Human Detection via Classification on Riemannian Manifolds

@article{Tuzel2007HumanDV,
  title={Human Detection via Classification on Riemannian Manifolds},
  author={Oncel Tuzel and Fatih Murat Porikli and Peter Meer},
  journal={2007 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2007},
  pages={1-8}
}
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… CONTINUE READING

Figures and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 375 CITATIONS, ESTIMATED 26% COVERAGE

Discriminative local binary patterns for human detection in personal album

  • 2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
VIEW 15 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Pedestrian detection based on multifractal analysis

  • 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA)
  • 2017
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Optimized Cascade of Classifiers for People Detection using Covariance Features

VIEW 15 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

EC720 PROJECT, FINAL REPORT: VIDEO ANALYTICS IN A RETAIL ENVIRONMENT

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Fast and Accurate Human Detection Using a Cascade of Boosted MS-LBP Features

  • IEEE Signal Processing Letters
  • 2012
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Fast human detection from joint appearance and foreground feature subset covariances

  • Computer Vision and Image Understanding
  • 2011
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Gabor-Based RCM Features for Ear Recognition

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Comprehensive Evaluation Framework and a Comparative Study for Human Detectors

  • IEEE Transactions on Intelligent Transportation Systems
  • 2009
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2007
2019

CITATION STATISTICS

  • 47 Highly Influenced Citations

  • Averaged 17 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

Fast Human Detection Using a Cascade of Histograms of Oriented Gradients

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Histograms of oriented gradients for human detection

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Affine Invariance Revisited

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 1 EXCERPT

Covariance Tracking using Model Update Based on Lie Algebra

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 1 EXCERPT

Incremental learning of object detectors using a visual shape alphabet

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 1 EXCERPT

Multiple Object Class Detection with a Generative Model

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 1 EXCERPT

Nonlinear Mean Shift for Clustering over Analytic Manifolds

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 1 EXCERPT

A Riemannian Framework for Tensor Computing

  • International Journal of Computer Vision
  • 2005
VIEW 2 EXCERPTS

Pedestrian detection in crowded scenes

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…