Un Nuevo Algoritmo para el Cálculo de Flujo Óptico y su Aplicación al Registro de Imágenes
A New Algorithm for Computing Optical Flow and His Application to Image Registration
Félix Calderón Solorio1 y José Luis Marroquín Zaleta2
1 División de Estudios de Posgrado, Facultad de Ingeniería Eléctrica Universidad Michoacana de San Nicolás Hidalgo Santiago Tapia 403, Col. Centro. E–mail: calderon@zeus.umich.mx
2 Centro de Investigación en Matemáticas Callejón Jalisco s/n, Mineral de Valenciana, Guanajuato, México. E–mail: jlm@cimat.mx
]]>Artículo recibido en Agosto 22. 2001
Aceptado en Marzo 15. 2003
Resumen
Presentamos un algoritmo novedoso para el cálculo de flujo óptico basado en la suma de diferencias al cuadrado de puntos correspondientes, con un término de relajación que permite eliminar observaciones erróneas. Este algoritmo solamente necesita información de un par de cuadros y es robusto en presencia de ruido. Se presenta también su aplicación en registro de imágenes cerebrales de resonancia magnética, con información de atlas cerebrales para realizar la segmentación cerebro / no–cerebro de un espécimen dado.
Palabras Clave: Flujo Óptico FO, Registro de Imágenes RI e Imágenes de Resonancia Magnética IRM.
Abstract
We present a new algorithm for computing the optical Flow which is based in the sum of squared difference between two points and we add a rest condition in order to eliminate outliers. This algorithm only needs a couple o frames and is very robust in presence of noise. We present his application in the register task of Magnetic Resonance Images of human heads with brain atlas in order to do the head segmentation in brain and no brain.
]]> Keywords: Optical Flow OF, Image Registration IR and Magnetic Resonance Images MRI.
DESCARGAR ARTÍCULO EN FORMATO PDF
Agradecimientos
Este trabajo fue financiado en parte por el Consejo Nacional de Ciencia y Tecnología (CONACyT, México), Felix Calderón fue financiado por la beca 119039 y José Luis Marroquín por el proyecto 34575–A Las imágenes de la figura 9 fueron proporcionadas por el Dr. B. C. Vemuri.
Bibliografía
Adelson, E. H. & Bergen, J. R., 1986. The extraction of spatiotemporal energy in human and machine vision. Proc. IEEE Workshop on Visual Motion, Charleston, pp. 151—156. [ Links ]
Anadan, P., 1989. A computational framework and an algorithm for the measurement of visual motion. Intern. J. Comput., 2, 283—310. [ Links ]
Bab–Hadiashar, A. & Suter, D., 1996.Robust optic flow estimation using least median of squares. IEEE International Conference on Image Processing ICIP96. [ Links ]
Barman, H., Haglund, L., Knutsson, H., & Granlund, G, 1991. Estimation of velocity, acceleration and disparity in time sequences. Proc. IEEE Workshop on Visual Motion, Princeton, pp. 44—51. [ Links ]
Barron, J. L., Fleet, D. J., & Beauchemin, S. S., 1994. Performance of optical flow techniques. International Journal of Computer Vision, 12:1, 43—77. [ Links ]
Bigun, J., Grandlund, G., & Wiklund, J., 1991. Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Trans. Patt. Anal. Mach. 13, 775—790. [ Links ]
Burt, P. J., Yen, C, & Xu, X., 1983. Multiresolution flow–through motion analysis. Proc. Conf. Comput. Vis. Patt. Recog, pp. 246—252. [ Links ]
Dennis, J.E. & Schnabel, R.B., (1996). Numerical Methods for Unconstrained Optimization and Nonlinear Equiations. Philadelphia: Society for Industrial and Applied Mathematics, siam. Métodos de Newton en gral. [ Links ]
Fennema, C. & Thompson, W., 1979. Velocity determination in scenes containing several moving objects. Comput. Graph. Image Process, 9, 301—315. [ Links ]
Fleet, D.J., 1992 Measurement of image velocity. Kluwer Academic Publishers: Norwell, MA. [ Links ]
Gill, P. E., Murray, W., & Wright, M. H., 1981. Practical Optimization. London, New York: Academic Press. [ Links ]
Glazer,F., Reynolds, G,& Añadan, P., 1983. Scene matching through hierarchical correlation. Proc. Conf. Comput. Vis. Patt, Recog., pp. 432—411. [ Links ]
