Discontinuity Preserving in TV-L1 Optical Flow Methods

Authors: Monzón López, Nelson; Salgado de la Nuez, Agustín J.; Sánchez Pérez, Javier
Line of Research: Optical flow
Year: 2014
Type of Publication: Technical Report
Keywords: Optical Flow, Total Variation, TV-L1 , Variational Method, Diffusion Process
Journal: CTIM Technical Report
Institution: Universidad de Las Palmas de Gran Canaria
Number: 5
ISSN: 2254-2353
Month: November
We analyze the discontinuity preserving problem in TV-L1 optical flow methods. This type of methods typically creates rounded effects at flow boundaries, which usually do not coincide with object contours. A simple strategy to overcome this problem consists in inhibiting the diffusion at high image gradients. In this work, we first introduce a general framework for TV regularizers in optical flow and relate it with some standard approaches. Our survey takes into account several methods that use decreasing functions for mitigating the diffusion at image contours. Consequently, this kind of strategies may produce instabilities in the estimation of the optical flows. Hence, we study the problem of instabilities and show that it actually arises from an ill-posed formulation. From this study, it is possible to come across with different schemes to solve this problem. One of these consists in separating the pure TV process from the mitigating strategy. This has been used in another work and we demonstrate here that it has a good performance. Furthermore, we propose two alternatives to avoid the instability problems: (i) we study a fully automatic approach that solves the problem based on the information of the whole image; (ii) we derive a semi-automatic approach that takes into account the image gradients in a close neighborhood adapting the parameter in each position. In the experimental results, we present a detailed study and comparison between the different alternatives. These methods provide very good results, especially for sequences with a few dominant gradients. Additionally, a surprising effect of these approaches is that they can cope with occlusions. This can be easily achieved by using strong regularizations and high penalizations at image contours.
Full text: CTIM_5_2014.pdf