Independent 3D Motion Detection Using Residual Parallax Normal Flow Fields

This paper considers a speci c problem of visual perception of motion, namely the problem of visual detection of independent 3D motion. Most of the existing techniques for solving this problem rely on restrictive assumptions about the environment, the observer's motion, or both. Moreover, they are based on the computation of a dense optical ow eld, which amounts to solving the illposed correspondence problem. In this work, independent motion detection is formulated as a problem of robust parameter estimation applied to the visual input acquired by a rigidly moving observer. The proposed method automatically selects a planar surface in the scene and the residual planar parallax normal ow eld with respect to the motion of this surface is computed at two successive time instants. The two resulting normal ow elds are then combined in a linear model. The parameters of this model are related to the parameters of self-motion (egomotion) and their robust estimation leads to a segmentation of the scene based on 3D motion. The method avoids a complete solution to the correspondence problem by selectively matching subsets of image points and by employing normal ow elds. Experimental results demonstrate the e ectiveness of the proposed method in detecting independent motion in scenes with large depth variations and unrestricted observer motion.