Groups of Adjacent Contour Segments for Object Detection

Vittorio Ferrari 1 Loic Fevrier 1 Frédéric Jurie 1 Cordelia Schmid 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 : We present a family of scale-invariant local shape features formed by chains of k connected, roughly straight contour segments (kAS), and their use for object class detection. kAS are able to cleanly encode pure fragments of an object boundary, without including nearby clutter. Moreover, they offer an attractive compromise between information content and repeatability, and encompass a wide variety of local shape structures. We also define a translation and scale invariant descriptor encoding the geometric configuration of the segments within a kAS, making $k$AS easy to reuse in other frameworks, for example as a replacement or addition to interest points. We demonstrate the high performance of kAS within a simple but powerful sliding-window object detection scheme. Through extensive evaluations, involving eight diverse object classes and more than 1400 images, we 1) study the evolution of performance as the degree of feature complexity k varies and determine the best degree; 2) show that kAS substantially outperform interest points for detecting shape-based classes; 3) compare our object detector to the recent, state-of-the-art system by Dalal and Triggs.
Type de document :
Rapport
[Research Report] RR-5980, INRIA. 2006
Liste complète des métadonnées

https://hal.inria.fr/inria-00096663
Contributeur : Rapport de Recherche Inria <>
Soumis le : jeudi 21 septembre 2006 - 10:50:31
Dernière modification le : mercredi 6 juin 2018 - 01:22:32
Document(s) archivé(s) le : lundi 20 septembre 2010 - 17:00:26

Fichiers

Identifiants

  • HAL Id : inria-00096663, version 2

Collections

Citation

Vittorio Ferrari, Loic Fevrier, Frédéric Jurie, Cordelia Schmid. Groups of Adjacent Contour Segments for Object Detection. [Research Report] RR-5980, INRIA. 2006. 〈inria-00096663v2〉

Partager

Métriques

Consultations de la notice

656

Téléchargements de fichiers

586