Part-based human detection on Riemannian manifolds

Diego Tosato, Michela Farenzena, Marco Cristani, Vittorio MurinoICIP 2010 · OpenReview

Abstract

In this paper we propose a novel part-based framework for pedestrian detection. We model a human as a hierarchy of fixed overlapped parts, each of which described by covariances of features. Each part is modeled by a boosted classifier, learnt using Logitboost on Riemannian manifolds. All the classifiers are then linked to form a high-level classifier, through weighted summation, whose weights are estimated during the learning. The final classifier is simple, light and robust. The experimental results show that we outperform the state-of-the-art human detection performances on the INRIA person dataset.
BibTeX
@inproceedings{tosato2010part,
  author = {Diego Tosato and Michela Farenzena and Marco Cristani and Vittorio Murino},
  title = {{Part-based human detection on Riemannian manifolds}},
  booktitle = {ICIP},
  year = {2010},
  url = {https://openreview.net/forum?id=PP_uZvrl6Nz},
}

Loading related content...

Figure