PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Uncertainty Optimization for Robust Dynamic Optical Flow Estimation
Volker Willert, Marc Toussaint, Julian Eggert and Edgar Körner
In: The sixth Int Conf on Machine Learning and Applications (ICMLA 2007), Dec 2007, Cincinnati.


We develop an optical flow estimation framework that focuses on motion estimation over time formulated in a Dynamic Bayesian Network. It realizes a spatiotemporal integration of motion information using a dynamic and robust prior that incorporates spatial and temporal coherence constraints on the flow field. The main contribution is the embedding of these particular assumptions on optical flow evolution into the Bayesian propagation approach that leads to a computationally feasible Two-Filter inference method and is applicable for on- and offline parameter optimization. We analyse the possibility to optimize imposed Student’s t-distributed model uncertainties, which are the camera noise and the transition noise. Experiments with synthetic sequences illustrate how the probabilistic framework improves the optical flow estimation because it allows for noisy data, motion ambiguities and motion discontinuities.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:3870
Deposited By:Marc Toussaint
Deposited On:25 February 2008