ML Anthology

View-Based Adaptive Affine Tracking

Fernando De la Torre, Shaogang Gong, Stephen J. McKenna
ECCV 1998 pp. 828-842
doi:10.1007/BFB0055707 /eccv/1998/latorre1998eccv-view/

Abstract

We propose a model for view-based adaptive affine tracking of moving objects. We avoid the need for feature-based matching in establishing correspondences through learning landmarks. We use an effective bootstrapping process based on colour segmentation and selective attention. We recover affine parameters with dynamic updates to the eigenspace using most recent history and perform predictions in parameter space. Experimental results are given to illustrate our approach.

PDF ECCV Semantic Scholar

Cite

Text

De la Torre et al. "View-Based Adaptive Affine Tracking." European Conference on Computer Vision, 1998. doi:10.1007/BFB0055707

Markdown

[De la Torre et al. "View-Based Adaptive Affine Tracking." European Conference on Computer Vision, 1998.](https://mlanthology.org/eccv/1998/latorre1998eccv-view/) doi:10.1007/BFB0055707

BibTeX

@inproceedings{latorre1998eccv-view,
  title     = {{View-Based Adaptive Affine Tracking}},
  author    = {De la Torre, Fernando and Gong, Shaogang and McKenna, Stephen J.},
  booktitle = {European Conference on Computer Vision},
  year      = {1998},
  pages     = {828-842},
  doi       = {10.1007/BFB0055707},
  url       = {https://mlanthology.org/eccv/1998/latorre1998eccv-view/}
}