Using 3D Spline Differentiation to Compute Quantitative Optical Flow

We show that differentiation via fitting B-splines to the spatio-temporal intensity data comprising an image sequence provides at least the same and usually better 2D Lucas and Kanade optical flow than that computed via Simoncelli's balanced/matched filters.

• Type: Conference
• Year: 2006
• Where: CRV
• Authors: John L. Barron, Marc Daniel, Jean-Luc Mari
• Keywords: Better 2d Lucas, CRV 2006, Fitting B-splines, Robotics, Spatio-temporal Intensity Data