What is an object?

B. Alexe, T. Deselaers, V. Ferrari

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

Abstract

We present a generic objectness measure, quantifying how likely it is for an image window to contain an object of any class. We explicitly train it to distinguish objects with a well-defined boundary in space, such as cows and telephones, from amorphous background elements, such as grass and road. The measure combines in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary. This includes an innovative cue measuring the closed boundary characteristic. In experiments on the challenging PASCAL VOC 07 dataset, we show this new cue to outperform a state-of-the-art saliency measure, and the combined measure to perform better than any cue alone. Finally, we show how to sample windows from an image according to their objectness distribution and give an algorithm to employ them as location priors for modern class-specific object detectors. In experiments on PASCAL VOC 07 we show this greatly reduces the number of windows evaluated by class-specific object detectors.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages73-80
Number of pages8
ISBN (Print)978-1-4244-6984-0
DOIs
Publication statusPublished - 1 Jun 2010

Keywords

  • belief networks
  • image recognition
  • object detection
  • Bayesian framework
  • image cues measurement
  • image window
  • objectness measurement
  • Bayesian methods
  • Detectors
  • Image color analysis
  • Image edge detection
  • Image segmentation
  • Pixel
  • Training

Fingerprint Dive into the research topics of 'What is an object?'. Together they form a unique fingerprint.

Cite this