ML Anthology

Multifeature Object Tracking Using a Model-Free Approach

Hieu Tat Nguyen, Marcel Worring
CVPR 2000 pp. 1145-1150
doi:10.1109/CVPR.2000.855812 /cvpr/2000/nguyen2000cvpr-multifeature/

Abstract

In this paper we introduce a new model-free method for object tracking. The tracking is posed as a segmentation problem which we solve using the watershed algorithm. A framework is defined to compute the required topographic surface from distances to the predicted contour intensity, edges and motion edges. This multifeature tracking approach yields accurate results in the presence of object corners, image clutter and camera motion. Results on real sequences confirm the stability and robustness of the method. Objects are tracked over long sequences and in the presence of fast object motion.

CVPR Semantic Scholar

Cite

Text

Nguyen and Worring. "Multifeature Object Tracking Using a Model-Free Approach." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.855812

Markdown

[Nguyen and Worring. "Multifeature Object Tracking Using a Model-Free Approach." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/nguyen2000cvpr-multifeature/) doi:10.1109/CVPR.2000.855812

BibTeX

@inproceedings{nguyen2000cvpr-multifeature,
  title     = {{Multifeature Object Tracking Using a Model-Free Approach}},
  author    = {Nguyen, Hieu Tat and Worring, Marcel},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {1145-1150},
  doi       = {10.1109/CVPR.2000.855812},
  url       = {https://mlanthology.org/cvpr/2000/nguyen2000cvpr-multifeature/}
}