Automatic extraction of deformable part models
International Journal of Computer Vision
Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics
IEEE Transactions on Pattern Analysis and Machine Intelligence
Realistic modeling for facial animation
SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Frequency-Based Nonrigid Motion Analysis: Application to Four Dimensional Medical Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Synthesizing sounds from physically based motion
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Physics-Based Deformable Models: Applications to Computer Vision, Graphics, and Medical Imaging
Physics-Based Deformable Models: Applications to Computer Vision, Graphics, and Medical Imaging
Shape and Nonrigid Motion Estimation Through Physics-Based Synthesis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Physically-Based Combinations of Views: Representing Rigid and Nonrigid Motion
Physically-Based Combinations of Views: Representing Rigid and Nonrigid Motion
Monocular model-based 3D tracking of rigid objects
Foundations and Trends® in Computer Graphics and Vision
| Hi-index | 0.00 |
In this paper we develop highly flexible Timoshenko beam model for tracking large deformations in noisy data. We demonstrate that by neglecting some physical properties of Timoshenko beam, classical energy beam can be derived. The comparison of these two models in terms of their robustness and precision against noisy data is given. We demonstrate that Timoshenko beam model is more robust and precise for tracking large deformations in the presence of clutter and partial occlusions. The experiments using both synthetic and real image data are performed. In synthetic images we fit both models to noisy data and use Monte Carlo simulation to analyze their performance. In real images we track deformations of the pole vault, the rat whiskers and the car antenna.