10, 849 (1988), DOI: 10.1109/34.9107. Web of Science, Google Scholar
H. G. Barrowet al., Parametric correspondence and chamfer matching: Two new techniques for image matching, Proc. Int. Joint Conf. Artificial Intelligence (1977) pp. 659–663. Google Scholar
J. Le Moigneet al., Multisensor registration of Earth remotely sensed imagery, Proc. SPIE 4541 (2001) pp. 1–10. Google Scholar
J. D. Owenset al., Comput. Graph. Forum 26, 80 (2007), DOI: 10.1111/j.1467-8659.2007.01012.x. Web of Science, Google Scholar
M. Pharr and R. Fernando , GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation ( Addison-Wesley , Massachusetts , 2005 ) . Google Scholar
R. Fernando and M. J. Kilgard , The Cg Tutorial: The Definitive Guide to Programmable Real-Time Graphics ( Addison-Wesley , Boston , 2003 ) . Google Scholar
S. St-Laurent , The Complete Effect and HLSL Guide ( Paradoxal Press , Redmond , 2005 ) . Google Scholar
R. J. Rost , OpenGL Shading Language , 2nd edn. ( Addison-Wesley Profreesional , 2006 ) . Google Scholar
P. S. McCormicket al., Parallel Comput. 33, 648 (2007). Web of Science, Google Scholar
J. L. T. Cornwall, Efficient multiple pass, multiple output algorithms on the GPU, Eur. Conf. Visual Media Production (2005) pp. 253–262. Google Scholar
J. Juliano and J. Sandmel, OpenGL extension (2005), http://www.nvidia.com/dev_content/nvopenglspecs/GL_EXT_framebuffer_object.txt . Google Scholar
M. Strengert, M. Kraus and T. Ertl, Pyramid Methods in GPU-Based Image Processing, Proc. Vision, Modeling, and Visualization (2006) pp. 169–176. Google Scholar
C. Tenlladoet al., IEEE Trans. Parallel Distrib. Syst. 19, 299 (2008), DOI: 10.1109/TPDS.2007.70716. Web of Science, Google Scholar
T. T. Wonget al., IEEE Trans. Multimed. 9, 668 (2007), DOI: 10.1109/TMM.2006.887994. Web of Science, Google Scholar
T. Smalley, Intel's Core 2 Duo processors (2006), http://www.bit-tech.net/hardware/cpus/2006/07/14/intel_core_2_duo_processors/1 . Google Scholar
H. Nguyen , GPU Gems 3 ( Addison-Wesley , Boston , 2007 ) . Google Scholar

Vol. 19, No. 01

Metrics

Downloaded 33 times

History

Keywords

PDF download

System Upgrade on Tue, May 28th, 2024 at 2am (EDT)

IMAGE REGISTRATION AND FUSION SYSTEM BASED ON GPU

Abstract

Recommended