Sciweavers

17 search results - page 3 / 4
» Robust 3D Segmentation of Multiple Moving Objects Under Weak...
Sort
View
ICCV
2009
IEEE
1136views Computer Vision» more  ICCV 2009»
14 years 10 months ago
Robust Graph-Cut Scene Segmentation and Reconstruction for Free-Viewpoint Video of Complex Dynamic Scenes
Current state-of-the-art image-based scene reconstruction techniques are capable of generating high-fidelity 3D models when used under controlled capture conditions. However, th...
Jean-Yves Guillemaut, Joe Kilner and Adrian Hilton
ICCS
2005
Springer
13 years 10 months ago
Towards a Bayesian Approach to Robust Finding Correspondences in Multiple View Geometry Environments
Abstract. This paper presents a new Bayesian approach to the problem of finding correspondences of moving objects in a multiple calibrated camera environment. Moving objects are d...
Cristian Canton-Ferrer, Josep R. Casas, Montse Par...
ICPR
2006
IEEE
14 years 6 months ago
Detection-Assisted Initialization, Adaptation and Fusion of Body Region Trackers for Robust Multiperson Tracking
In this paper, we present a system for simultaneous tracking of multiple persons in a smartroom using multiple cameras. Robust person tracks are created, continuously adapted, and...
Keni Bernardin, Alexander Elbs, Rainer Stiefelhage...
SSIAI
2000
IEEE
13 years 9 months ago
A New Bayesian Relaxation Framework for the Estimation and Segmentation of Multiple Motions
In this paper we propose a new probabilistic relaxation framework to perform robust multiple motion estimation and segmentation from a sequence of images. Our approach uses displa...
Alexander Strehl, Jake K. Aggarwal
PAMI
2007
187views more  PAMI 2007»
13 years 4 months ago
Detecting Motion Regions in the Presence of a Strong Parallax from a Moving Camera by Multiview Geometric Constraints
—We present a method for detecting motion regions in video sequences observed by a moving camera in the presence of a strong parallax due to static 3D structures. The proposed me...
Chang Yuan, Gérard G. Medioni, Jinman Kang,...