Probabilistic Exploitation of the Lucas and Kanade Smoothness Constraint

The basic idea of Lucas and Kanade is to constrain the local motion measurement by assuming a constant velocity within a spatial neighborhood. We reformulate this spatial constraint in a probabilistic way assuming Gaussian distributed uncertainty in spatial identification of velocity measurements and extend this idea to scale and time dimensions. Thus, we are able to combine uncertain velocity measurements observed at different image scales and positions over time. We arrive at a new recurrent optical flow filter formulated in a Dynamic Bayesian Network applying suitable factorisation assumptions and approximate infer

• Type: Conference
• Year: 2008
• Where: ICMLA
• Authors: Volker Willert, Julian Eggert, Marc Toussaint, Edgar Körner
• Keywords: ICMLA 2008, Machine Learning, Spatial, Uncertain Velocity Measurements, Velocity Measurements