Physically-based motion models for 3D tracking: A convex formulation
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2064-2071
Abstract
In this paper, we propose a physically-based dynamical model for tracking. Our model relies on Newton's second law of motion, which governs any real-world dynamical system. As a consequence, it can be generally applied to very different tracking problems. Furthermore, since the equations describing Newton's second law are simple linear equalities, they can be incorporated in any tracking framework at very little cost. Leveraging this lets us introduce a convex formulation of 3D tracking from monocular images. We demonstrate the strengths of our approach on various types of motion, such as billiards and acrobatics.Keywords
This publication has 21 references indexed in Scilit:
- Physical simulation for probabilistic motion tracking2008
- Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical PriorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Gaussian Process Dynamical Models for Human MotionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Deformable Surface Tracking Ambiguities2007
- 3D People Tracking with Gaussian Process Dynamical Models2006
- Priors for people tracking from small training sets2005
- Robust online appearance models for visual trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Learning and classification of complex dynamicsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Physically based motion transformation1999
- Shape and nonrigid motion estimation through physics-based synthesisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993