Perceptual Organization for Scene Segmentation and Description

  • Mohan R
  • Nevatia R
  • 37

    Readers

    Mendeley users who have this article in their library.
  • 115

    Citations

    Citations of this article.

Abstract

A data-driven system for segmenting scenes into objects and their components is presented. This segmentation system generates hierarchies of features that correspond to structural elements such as boundaries and surfaces of objects. The technique is based on perceptual organization, implemented as a mechanism for exploiting geometrical regularities in the shapes of objects as projected on images. Edges are recursively grouped on geometrical relationships into a description hierarchy ranging from edges to the visible surfaces of objects. These edge groupings, which are termed collated features, are abstract descriptors encoding structural information. The geometrical relationships employed are quasi-invariant over 2-D projections and are common to structures of most objects. Thus, collations have a high likelihood of corresponding to parts of objects. Collations serve as intermediate and high-level features for various visual processes. Applications of collations to stereo correspondence, object-level segmentation, and shape description are illustrated.

Author-supplied keywords

  • Constraint satisfaction networks
  • perceptual organization
  • segmentation
  • symmetry

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text

Authors

  • Rakesh Mohan

  • Ramakant Nevatia

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free