vers le site de l'ENS
Lien vers l'accueil
lancer la recherche

» Conférences d’après mars 2011 : nouveau site


Séminaire Vision artificielle / Équipe Willow

< précédent | suivant >

Detecting people in images and videos and reconstructing their movements
Bill Triggs (INRIA-univ. Grenoble)

16 novembre 2005

Detecting humans in images is a challenging task owing to their variable appearance and the wide range of poses that they can adopt. I will present detectors for upright humans in static images and in videos. The detectors use a linear SVM classifier over a robust visual feature set based on well normalized local histograms of image gradient orientations. The video detector also incorporates oriented histograms of differential optical flow to capture cues for human motion despite moving cameras and backgrounds.
In the second part of the talk, I will give an overview of some of our work on reconstructing human body motions from monocular image sequences. We avoid using an explicit 3-D body model, instead taking a learning based approach that directly regresses 3-D pose (joint angles) from robust shape descriptors extracted from image silhouettes. A kernelized Relevance Vector Machine is used for regression. Ambiguities in the silhouette representation cause occasional failures and we present two methods to correct this: incorporating a learned dynamical model, and using multi-valued regression to generate several reconstruction hypotheses along with their associated probabilities of being correct.
Work done with my students Navneet Dalal and Ankur Agarwal.

pictogrammeformat audio mp3 - ??? (erreur acces)

- Visualiser
- Télécharger
pictogrammeformat quicktime mov, haut débit, streaming / diffusion en ligne

pictogrammeformat mp4, vidéo à télécharger - ??? (erreur acces)

Bill Triggs Bill Triggs (INRIA-univ. Grenoble)