報告摘要：
The segmentation of foreground objects in camera images is a fundamental step in many computer vision applications. For visual effect creation, the foreground segmentation is required for the integration of virtual objects between scene elements. On the other hand, camera and scene estimation is needed to integrate the virtual objects perspectively correct into the video.
We present the different steps of structure and motion discovery. Precise feature detection, discontinued feature tracks and occlusion detection will be covered in detail. The combination of optical flow for features in consecutive frames and feature point matching for the wide baseline feature connection provides accurate and stable feature tracking. The knowledge of occluded parts of a connected feature track is used to feed an efficient segmentation algorithm which crops the foreground image regions automatically. The presented graph cut based segmentation uses a graph contraction technique to minimize the computational expense. The presented application in the integration of virtual objects into video. For this application, the accurate estimation of camera and scene is crucial. The segmentation is used for the automatic occlusion of the integrated objects with foreground scene content.
報告人簡介：
Jörn Ostermann studied Electrical Engineering and Communications Engineering at the University of Hannover and Imperial College London, respectively. He received Dipl.-Ing. and Dr.-Ing. from the University of Hannover in 1988 and 1994, respectively. In 1994 and 1995 he worked at AT&T Bell Labs. He was with AT&T Labs - Research from 1996 to 2003. Since 2003 he is Full Professor and Head of the Institut für Informationsverarbeitung at the Leibniz Universität Hannover, Germany.
His current research interests are video coding and streaming, 3D modelling, face animation, and computer-human interfaces.
