Computation and memory efficient image segmentation

Yiren Zhou, Thanh-Toan Do, Haitian Zheng, Ngai-Man Cheung, Lu Fang

Research output: Contribution to journalArticleResearchpeer-review

6 Citations (Scopus)


In this paper, we address the segmentation problem under limited computation and memory resources. Given a segmentation algorithm, we propose a framework that can reduce its computation time and memory requirement simultaneously, while preserving its accuracy. The proposed framework uses standard pixel-domain downsampling and includes two main steps. Coarse segmentation is first performed on the downsampled image. Refinement is then applied to the coarse segmentation results. We make two novel contributions to enable competitive accuracy using this simple framework. First, we rigorously examine the effect of downsampling on segmentation using a signal processing analysis. The analysis helps to determine the uncertain regions, which are small image regions where pixel labels are uncertain after the coarse segmentation. Second, we propose an efficient minimum spanning tree-based algorithm to propagate the labels into the uncertain regions. We perform extensive experiments using several standard data sets. The experimental results show that our segmentation accuracy is comparable to state-of-the-art methods, while requiring much less computation time and memory than those methods.

Original languageEnglish
Pages (from-to)46-61
Number of pages16
JournalIEEE Transactions on Circuits and Systems for Video Technology
Issue number1
Publication statusPublished - Jan 2018
Externally publishedYes


  • Computation and memory efficient
  • downsampling
  • minimum spanning tree (MST)
  • segmentation

Cite this