Visual salience and stack extension based ghost removal for high-dynamic-range imaging

Zijie Wang, Qin Liu, Takeshi Ikenaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

High-dynamic-range imaging (HDRI) techniques are proposed to extend the dynamic range of captured images against sensor limitation. The key issue of multi-exposure fusion in HDRI is removing ghost artifacts caused by motion of moving objects and handheld cameras. This paper proposes a ghost-free HDRI algorithm based on visual salience and stack extension. To improve the accuracy of ghost areas detection, visual salience based bilateral motion detection is introduced to measure image differences. For exposure fusion, the proposed algorithm reduces brightness discontinuity and enhances details by stack extension, and rejects the information of ghost areas to avoid artifacts via fusion masks. Experiment results show that the proposed algorithm can remove ghost artifacts accurately for both static and handheld cameras, remain robust to scenes with complex motion and keep low complexity over recent advances including patch based method and rank minimization based method by 20.4% and 63.6% time savings on average.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages2244-2248
Number of pages5
Volume2017-September
ISBN (Electronic)9781509021758
DOIs
Publication statusPublished - 2018 Feb 20
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: 2017 Sep 172017 Sep 20

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period17/9/1717/9/20

Fingerprint

Imaging techniques
Fusion reactions
Cameras
Image sensors
Masks
Luminance
Experiments

Keywords

  • Exposure fusion
  • Ghost removal
  • High-dynamic-range imaging (HDRI)
  • Motion detection
  • Visual salience

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Wang, Z., Liu, Q., & Ikenaga, T. (2018). Visual salience and stack extension based ghost removal for high-dynamic-range imaging. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (Vol. 2017-September, pp. 2244-2248). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8296681

Visual salience and stack extension based ghost removal for high-dynamic-range imaging. / Wang, Zijie; Liu, Qin; Ikenaga, Takeshi.

2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. p. 2244-2248.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, Z, Liu, Q & Ikenaga, T 2018, Visual salience and stack extension based ghost removal for high-dynamic-range imaging. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. vol. 2017-September, IEEE Computer Society, pp. 2244-2248, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 17/9/17. https://doi.org/10.1109/ICIP.2017.8296681
Wang Z, Liu Q, Ikenaga T. Visual salience and stack extension based ghost removal for high-dynamic-range imaging. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September. IEEE Computer Society. 2018. p. 2244-2248 https://doi.org/10.1109/ICIP.2017.8296681
Wang, Zijie ; Liu, Qin ; Ikenaga, Takeshi. / Visual salience and stack extension based ghost removal for high-dynamic-range imaging. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. pp. 2244-2248
@inproceedings{5acb5fc28097464890d404de4b7fd799,
title = "Visual salience and stack extension based ghost removal for high-dynamic-range imaging",
abstract = "High-dynamic-range imaging (HDRI) techniques are proposed to extend the dynamic range of captured images against sensor limitation. The key issue of multi-exposure fusion in HDRI is removing ghost artifacts caused by motion of moving objects and handheld cameras. This paper proposes a ghost-free HDRI algorithm based on visual salience and stack extension. To improve the accuracy of ghost areas detection, visual salience based bilateral motion detection is introduced to measure image differences. For exposure fusion, the proposed algorithm reduces brightness discontinuity and enhances details by stack extension, and rejects the information of ghost areas to avoid artifacts via fusion masks. Experiment results show that the proposed algorithm can remove ghost artifacts accurately for both static and handheld cameras, remain robust to scenes with complex motion and keep low complexity over recent advances including patch based method and rank minimization based method by 20.4{\%} and 63.6{\%} time savings on average.",
keywords = "Exposure fusion, Ghost removal, High-dynamic-range imaging (HDRI), Motion detection, Visual salience",
author = "Zijie Wang and Qin Liu and Takeshi Ikenaga",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ICIP.2017.8296681",
language = "English",
volume = "2017-September",
pages = "2244--2248",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Visual salience and stack extension based ghost removal for high-dynamic-range imaging

AU - Wang, Zijie

AU - Liu, Qin

AU - Ikenaga, Takeshi

PY - 2018/2/20

Y1 - 2018/2/20

N2 - High-dynamic-range imaging (HDRI) techniques are proposed to extend the dynamic range of captured images against sensor limitation. The key issue of multi-exposure fusion in HDRI is removing ghost artifacts caused by motion of moving objects and handheld cameras. This paper proposes a ghost-free HDRI algorithm based on visual salience and stack extension. To improve the accuracy of ghost areas detection, visual salience based bilateral motion detection is introduced to measure image differences. For exposure fusion, the proposed algorithm reduces brightness discontinuity and enhances details by stack extension, and rejects the information of ghost areas to avoid artifacts via fusion masks. Experiment results show that the proposed algorithm can remove ghost artifacts accurately for both static and handheld cameras, remain robust to scenes with complex motion and keep low complexity over recent advances including patch based method and rank minimization based method by 20.4% and 63.6% time savings on average.

AB - High-dynamic-range imaging (HDRI) techniques are proposed to extend the dynamic range of captured images against sensor limitation. The key issue of multi-exposure fusion in HDRI is removing ghost artifacts caused by motion of moving objects and handheld cameras. This paper proposes a ghost-free HDRI algorithm based on visual salience and stack extension. To improve the accuracy of ghost areas detection, visual salience based bilateral motion detection is introduced to measure image differences. For exposure fusion, the proposed algorithm reduces brightness discontinuity and enhances details by stack extension, and rejects the information of ghost areas to avoid artifacts via fusion masks. Experiment results show that the proposed algorithm can remove ghost artifacts accurately for both static and handheld cameras, remain robust to scenes with complex motion and keep low complexity over recent advances including patch based method and rank minimization based method by 20.4% and 63.6% time savings on average.

KW - Exposure fusion

KW - Ghost removal

KW - High-dynamic-range imaging (HDRI)

KW - Motion detection

KW - Visual salience

UR - http://www.scopus.com/inward/record.url?scp=85045341518&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045341518&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8296681

DO - 10.1109/ICIP.2017.8296681

M3 - Conference contribution

AN - SCOPUS:85045341518

VL - 2017-September

SP - 2244

EP - 2248

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

ER -