Ghost-free high dynamic range imaging via moving objects detection and extension

Benkang Zhang, Qin Liu, Takeshi Ikenaga

研究成果: Conference contribution

7 被引用数 (Scopus)

抄録

High dynamic range imaging(HDRI) techniques are proposed to synthesize high dynamic range (HDR) images from multi-exposure images. However, ghost artifacts may appear if images are synthesized directly when there are moving objects in the scene. This paper presents an algorithm to composite a HDR image from multi-exposure images without ghost artifacts. To remove the ghosts in the final image, the proposed algorithm firstly produces a 0-1 map based on a Markov Random Field(MRF) framework. The moving areas are detected and marked with 1. Then, moving areas are extended and used in the final exposure fusion step. The marked pixels are assigned zero weights to prevent ghost artifacts.

本文言語English
ホスト出版物のタイトル2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
出版社Institute of Electrical and Electronics Engineers Inc.
ページ459-462
ページ数4
ISBN(電子版)9789881476807
DOI
出版ステータスPublished - 2016 2月 19
イベント2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 - Hong Kong, Hong Kong
継続期間: 2015 12月 162015 12月 19

Other

Other2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
国/地域Hong Kong
CityHong Kong
Period15/12/1615/12/19

ASJC Scopus subject areas

  • 人工知能
  • モデリングとシミュレーション
  • 信号処理

フィンガープリント

「Ghost-free high dynamic range imaging via moving objects detection and extension」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル