Multi-class Classification on Riemannian manifolds for Video Surveillance

Mauro Spera, Diego Tosato, Michela Farenzena, Marco Cristani, Vittorio Murino

Risultato della ricerca: Contributo in libroChapter

49 Citazioni (Scopus)

Abstract

In video surveillance, classication of visual data can be very hard, due to the scarce resolution and the noise characterizing the sensors' data. In this paper, we propose a novel feature, the ARray of COvariances (ARCO), and a multi-class classifcation framework operatingon Riemannian manifolds. ARCO is composed by a structure of covariance matrices of image features, able to extract information from data at prohibitive low resolutions. The proposed classication framework consists in instantiating a new multi-class boosting method, working on the manifold Sym+ of symmetric positive defnite d x d (covariance) matrices. As practical applications, we consider different surveillance tasks, such as head pose classifcation and pedestrian detection, providing novel state-of-the-art performances on standard datasets.
Lingua originaleEnglish
Titolo della pubblicazione ospiteComputer Vision - ECCV 2010
Pagine378-391
Numero di pagine14
Volume6312
Stato di pubblicazionePubblicato - 2010

Serie di pubblicazioni

NomeLECTURE NOTES IN COMPUTER SCIENCE

Keywords

  • Riemannian Manifolds, Video Surveillance, Multi-class Boosting, Head Pose Estimation, Pedestrian Detection

Fingerprint

Entra nei temi di ricerca di 'Multi-class Classification on Riemannian manifolds for Video Surveillance'. Insieme formano una fingerprint unica.

Cita questo