The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields

Abstract

Most approaches for estimating optical flow assume that, within a finite image region, only a single motion is present. Thissingle motion assumptionis violated in common situations involving transparency, depth discontinuities, independently moving objects, shadows, and specular reflections. To robustly estimate optical flow, the single motion assumption must be relaxed. This paper presents a framework based onrobust estimationthat addresses violations of the brightness constancy and spatial smoothness assumptions caused by multiple motions. We show how therobust estimation frameworkcan be applied to standard formulations of the optical flow problem thus reducing their sensitivity to violations of their underlying assumptions. The approach has been applied to three standard techniques for recovering optical flow: area-based regression, correlation, and regularization with motion discontinuities. This paper focuses on the recovery of multiple parametric motion models within a region, as well as the recovery of piecewise-smooth flow fields, and provides examples with natural and synthetic image sequences.