Accurate Object Detection with Deformable Shape Models Learnt from Images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Accurate Object Detection with Deformable Shape Models Learnt from Images

Vittorio Ferrari
  • Fonction : Auteur
  • PersonId : 835170
Frédéric Jurie
Cordelia Schmid
  • Fonction : Auteur
  • PersonId : 831154

Résumé

We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the accurate boundaries of the objects, rather than just their bounding-boxes. This is made possible by 1) a novel technique for learning a shape model of an object class given images of example instances; 2) the combination of Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately, while needing no segmented examples for training (only bounding-boxes).
Fichier principal
Vignette du fichier
FJS07.pdf (4.06 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-00203920 , version 1 (21-01-2008)

Identifiants

Citer

Vittorio Ferrari, Frédéric Jurie, Cordelia Schmid. Accurate Object Detection with Deformable Shape Models Learnt from Images. CVPR 2007 - Conference on Computer Vision and Pattern Recognition, Jun 2007, Minneapolis, United States. pp.1-8, ⟨10.1109/CVPR.2007.383043⟩. ⟨hal-00203920⟩
266 Consultations
655 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More