Using the Inner-Distance for Classification of Articulated Shapes

  • Authors:
  • Haibin Ling;David W. Jacobs

  • Affiliations:
  • University of Maryland at College Park;University of Maryland at College Park

  • Venue:
  • CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose using the inner-distance between landmark points to build shape descriptors. The inner-distance isdefined as the length of the shortest path between landmark points within the shape silhouette. We show that the inner-distance is articulation insensitive and more effective at capturing complex shapes with part structures than Euclidean distance. To demonstrate this idea, it is used to build a new shape descriptor based on shape contexts. After that, we design a dynamic programming based method for shape matching and comparison. We have tested our approach on a variety of shape databases including an articulated shape dataset, MPEG7 CE-Shape-1, Kimia silhouettes, a Swedish leaf database and a human motion silhouette dataset. In all the experiments, our method demonstrates effective performance compared with other algorithms.