Groups of Adjacent Contour Segments for Object Detection - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2008

Groups of Adjacent Contour Segments for Object Detection

Résumé

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 kAS easy to reuse in other frameworks, for example as a replacement or addition to interest points. Software for detecting and describing kAS is released on lear.inrialpes.fr/software. 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 [4].
Fichier principal
Vignette du fichier
FFJS07.pdf (1.06 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00204002 , version 1 (11-01-2008)

Identifiants

Citer

Vittorio Ferrari, Loic Fevrier, Frédéric Jurie, Cordelia Schmid. Groups of Adjacent Contour Segments for Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30 (1), pp.36-51. ⟨10.1109/TPAMI.2007.1144⟩. ⟨hal-00204002⟩
425 Consultations
415 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More