Title :
Total variation regularization of local-global optical flow
Author :
Drulea, Marius ; Nedevschi, Sergiu
Abstract :
More data fidelity terms in variational optical flow methods improve the estimation´s robustness. A robust and anisotropic smoother enhances the specific fill-in process. This work presents a combined local-global (CLG) approach with total variation regularization. The combination of bilateral filtering and anisotropic (image driven) regularization is used to control the propagation phenomena. The resulted method, CLG-TV, is able to compute larger displacements in a reasonable time. The numerical scheme is highly parallelizable and runs in real-time on current generation graphic processing units.
Keywords :
coprocessors; image sequences; motion estimation; numerical analysis; smoothing methods; CLG optical flow approach; CLG-TV method; anisotropic regularization; anisotropic smoother; bilateral filtering; combined local-global optical flow approach; data fidelity terms; estimation robustness; fill-in process; graphic processing units; numerical scheme; total variation regularization; variational optical flow method; Computer vision; Image motion analysis; Mathematical model; Minimization; Optical filters; Optical imaging; Robustness;
Conference_Titel :
Intelligent Transportation Systems (ITSC), 2011 14th International IEEE Conference on
Conference_Location :
Washington, DC
Print_ISBN :
978-1-4577-2198-4
DOI :
10.1109/ITSC.2011.6082986