MRF Solutions for Probabilistic Optical Flow Formulations

In this paper we propose an efficient, non-iterative method for estimating optical flow. We develop a probabilistic framework that is appropriate for describing the inherent uncertainty in the brightness constraint due to errors in image derivative computation. We separate the flow into two one-dimensional representations and pose the problem of flow estimation as one of solving for the most probable configuration of one-dimensional labels in an Markov Random Fields (MRF) with linear clique potentials. The global optimum for this problem can be efficiently solved for using the maxflow computation in a graph. We develop this formulation and describe how the use of the probabilistic framework, the parametrisation and the MRF formulation together enables us to capture the desirable properties for flow estimation, especially preserving motion discontinuities. We demonstrate the performance of our algorithm and compare our results with that of other algorithms described in the performance ...

• Type: Conference
• Year: 2000
• Where: ICPR
• Authors: Sébastien Roy, Venu Govindu
• Keywords: Computer Vision, Flow Estimation, ICPR 2000, Image Derivative Computation, Probabilistic Framework