International Journal of Computer Vision

, Volume 103, Issue 1, pp 1–21

Structure-Sensitive Superpixels via Geodesic Distance

  • Peng Wang
  • Gang Zeng
  • Rui Gan
  • Jingdong Wang
  • Hongbin Zha
Article

DOI: 10.1007/s11263-012-0588-6

Cite this article as:
Wang, P., Zeng, G., Gan, R. et al. Int J Comput Vis (2013) 103: 1. doi:10.1007/s11263-012-0588-6

Abstract

Segmenting images into superpixels as supporting regions for feature vectors and primitives to reduce computational complexity has been commonly used as a fundamental step in various image analysis and computer vision tasks. In this paper, we describe the structure-sensitive superpixel technique by exploiting Lloyd’s algorithm with the geodesic distance. Our method generates smaller superpixels to achieve relatively low under-segmentation in structure-dense regions with high intensity or color variation, and produces larger segments to increase computational efficiency in structure-sparse regions with homogeneous appearance. We adopt geometric flows to compute geodesic distances amongst pixels. In the segmentation procedure, the density of over-segments is automatically adjusted through iteratively optimizing an energy functional that embeds color homogeneity, structure density. Comparative experiments with the Berkeley database show that the proposed algorithm outperforms the prior arts while offering a comparable computational efficiency as TurboPixels. Further applications in image compression, object closure extraction and video segmentation demonstrate the effective extensions of our approach.

Keywords

Superpixel segmentation Geodesic distance Iterative optimization Structure-sensitivity 

Copyright information

© Springer Science+Business Media New York 2012

Authors and Affiliations

  • Peng Wang
    • 1
  • Gang Zeng
    • 1
  • Rui Gan
    • 2
  • Jingdong Wang
    • 3
  • Hongbin Zha
    • 1
  1. 1.Key Laboratory on Machine PerceptionPeking UniversityBeijingChina
  2. 2.School of Mathematical SciencesPeking UniversityBeijingChina
  3. 3.Microsoft Research AsiaBeijingChina

Personalised recommendations