A modified variational functional for estimating dense and discontinuity preserving optical flow in various spectrum

Variational methods are among the most successful approaches in the estimation of optical flow between two images. This paper presents a variational energy functional that incorporates the global model of Horn and Schunck (1981) and the classical model of Nagel and Enkelmann (1986) as a new regularization functional. In particular, the objective of this paper is to combine the advantages of both these models. This formulation yields a dense optical flow, preserves discontinuities in the flow field, and provides a significant robustness against outliers (occlusions, illumination changes and noise). The proposed variational functional is solved by an efficient numerical scheme. Stability and convergence analysis are given in order to show the mathematical applicability of the proposed model. Experimental results on different datasets verify the robustness and accuracy of the proposed model.