ML Anthology

Spatiograms Versus Histograms for Region-Based Tracking

Stan Birchfield, Sriram Rangarajan
CVPR 2005 pp. 1158-1163
doi:10.1109/CVPR.2005.330 /cvpr/2005/birchfield2005cvpr-spatiograms/

Abstract

We introduce the concept of a spatiogram, which is a generalization of a histogram that includes potentially higher order moments. A histogram is a zeroth-order spatiogram, while second-order spatiograms contain spatial means and covariances for each histogram bin. This spatial information still allows quite general transformations, as in a histogram, but captures a richer description of the target to increase robustness in tracking. We show how to use spatiograms in kernel-based trackers, deriving a mean shift procedure in which individual pixels vote not only for the amount of shift but also for its direction. Experiments show improved tracking results compared with histograms, using both mean shift and exhaustive local search.

PDF CVPR Semantic Scholar

Cite

Text

Birchfield and Rangarajan. "Spatiograms Versus Histograms for Region-Based Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.330

Markdown

[Birchfield and Rangarajan. "Spatiograms Versus Histograms for Region-Based Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/birchfield2005cvpr-spatiograms/) doi:10.1109/CVPR.2005.330

BibTeX

@inproceedings{birchfield2005cvpr-spatiograms,
  title     = {{Spatiograms Versus Histograms for Region-Based Tracking}},
  author    = {Birchfield, Stan and Rangarajan, Sriram},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {1158-1163},
  doi       = {10.1109/CVPR.2005.330},
  url       = {https://mlanthology.org/cvpr/2005/birchfield2005cvpr-spatiograms/}
}