Human Detection via Classification on Riemannian Manifolds
Lists
Only you see this
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.
BibTeX
@inproceedings{tuzel2007human,
author = {Oncel Tuzel and Fatih Porikli and Peter Meer},
title = {{Human Detection via Classification on Riemannian Manifolds}},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2007},
doi = {10.1109/cvpr.2007.383197},
}