Previous |  Up |  Next


MSC: 35L45, 65M25, 68U10
Optical flow, advection equation, level-set motion, characteristic curves
In this paper we describe two methods for optical flow estimation between two images. Both methods are based on the backward tracking of characteristics for advection equation and the difference is on the choice of advection vector field. We present numerical experiments on 2D data of cell nucleus.
[1] Bartalmı́o, M., Sapiro, G., Randall, G.: Morphing Active Contours. IEEE Trans. PAMI,22(7) (2000), pp. 733–737.
[2] Bruhn, A., Weickert, J., Schn\"orr, Ch.: Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow Methods. Int. Journal of Comp. Vision. 61(3) (2005), pp. 211-231. DOI 10.1023/B:VISI.0000045324.43199.43
[3] Horn, B., Schunck, B.: Determining optic flow. Artificial Intelligence, 17(1-3) (1981), pp. 185-203. DOI 10.1016/0004-3702(81)90024-2
[4] Kleinová, V.: Algoritmy extrakcie rýchlostného poľa z postupnosti obrazov. Diploma thesis, Faculty of Civil Engineering, Slovak University of Technology in Bratislava (2014).
[5] Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereovision. In Int. Joint Conf. on Artificial Intel, 2 (1981), pp. 674-679.
[6] Osher, S., Sethian, J.A.: Fronts Propagating with Curvature Dependent Speed: Algorithms Based on Hamilton-Jacobi Formulations. J. Computational Physics, 79 (1988), pp. 12-49. DOI 10.1016/0021-9991(88)90002-2 | MR 0965860
[7] LeVeque, R. J.: Finite Volume Methods for Hyperbolic Problems. Cambridge University Press, 1 (2002), ISBN: 0521009243. MR 1925043
[8] Rouy, E., Tourin, A.: A viscosity solutions approach to shape-from-shading. SIAM J. Num. Anal. 29 (1992), pp. 867-884. DOI 10.1137/0729053 | MR 1163361
[9] Vemuri, B.C., Ye, J., Chen, Y., Leonard, C.M.: Image registration via level-set motion: Applications to atlas-based segmentation. Medical Image Analysis, 7(1) (2003), pp. 1-20. DOI 10.1016/S1361-8415(02)00063-4
Partner of
EuDML logo