Haglund, L., 1992. Adaptive Multidimensional Filtering. PhD thesis, Dept. Electrical Engineering Univ. of Linkoping. [ Links ]
Hearn, D. & Baker, M. P., 1997. Computer Graphics C Version. Simon and Schuster/A Viacom Upper Saddle River, New Jersey 07458: Prentice Hall, Inc., second edition. [ Links ]
Heeger, D.J., 1987. Model for the extraction of image flow. J. Opt. Soc. Am. A, 4, 1455—1471. [ Links ]
Horn, B. K. P., 1986. Robot Vision. Cambridge, Massachusetts: MIT Press, second edition. Chapter 12. [ Links ]
Jahne, B. ,1987. Image secuence analysis of complex physical objects: Nonlinear small water surface waves. Proc. 1st Intern. Conf. Comput.Vis. London, pp. 191—200. [ Links ]
Jahne, B., 1997. Digital Image Processing. Concepts, Algorithms and Scientific Applications. Berlin Heidelberg: Springer–Verlang. [ Links ]
Kelley, C. T., 1995. Iterative Methods for Linear and Nonlinear Equations, volume 16. Philadelphia. USA: Society for Industrial and Applied Mathematics. SIAM. Iteración de Richarson. [ Links ]
Lai, S.–H. & Vemuri, B.C., 1998. Reliable and efficient computation of optical flow. International Journal of Computer Vision, 29(2), 87—105. [ Links ]
Little, J. J., Bulthoff, H. H., & Poggio, T.A., (1988). Parallel optical flow using local voting. Proc. 2nd Inter. Conf. Vis., pp. 454—459. [ Links ]
Little, J. J. & Verri, A., 1989. Analysis of differential and matching methods for optical flow. IEEE Workshop on Visual Motion, pp. 173—180. [ Links ]
Lucas, B. & Kanade, T., 1981. An iterative image registration technique with an application to stereo vision. Proc. DARPA Image Understanding Workshop, pp. 121 —130. [ Links ]
Nagel, H. H., 1983. Displacement vectors derived from second–order intensity variations in image sequences. Comput. Graph. Image Process, 21, 85—117. [ Links ]
Nagel, H. H., 1987. On the estimation of optical flow: Relations between different approaches and some new results. Artificial Intelligence, 33, 299—324. [ Links ]
Nesi, P., Bimbo, A. D., & Ben–Tzvi, D., 1995. A roboust algorithm for optical flow estimation. Computer Vision and Image Understanding, 62, 51—60. [ Links ]
Rivera, M. & Marroquín, J. L., 2000. The adaptive rest–condition spring system: An edge–preserving regularization techique. IEEE Int. Conf. on Image Processing (ICIP–2000), IEEE Signal Processing Society, Vancouver, BC, Canada, II, 805—807. [ Links ]
Romeny, B. M. T. H., 1994. Geometry–Driven Diffusion in Computer Vision. Dordrecht, The Netherlands: Kluwer Academic Publishers. [ Links ]
Rousseeuw, P. J., 1984. Least median of squares regression. Journal of the American Statistical Association, 79, 871—880. [ Links ]
Scales, L. E., 1984, Introduction to Non–Linear Optimization. Liverpool. UK: Department of Computer Science University of Liverpool. [ Links ]
Schunck, B. G., 1989. Image flow segmentation and estimation by constraint line clustering. IEEE Trans. Pattern Anal. Mack Intell., 11, 1010—1027. [ Links ]
Shi, J. & Tomasi, C, 1994. Good features to track. IEEE Conference on Computer Vision and Pattern Recognition CVPR94, pp 593—600. [ Links ]
Szeliski, R. & Coughlan, J., 1994. Spline–Based Image Registration. Technical Report 94/1, Harvard University, Department of Physics, Cambridge, Ma 02138. [ Links ]
Tomasi, C. & Kanade, T., 1991. Detection and Tracking of Point Features. Technical Report CMUS–CS–91–132, Carnegie Mellon University. [ Links ]
Tommasini, T., Fuiello, A., Trueco, E., & Roberto, V., 1998. Making good features track better. Computer Vision and Pattern Recognition CVPR, pp. 178—182. [ Links ]
Tretiak, O. & Pastor, L., 1984. Velocity estimation from image sequences with second order differential operators. Proc. 7th Intern. Conf. Patt. Recog. Montreal, pp. 20—22. [ Links ]
Uras, S., Girosi, F., Verri, A., & Torre, V., 1988. A computational approach to motion perception. Biol. Cybern, 60, 79—97. [ Links ] ]]>