Computation of Dense Optical Flow with a Parametric Smoothness Model

✍ Scribed by Navid Haddadi; C.-C.Jay Kuo

• Book ID: 102976361
• Publisher: Elsevier Science
• Year: 1993
• Tongue: English
• Weight: 888 KB
• Volume: 4
• Category: Article
• ISSN: 1047-3203
• DOI: 10.1006/jvci.1993.1029

✦ Synopsis

A new algorithm is presented for the computation of dense optical flow and motion boundaries from an image sequence using two or more frames. The algorithm is based on a novel parametric smoothness model; it decomposes optical flow into irrotational and solenoidal fields, and imposes the smoothness constraint on each field separately. This model implies smooth translation and rotation of the underlying motion process. In contrast, the smoothness constraints used in all previous work do not distinguish the translational and rotational components but simply combine them as a whole. The derivation of the parametric smoothness model sheds new light on the interpretation of the conventional membrane model. The problem of oversmoothing across motion boundaries can be resolved to a high degree by successively improving the estimate of the parameters of the smoothness model. Significant improvements over classical gradient based methods have been obtained for a class of test problems by the proposed new algorithm. O 1993 Academic Press, Inc.