Human detection based on a probabilistic assembly of robust part detectors - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2004

Human detection based on a probabilistic assembly of robust part detectors

Résumé

We describe a novel method for human detection in single images which can detect full bodies as well as close-up views in the presence of clutter and occlusion. Humans are modeled as flexible assemblies of parts, and robust part detection is the key to the approach. The parts are represented by co-occurrences of local features which captures the spatial layout of the partrsquos appearance. Feature selection and the part detectors are learnt from training images using AdaBoost. The detection algorithm is very efficient as (i) all part detectors use the same initial features, (ii) a coarse-to-fine cascade approach is used for part detection, (iii) a part assembly strategy reduces the number of spurious detections and the search space. The results outperform existing human detectors.
Fichier principal
Vignette du fichier
miko_eccv2004.pdf (443.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

inria-00548537 , version 1 (20-12-2010)

Identifiants

Citer

Krystian Mikolajczyk, Cordelia Schmid, Andrew Zisserman. Human detection based on a probabilistic assembly of robust part detectors. European Conference on Computer Vision (ECCV '04), May 2004, Prague, Czech Republic. pp.69--82, ⟨10.1007/978-3-540-24670-1_6⟩. ⟨inria-00548537⟩
333 Consultations
983 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More