Putting objects in perspective

Derek Hoiem, Alexei A. Efros, Martial Hebert

Research output: Contribution to journalArticlepeer-review

Abstract

Image understanding requires not only individually estimating elements of the visual world but also capturing the interplay among them. In this paper, we provide a framework for placing local object detection in the context of the overall 3D scene by modeling the interdependence of objects, surface orientations, and camera viewpoint. Most object detection methods consider all scales and locations in the image as equally likely. We show that with probabilistic estimates of 3D geometry, both in terms of surfaces and world coordinates, we can put objects into perspective and model the scale and location variance in the image. Our approach reflects the cyclical nature of the problem by allowing probabilistic object hypotheses to refine geometry and vice-versa. Our framework allows painless substitution of almost any object detector and is easily extended to include other aspects of image understanding. Our results confirm the benefits of our integrated approach.

Original languageEnglish (US)
Pages (from-to)3-15
Number of pages13
JournalInternational Journal of Computer Vision
Volume80
Issue number1
DOIs
StatePublished - Oct 2008
Externally publishedYes

Keywords

  • 3D reconstruction
  • Camera calibration
  • Object detection
  • Object recognition
  • Scene understanding
  • Surface estimation
  • Viewpoint estimation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Putting objects in perspective'. Together they form a unique fingerprint.

Cite this