From Images to Shape Models for Object Detection

Vittorio Ferrari, Frederic Jurie, Cordelia Schmid

Research output: Contribution to journalArticlepeer-review

Abstract

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 can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate 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 and does not need segmented examples for training (only bounding-boxes).
Original languageEnglish
Pages (from-to)284-303
Number of pages20
JournalInternational Journal of Computer Vision
Volume87
Issue number3
DOIs
Publication statusPublished - 2010

Keywords

  • Object class detection
  • Learning category models
  • Local contour features
  • Shape matching

Fingerprint

Dive into the research topics of 'From Images to Shape Models for Object Detection'. Together they form a unique fingerprint.

Cite this