Sciweavers

Share
ICPR
2010
IEEE

A Re-evaluation of Pedestrian Detection on Riemannian Manifolds

8 years 8 months ago
A Re-evaluation of Pedestrian Detection on Riemannian Manifolds
Abstract--Boosting covariance data on Riemannian manifolds has proven to be a convenient strategy in a pedestrian detection context. In this paper we show that the detection performances of the state-of-the-art approach of Tuzel et al. [7] can be greatly improved, from both a computational and a qualitative point of view, by considering practical and theoretical issues, and allowing also the estimation of occlusions in a fine way. The resulting detection system reaches the best performance on the INRIA dataset, setting novel state-of-theart results. Keywords-Pedestrian Detection, Riemaniann Manifolds, Boosting In Computer Vision, detecting people in images is a crucial yet hard task; this is due to the presence of many acquisition settings and the large variations of human appearance and pose. Across the many nowadays techniques, whose recent samples are [6], [7], [8], the ensemble-offeatures based methods [3], [7] are very promising. They are based on boosting [4], which is reckoned t...
Diego Tosato, Michela Farenzena, Marco Cristani, V
Added 12 Feb 2011
Updated 12 Feb 2011
Type Journal
Year 2010
Where ICPR
Authors Diego Tosato, Michela Farenzena, Marco Cristani, Vittorio Murino
Comments (0)
books