We propose a fast texture-segmentation approach to the problem of 2D and 3D model-based contour tracking, which is suitable for real-time or interactive applications. Our approach relies on detecting texture boundaries in the direction normal to the contour boundaries and on using a hidden Markov model to link these boundary points in the other direction. The probabilities that appear in this computation closely relate to texture entropy and Kullback-Leibler divergence, a property we use to compute and update dynamic texture models. We demonstrate results both in the context of interactive 2D delineation and fast 3D tracking.
Fast texture-based tracking and delineation using texture entropy
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 2 ; 1154-1160 Vol. 2
2005-01-01
1303658 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Fast Texture-Based Tracking and Delineation Using Texture Entropy
British Library Conference Proceedings | 2005
|Multi-modal tracking using texture changes
British Library Online Contents | 2008
|Robust Tracking Using Foreground-Background Texture Discrimination
British Library Online Contents | 2006
|3D Head Tracking Using Motion Adaptive Texture-Mapping
British Library Conference Proceedings | 2001
|