ML Anthology

Incremental Focus of Attention for Robust Visual Tracking

Kentaro Toyama, Gregory D. Hager
CVPR 1996 pp. 189-195
doi:10.1109/CVPR.1996.517073 /cvpr/1996/toyama1996cvpr-incremental/

Abstract

We present the Incremental Focus of Attention (IFA) architecture for adding robustness to software-based, real-time, motion trackers. The framework provides a structure which, when given the entire camera image to search, efficiently focuses the attention of the system into a narrow set of possible slates that includes the target state. IFA offers a means for automatic tracking initialization and reinitialization when environmental conditions momentarily deteriorate and cause the system to lose track of its target. Systems based on the framework degrade gracefully as various assumptions about the environment are violated. In particular, multiple tracking algorithms are layered so that the failure of a single algorithm causes another algorithm of less precision to take over, thereby allowing the system to return approximate feature state information.

CVPR Semantic Scholar

Cite

Text

Toyama and Hager. "Incremental Focus of Attention for Robust Visual Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517073

Markdown

[Toyama and Hager. "Incremental Focus of Attention for Robust Visual Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/toyama1996cvpr-incremental/) doi:10.1109/CVPR.1996.517073

BibTeX

@inproceedings{toyama1996cvpr-incremental,
  title     = {{Incremental Focus of Attention for Robust Visual Tracking}},
  author    = {Toyama, Kentaro and Hager, Gregory D.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {189-195},
  doi       = {10.1109/CVPR.1996.517073},
  url       = {https://mlanthology.org/cvpr/1996/toyama1996cvpr-incremental/}
}