ML Anthology

Robust Object Trackinng Wvith Regional Affine Invariant Features

Son Dinh Tran, Larry S. Davis
ICCV 2007 pp. 1-8
doi:10.1109/ICCV.2007.4408948 /iccv/2007/tran2007iccv-robust/

Abstract

We present a tracking algorithm based on motion analysis of regional affine invariant image features. The tracked object is represented with a probabilistic occupancy map. Using this map as support, regional features are detected and probabilistically matched across frames. The motion of pixels is then established based on the feature motion. The object occupancy map is in turn updated according to the pixel motion consistency. We describe experiments to measure the sensitivities of our approach to inaccuracy in initialization, and compare it with other approaches.

ICCV Semantic Scholar

Cite

Text

Tran and Davis. "Robust Object Trackinng Wvith Regional Affine Invariant Features." IEEE/CVF International Conference on Computer Vision, 2007. doi:10.1109/ICCV.2007.4408948

Markdown

[Tran and Davis. "Robust Object Trackinng Wvith Regional Affine Invariant Features." IEEE/CVF International Conference on Computer Vision, 2007.](https://mlanthology.org/iccv/2007/tran2007iccv-robust/) doi:10.1109/ICCV.2007.4408948

BibTeX

@inproceedings{tran2007iccv-robust,
  title     = {{Robust Object Trackinng Wvith Regional Affine Invariant Features}},
  author    = {Tran, Son Dinh and Davis, Larry S.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2007},
  pages     = {1-8},
  doi       = {10.1109/ICCV.2007.4408948},
  url       = {https://mlanthology.org/iccv/2007/tran2007iccv-robust/}
}