Fast image registration in DirectX9 graphics hardware

• Autorzy: Strzódka R. , Droske M. , Rumpf M.
• Języki publikacji: EN

Abstrakty

EN

The analysis of image time series requires a correlation of the information between two images. The gradient flow registration is a method for correlating this information by successively minimizing an appropriate energy along its gradient A graphics hardware implementation of this approach to image registration is presented. The gradient flow formulation makes use of a robust multi-scale regularization, an efficient multi-grid solver and an effective time-step control. The locality of the involved operations implies a data-flow which is very well suited for an acceleration in the streaming architecture of the DX9 graphics hardware. Therefore, the implementation obtains registration results at very high performance, registering two 2562 in less than 2 seconds, such that it could be used as an interactive tool in medical image analysis.

Słowa kluczowe

EN

image registration; gradient flow; graphics hardware

PL

rejestracja obrazu; przepływ stopnia nachylenia; sprzęt graficzny

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2003
• Tom: Vol. 6
• Strony: IT43--49
• Opis fizyczny: Bibliogr. 21 poz., rys.

Twórcy

autor

Strzódka R.

• Research Center Caesar, D-53044 Bonn

autor

Droske M.

• Duisburg University, D-47048 Duisburg

autor

Rumpf M.

• Duisburg University, D-47048 Duisburg

Bibliografia

• [1] G.E. CHRISTENSEN, S.C. JOSHI, M.I. MILLER, "Volumetric transformations of brain anatomy," IEEE Trans. Medical Imaging, vol. 16, no. 6, pp. 864-877,1997.
• [2] C.A. DAVATZIKOS, R.N. BRYAN, J.L. PRINCE, "Image registration based on boundary mapping," IEEE Trans. Medical Imaging, vol. 15, no. 1, pp. 112-115, 1996.
• [3] U. GRENANDER, M.I. MILLER, "Computational anatomy: An emerging discipline," Quarterly Appl. Math., vol. LVI, no. 4, pp. 617-694, 1998.
• [4] F. MAES, A. COLLIGNON, D. VANDERMEULEN, G. MARCHAL, P. SUETENS, "Multi-modal volume registration by maximization of mutual information," IEEE Trans. Medical Imaging, vol. 16, no. 7, pp. 187-198, 1997.
• [5] J.P. THIRION, "Image matching as a diffusion process: An analogy with maxwell's demon," Medical Imag. Analysis, vol. 2, pp. 243-260, 1998.
• [6] U. CLARENZ, M. DROSKE, M. RUMPF, "Towards fast non-rigid registration," in Contemporary Mathematics, Special Issue on Inverse Problems and Image Analysis, Z. Nashed and O. Scherzer, Eds. 2002, AMS.
• [7] M. HANKE, C.W. GROETSCH, ''Nonstationary iterated tikhonov regularization," J. Optim. Theory and Applications, vol. 98, pp. 37-53, 1998.
• [8] S. HENN, K. WITSCH, "Iterative multigrid regularization techniques for image matching," SIAM J. Sci Comput. (SISC), vol. Vol. 23 no. 4, pp. pp. 1077-1093, 2001.
• [9] L. ALVAREZ, J. WEICKERT, J. S'ANCHEZ, "Reliable estimation of dense optical flow fields with large displacements, "International Journal of Computer Vision, vol. 39, pp. 41-56, 2000.
• [10] MARK S. PEERCY, MARC OLANO, JOHN AIREY, P. JEFFREY UNGAR, "Interactive multi-pass programmable shading," in Siggraph 2000, Computer Graphics Proceedings, Kurt Akeley, Ed. 2000, Annual Conference Series, pp. 425-432, ACM Press / ACM SIGGRAPHI Addison Wesley Longman.
• [11] KEKOA PROUDFOOT, WILLIAM R. MARK, SVETOSLAV TZVETKOV, PAT HANRAHAN, "A real-time procedural shading system for programmable graphics," in SIGGRAPH 2001, Computer Graphics Proceedings, Eugene Fiume, Ed. 2001, Annual Conference Series, pp. 159-170, ACM Press / ACM SIGGRAPH.
• [12] J. LENGYEL, M. REICHERT, B.R. DONALD, D.P. GREENBERG, "Real-time robot motion planning using rasterizing computer graphics hardware," in Proceedings of SIGGRAPH 1990, 1990, pp. 327-335.
• [13] KENNETH E. HOFF III, JOHN KEYSER, MING LIN, DINESH MANOCHA, TIM CULVER, "Fast computation of generalized Voronoi diagrams using graphics hardware, "Computer Graphics, vol. 33, no. Annual Conference Series, pp. 277-286, 1999.
• [14] D. WEISKOPF, M. HOPF, T. ERTL, "Hardware accelerated visualization of time-varying 2d and 3d vector fields by texture advection via programmable per-pixel operations," in Proceedings of VMV'01, 2001, pp. 439-446.
• [15] M. HOPF, T. ERTL, "Accelerating Morphological Analysis with Graphics Hardware," in Workshop on Vision, Modelling, and Visualization VMV'00, 2000, pp. 337-345.
• [16] M. RUMPF, R. STRZODKA, "Level set segmentation in graphics hardware," in Proceedings ICIP'01, 2001, vol. 3, pp. 1103-1106.
• [17] MARK J. HARRIS, "General purpose computation using graphics hardware, "http://www.cs.unc.edu/-harrism/gpgpu.
• [18] CHRIS TRENDALL, A. JAMES STEWART, "General calculations using graphics hardware, with applications to interactive caustics," in Eurographics Workshop on Rendering, June 2000.
• [19] M. RUMPF, R. STRZODKA, "Using graphics cards for quantized FEM computations," in Proceedings VIIP'01, 2001, pp. 193-202.
• [20] MARK J. HARRIS, GREG COOMBE, THORSTEN SCHEUERMANN, ANSELMO LASTRA, "Physically based visual simulation on graphics hardware," in Proceedings of Graphics Hardware 2002, 2002, pp. 109-118.
• [21] NVIDIA Corporation, "Cg programming language, "http://developer.nvidia.com/view.asp?PAGE=cgmain,2002.