Split-and-Merge-Based Block Partitioning for High Efficiency Image Coding

Byeong Doo Choi, Sung-Jea Ko

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Quadtree-based partitioning (i.e., recursively dividing a picture into square blocks) is one of the most popular partitioning-based image coding schemes because of its computational simplicity and efficient representation of partitioning. However, the rate-distortion performance of quadtree-based partitioning reaches a limit because the dependence between child blocks of different parents is not exploited. In this paper, a new bottom-up-based block partitioning method called split-and-merge is proposed. This method splits an image into multiple square blocks and merges them into nonsquare blocks to exploit the dependence between split blocks. Moreover, a modification of the conventional intra prediction and transform is employed for nonsquare blocks. The experimental results indicate that the proposed method results in an average and maximum bit rate reduction of 3.1% and 8.3%, respectively, relative to High Efficiency Video Coding intra coding.

Original languageEnglish
Article number7583648
Pages (from-to)540-549
Number of pages10
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume28
Issue number2
DOIs
Publication statusPublished - 2018 Feb 1

    Fingerprint

Keywords

  • Block merge
  • high efficiency image coding
  • High Efficiency Video Coding (HEVC)
  • image partitioning
  • nonsquare image transform
  • nonsquare intra prediction
  • quadtree partitioning
  • rate-distortion optimization (RDO)

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Cite this