Rigid and Non-Rigid 3D Motion Estimation from Multiview Image Sequences

摘要: Multiview image sequence processing has been the focus of considerable attention in recent literature. This paper presents an efficient technique for object-based rigid and non-rigid 3D motion estimation, applicable to problems occurring multiview coding applications. More specifically, a neural network is formed estimation each object scene, using initially estimated 2D vectors corresponding camera view. Non-linear error minimization techniques are adopted weight update. Furthermore, novel also proposed local deformations, based on geometry. Experimental results both stereoscopic trinocular setups illustrate evaluate scheme.