Edge affinity for pose-contour matching

  • Authors:
  • V. S. N. Prasad;Larry S. Davis;Son Dinh Tran;Ahmed Elgammal

  • Affiliations:
  • University of Maryland, Institute of Advanced Computer Studies (UMIACS), College Park, MD;University of Maryland, Institute of Advanced Computer Studies (UMIACS), College Park, MD;University of Maryland, Institute of Advanced Computer Studies (UMIACS), College Park, MD;Department of Computer Science, Rutgers University, Piscataway, NJ

  • Venue:
  • Computer Vision and Image Understanding
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an approach for whole-body pose-contour matching. Contour matching in natural images in the absence of foreground-background segmentation is difficult. Usually an asymmetric approach is adopted, where a contour is said to match well if it aligns with a subset of the image's gradients. This leads to problems as the contour can match with a portion of an object's outline and ignore the remainder. We present a model for using edge continuity to address this issue. Pairs of edge elements in the image are linked with affinities if they are likely to belong to the same object. A contour that matches with a set of image gradients is constrained to also match with other gradients having high affinities with the chosen ones. Experimental results show that this improves matching performance.