ML Anthology

Fast Texture-Based Tracking and Delineation Using Texture Entropy

Ali Shahrokni, Tom Drummond, Pascal Fua
ICCV 2005 pp. 1154-1160
doi:10.1109/ICCV.2005.97 /iccv/2005/shahrokni2005iccv-fast/

Abstract

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

PDF ICCV Semantic Scholar

Cite

Text

Shahrokni et al. "Fast Texture-Based Tracking and Delineation Using Texture Entropy." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.97

Markdown

[Shahrokni et al. "Fast Texture-Based Tracking and Delineation Using Texture Entropy." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/shahrokni2005iccv-fast/) doi:10.1109/ICCV.2005.97

BibTeX

@inproceedings{shahrokni2005iccv-fast,
  title     = {{Fast Texture-Based Tracking and Delineation Using Texture Entropy}},
  author    = {Shahrokni, Ali and Drummond, Tom and Fua, Pascal},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1154-1160},
  doi       = {10.1109/ICCV.2005.97},
  url       = {https://mlanthology.org/iccv/2005/shahrokni2005iccv-fast/}
}