ML Anthology

Object Tracking Using Affine Structure for Point Correspondences

Gurmeet Singh Manku, Pankaj Jain, Amit Aggarwal, Lalit Kumar, Subhashis Banerjee
CVPR 1997 pp. 704-709
doi:10.1109/CVPR.1997.609403 /cvpr/1997/manku1997cvpr-object/

Abstract

A new object tracking algorithm based on affine structure has been developed and it is shown that its performance is better than that of a Kalman filter based correlation tracker. The algorithm is fast, reliable, viewpoint invariant, and insensitive to occlusion and/or individual corner disappearance or reappearance. Detailed experimental analysis on a long real image sequence is also presented.

CVPR Semantic Scholar

Cite

Text

Manku et al. "Object Tracking Using Affine Structure for Point Correspondences." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609403

Markdown

[Manku et al. "Object Tracking Using Affine Structure for Point Correspondences." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/manku1997cvpr-object/) doi:10.1109/CVPR.1997.609403

BibTeX

@inproceedings{manku1997cvpr-object,
  title     = {{Object Tracking Using Affine Structure for Point Correspondences}},
  author    = {Manku, Gurmeet Singh and Jain, Pankaj and Aggarwal, Amit and Kumar, Lalit and Banerjee, Subhashis},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {704-709},
  doi       = {10.1109/CVPR.1997.609403},
  url       = {https://mlanthology.org/cvpr/1997/manku1997cvpr-object/}
}