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.
Complete list of metadatas

https://hal.inria.fr/inria-00096663
Contributor : Rapport de Recherche Inria <>
Submitted on : Thursday, September 21, 2006 - 10:50:31 AM
Last modification on : Wednesday, June 6, 2018 - 1:22:32 AM
Long-term archiving on : Monday, September 20, 2010 - 5:00:26 PM

Identifiers

  • 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⟩

Share

Metrics

Record views

777

Files downloads

753