Structure Preserving Object Tracking

CVPR 2013

doi:10.1109/CVPR.2013.240 /cvpr/2013/zhang2013cvpr-structure/

Abstract

Model-free trackers can track arbitrary objects based on a single (bounding-box) annotation of the object. Whilst the performance of model-free trackers has recently improved significantly, simultaneously tracking multiple objects with similar appearance remains very hard. In this paper, we propose a new multi-object model-free tracker (based on tracking-by-detection) that resolves this problem by incorporating spatial constraints between the objects. The spatial constraints are learned along with the object detectors using an online structured SVM algorithm. The experimental evaluation of our structure-preserving object tracker (SPOT) reveals significant performance improvements in multi-object tracking. We also show that SPOT can improve the performance of single-object trackers by simultaneously tracking different parts of the object.

PDF CVPR Semantic Scholar

Cite

Text

Zhang and van der Maaten. "Structure Preserving Object Tracking." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.240

Markdown

[Zhang and van der Maaten. "Structure Preserving Object Tracking." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/zhang2013cvpr-structure/) doi:10.1109/CVPR.2013.240

BibTeX

@inproceedings{zhang2013cvpr-structure,
  title     = {{Structure Preserving Object Tracking}},
  author    = {Zhang, Lu and van der Maaten, Laurens},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.240},
  url       = {https://mlanthology.org/cvpr/2013/zhang2013cvpr-structure/}
}