Learn to Track Edges

Yanghai Tsin, Yakup Genc, Ying Zhu, Visvanathan Ramesh

ICCV 2007 pp. 1-8

doi:10.1109/ICCV.2007.4409037 /iccv/2007/tsin2007iccv-learn/

Abstract

Reliability of a model-based edge tracker critically depends on its ability to establish correct correspondences between points on the model edges and edge pixels in an image. This is a non-trivial problem especially in the presence of large inter-frame motions and in cluttered environments. We propose an online learning approach to solving this problem. An edge pixel is represented by a descriptor composed of a small segment of intensity patterns. From training examples the algorithm utilizes the randomized forest model to learn a posteriori distribution of correspondence given the descriptor. In a new frame, the edge pixels are classified using maximum a posteriori (MAP) estimation. The proposed method is very powerful and it enables us to apply the proposed tracker to many previously impossible scenarios with unprecedented robustness.

ICCV Semantic Scholar

Cite

Text

Tsin et al. "Learn to Track Edges." IEEE/CVF International Conference on Computer Vision, 2007. doi:10.1109/ICCV.2007.4409037

Markdown

[Tsin et al. "Learn to Track Edges." IEEE/CVF International Conference on Computer Vision, 2007.](https://mlanthology.org/iccv/2007/tsin2007iccv-learn/) doi:10.1109/ICCV.2007.4409037

BibTeX

@inproceedings{tsin2007iccv-learn,
  title     = {{Learn to Track Edges}},
  author    = {Tsin, Yanghai and Genc, Yakup and Zhu, Ying and Ramesh, Visvanathan},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2007},
  pages     = {1-8},
  doi       = {10.1109/ICCV.2007.4409037},
  url       = {https://mlanthology.org/iccv/2007/tsin2007iccv-learn/}
}