Model-Based Joint Motion and Structure Estimation from Stereo Images

摘要: In this paper we integrate motion and structure estimation in order to exploit their coherence. We propose an algorithm that uses models for object surfaces estimates the model parameters using image intensity matching criterion. The visible scene surface is represented with a parametrically deformable, spatially adaptive, wireframe model. Object first modeled well-known rigid assumption along quaternion rotation representation. Nonrigid modeling finite element technique also investigated as alternative or refinement of it. A functional containing smoothness constraints minimized respect unknown parameters. discontinuity detection scheme allowing deactivation across boundaries, investigated. regularization coarse fine strategy employed.