ML Anthology

Human Detection via Classification on Riemannian Manifolds

Oncel Tuzel, Fatih Porikli, Peter Meer
CVPR 2007
doi:10.1109/CVPR.2007.383197 /cvpr/2007/tuzel2007cvpr-human/

Abstract

We present a new algorithm to detect humans in still images utilizing covariance matrices as object descriptors. Since these descriptors do not lie on a vector space, well known machine learning techniques are not adequate to learn the classifiers. The space of d-dimensional nonsingular covariance matrices can be represented as a connected Riemannian manifold. We present a novel approach for classifying points lying on a Riemannian manifold by incorporating the a priori information about the geometry of the space. The algorithm is tested on INRIA human database where superior detection rates are observed over the previous approaches.

PDF CVPR Semantic Scholar

Cite

Text

Tuzel et al. "Human Detection via Classification on Riemannian Manifolds." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383197

Markdown

[Tuzel et al. "Human Detection via Classification on Riemannian Manifolds." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/tuzel2007cvpr-human/) doi:10.1109/CVPR.2007.383197

BibTeX

@inproceedings{tuzel2007cvpr-human,
  title     = {{Human Detection via Classification on Riemannian Manifolds}},
  author    = {Tuzel, Oncel and Porikli, Fatih and Meer, Peter},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383197},
  url       = {https://mlanthology.org/cvpr/2007/tuzel2007cvpr-human/}
}