Human Detection Using Oriented Histograms of Flow and Appearance

Navneet Dalal 1 Bill Triggs 1 Cordelia Schmid 1, *
* Auteur correspondant
1 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 : Detecting humans in films and videos is a challenging problem owing to the motion of the subjects, the camera and the background and to variations in pose, appearance, clothing, illumination and background clutter. We develop a detector for standing and moving people in videos with possibly moving cameras and backgrounds, testing several different motion coding schemes and showing empirically that orientated histograms of differential optical flow give the best overall performance. These motion-based descriptors are combined with our Histogram of Oriented Gradient appearance descriptors. The resulting detector is tested on several databases including a challenging test set taken from feature films and containing wide ranges of pose, motion and background variations, including moving cameras and backgrounds. We validate our results on two challenging test sets containing more than 4400 human examples. The combined detector reduces the false alarm rate by a factor of 10 relative to the best appearance-based detector, for example giving false alarm rates of 1 per 20,000 windows tested at 8% miss rate on our Test Set 1.
Type de document :
Communication dans un congrès
Ales Leonardis and Horst Bischof and Axel Pinz. European Conference on Computer Vision (ECCV '06), May 2006, Graz, Austria. Springer-Verlag, 3952, pp.428--441, 2006, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/13w8520tp9088761/〉. 〈10.1007/11744047_33〉
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548587
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:49:35
Dernière modification le : mercredi 11 avril 2018 - 01:53:08
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:21:37

Fichier

DTS06.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Navneet Dalal, Bill Triggs, Cordelia Schmid. Human Detection Using Oriented Histograms of Flow and Appearance. Ales Leonardis and Horst Bischof and Axel Pinz. European Conference on Computer Vision (ECCV '06), May 2006, Graz, Austria. Springer-Verlag, 3952, pp.428--441, 2006, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/13w8520tp9088761/〉. 〈10.1007/11744047_33〉. 〈inria-00548587〉

Partager

Métriques

Consultations de la notice

1572

Téléchargements de fichiers

4495