Human detection based on a probabilistic assembly of robust part detectors

Krystian Mikolajczyk 1 Cordelia Schmid 2, * Andrew Zisserman 3
* Auteur correspondant
2 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : 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.
Type de document :
Communication dans un congrès
Tomás Pajdla and Jiri Matas. European Conference on Computer Vision (ECCV '04), May 2004, Prague, Czech Republic. Springer-Verlag, I, pp.69--82, 2004, 〈http://springerlink.metapress.com/content/j576cjbqmc4dqyug/〉. 〈10.1007/978-3-540-24670-1_6〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00548537
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:09:30
Dernière modification le : mercredi 11 avril 2018 - 01:55:11
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:11:48

Fichier

miko_eccv2004.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Krystian Mikolajczyk, Cordelia Schmid, Andrew Zisserman. Human detection based on a probabilistic assembly of robust part detectors. Tomás Pajdla and Jiri Matas. European Conference on Computer Vision (ECCV '04), May 2004, Prague, Czech Republic. Springer-Verlag, I, pp.69--82, 2004, 〈http://springerlink.metapress.com/content/j576cjbqmc4dqyug/〉. 〈10.1007/978-3-540-24670-1_6〉. 〈inria-00548537〉

Partager

Métriques

Consultations de la notice

513

Téléchargements de fichiers

962