Superpixel hierarchy

Xing Wei, Qingxiong Yang, Yihong Gong, Narendra Ahuja, Ming Hsuan Yang

Research output: Contribution to journalArticle

Abstract

Superpixel segmentation has been one of the most important tasks in computer vision. In practice, an object can be represented by a number of segments at finer levels with consistent details or included in a surrounding region at coarser levels. Thus, a superpixel segmentation hierarchy is of great importance for applications that require different levels of image details. However, there is no method that can generate all scales of superpixels accurately in real time. In this paper, we propose the superhierarchy algorithm which is able to generate multi-scale superpixels as accurately as the state-of-the-art methods but with one to two orders of magnitude speed-up. The proposed algorithm can be directly integrated with recent efficient edge detectors to significantly outperform the state-of-the-art methods in terms of segmentation accuracy. Quantitative and qualitative evaluations on a number of applications demonstrate that the proposed algorithm is accurate and efficient in generating a hierarchy of superpixels.

Original languageEnglish (US)
Pages (from-to)4838-4849
Number of pages12
JournalIEEE Transactions on Image Processing
Volume27
Issue number10
DOIs
StatePublished - Oct 2018

    Fingerprint

Keywords

  • Borůvka algorithm
  • Superpixel
  • segmentation

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Wei, X., Yang, Q., Gong, Y., Ahuja, N., & Yang, M. H. (2018). Superpixel hierarchy. IEEE Transactions on Image Processing, 27(10), 4838-4849. https://doi.org/10.1109/TIP.2018.2836300