Mutual Information-Based 3D Object Tracking

Abstract We propose a robust methodology for 3D modelbased markerless tracking of textured objects in monocular image sequences. The technique is based on mutual information maximization, a widely known criterion for multimodal image registration, and employs an efficient multiresolution strategy in order to achieve robustness while keeping fast computational time, thus achieving near real-time performance for visual tracking of complex textured surfaces. Keywords Surface-image alignment

• Type: Journal
• Year: 2008
• Where: IJCV
• Authors: Giorgio Panin, Alois Knoll
• Keywords: IJCV 2006, IJCV 2008, Monocular Image Sequences, Mutual Information, Mutual Information Maximization