Accurate Object Detection with Deformable Shape Models Learnt from Images

V. Ferrari, F. Jurie, C. Schmid

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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).
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on
Pages1-8
Number of pages8
ISBN (Electronic)1-4244-1180-7
DOIs
Publication statusPublished - 1 Jun 2007

Keywords / Materials (for Non-textual outputs)

  • image matching
  • object detection
  • accurate object detection
  • bounding-boxes
  • cluttered images
  • deformable shape models
  • shape matcher
  • Computer vision
  • Deformable models
  • Detectors
  • Image segmentation
  • Impedance matching
  • Object detection
  • Prototypes
  • Shape
  • Signal to noise ratio
  • Voting

Fingerprint

Dive into the research topics of 'Accurate Object Detection with Deformable Shape Models Learnt from Images'. Together they form a unique fingerprint.

Cite this