Human Detection via Classification on Riemannian Manifolds
Top Cited Papers
- 1 June 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
- https://doi.org/10.1109/cvpr.2007.383197
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.Keywords
This publication has 20 references indexed in Scilit:
- Incremental learning of object detectors using a visual shape alphabetPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Fast Human Detection Using a Cascade of Histograms of Oriented GradientsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Covariance Tracking using Model Update Based on Lie AlgebraPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Multiple Object Class Detection with a Generative ModelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- A Riemannian Framework for Tensor ComputingInternational Journal of Computer Vision, 2006
- Pedestrian Detection in Crowded ScenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Simultaneous multiple 3D motion estimation via mode finding on Lie groupsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Detecting pedestrians using patterns of motion and appearancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Example-based object detection in images by componentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- A Trainable System for Object DetectionInternational Journal of Computer Vision, 2000