A local basis representation for estimating human pose from cluttered images

Ankur Agarwal 1 Bill Triggs 1
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 : Recovering the pose of a person from single images is a challenging problem. This paper discusses a bottom-up approach that uses local image features to estimate human upper body pose from single images in cluttered backgrounds. The method takes the image window with a dense grid of local gradient orientation histograms, followed by non negative matrix factorization to learn a set of bases that correspond to local features on the human body, enabling selective encoding of human-like features in the presence of background clutter. Pose is then recovered by direct regression. This approach allows us to key on gradient patterns such as shoulder contours and bent elbows that are characteristic of humans and carry important pose information, unlike current regressive methods that either use weak limb detectors or require prior segmentation to work. The system is trained on a database of images with labelled poses. We show that it estimates pose with similar performance levels to current example-based methods, but unlike them it works in the presence of natural backgrounds, without any prior segmentation.
Type de document :
Communication dans un congrès
P. J. Narayanan and Shree K. Nayar and Heung-Yeung Shum. Asian Conference on Computer Vision (ACCV '06), Jan 2006, Hyderabad, India. Springer-Verlag, 3851, pp.50--59, 2006, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/p605657816802357/〉. 〈10.1007/11612032_6〉
Liste complète des métadonnées


https://hal.inria.fr/inria-00548593
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:49:45
Dernière modification le : mercredi 11 avril 2018 - 01:56:25
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:22:43

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Ankur Agarwal, Bill Triggs. A local basis representation for estimating human pose from cluttered images. P. J. Narayanan and Shree K. Nayar and Heung-Yeung Shum. Asian Conference on Computer Vision (ACCV '06), Jan 2006, Hyderabad, India. Springer-Verlag, 3851, pp.50--59, 2006, Lecture Notes in Computer Science (LNCS). 〈http://www.springerlink.com/content/p605657816802357/〉. 〈10.1007/11612032_6〉. 〈inria-00548593〉

Partager

Métriques

Consultations de la notice

386

Téléchargements de fichiers

497