ML Anthology

On-Line Simultaneous Learning and Tracking of Visual Feature Graphs

Arnaud Declercq, Justus H. Piater
CVPR 2007
doi:10.1109/CVPR.2007.383435 /cvpr/2007/declercq2007cvpr-line/

Abstract

Model learning and tracking are two important topics in computer vision. While there are many applications where one of them is used to support the other, there are currently only few where both aid each other simultaneously. In this work, we seek to incrementally learn a graphical model from tracking and to simultaneously use whatever has been learned to improve the tracking in the next frames. The main problem encountered in this situation is that the current intermediate model may be inconsistent with future observations, creating a bias in the tracking results. We propose an uncertain model that explicitly accounts for such uncertainties by representing relations by an appropriately weighted sum of informative (parametric) and uninformative (uniform) components. The method is completely unsupervised and operates in real time.

CVPR Semantic Scholar

Cite

Text

Declercq and Piater. "On-Line Simultaneous Learning and Tracking of Visual Feature Graphs." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383435

Markdown

[Declercq and Piater. "On-Line Simultaneous Learning and Tracking of Visual Feature Graphs." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/declercq2007cvpr-line/) doi:10.1109/CVPR.2007.383435

BibTeX

@inproceedings{declercq2007cvpr-line,
  title     = {{On-Line Simultaneous Learning and Tracking of Visual Feature Graphs}},
  author    = {Declercq, Arnaud and Piater, Justus H.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383435},
  url       = {https://mlanthology.org/cvpr/2007/declercq2007cvpr-line/}
}