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

Benkang Zhang; Qin Liu; Takeshi Ikenaga

doi:10.1109/APSIPA.2015.7415313

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

Benkang Zhang, Qin Liu, Takeshi Ikenaga

Graduate School of Information, Production and Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

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.

Original language	English
Title of host publication	2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	459-462
Number of pages	4
ISBN (Electronic)	9789881476807
DOIs	https://doi.org/10.1109/APSIPA.2015.7415313
Publication status	Published - 2016 Feb 19
Event	2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 - Hong Kong, Hong Kong Duration: 2015 Dec 16 → 2015 Dec 19

Other

Other	2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015
Country/Territory	Hong Kong
City	Hong Kong
Period	15/12/16 → 15/12/19

Keywords

Exposure Fusion
Ghost Free
High Dynamic Range Imaging
Image Segmentation
Moving Objects Detection

ASJC Scopus subject areas

Artificial Intelligence
Modelling and Simulation
Signal Processing

Access to Document

10.1109/APSIPA.2015.7415313

Cite this

Ghost-free high dynamic range imaging via moving objects detection and extension. / Zhang, Benkang; Liu, Qin; Ikenaga, Takeshi.
2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 459-462 7415313.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, B, Liu, Q & Ikenaga, T 2016, Ghost-free high dynamic range imaging via moving objects detection and extension. in 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015., 7415313, Institute of Electrical and Electronics Engineers Inc., pp. 459-462, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015, Hong Kong, Hong Kong, 15/12/16. https://doi.org/10.1109/APSIPA.2015.7415313

@inproceedings{f1dcfb2b60da42caa76f2b07b02b3d67,

title = "Ghost-free high dynamic range imaging via moving objects detection and extension",

abstract = "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.",

keywords = "Exposure Fusion, Ghost Free, High Dynamic Range Imaging, Image Segmentation, Moving Objects Detection",

author = "Benkang Zhang and Qin Liu and Takeshi Ikenaga",

year = "2016",

month = feb,

day = "19",

doi = "10.1109/APSIPA.2015.7415313",

language = "English",

pages = "459--462",

booktitle = "2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015 ; Conference date: 16-12-2015 Through 19-12-2015",

}

TY - GEN

T1 - Ghost-free high dynamic range imaging via moving objects detection and extension

AU - Zhang, Benkang

AU - Liu, Qin

AU - Ikenaga, Takeshi

PY - 2016/2/19

Y1 - 2016/2/19

N2 - 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.

AB - 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.

KW - Exposure Fusion

KW - Ghost Free

KW - High Dynamic Range Imaging

KW - Image Segmentation

KW - Moving Objects Detection

UR - http://www.scopus.com/inward/record.url?scp=84986206112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986206112&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2015.7415313

DO - 10.1109/APSIPA.2015.7415313

M3 - Conference contribution

AN - SCOPUS:84986206112

SP - 459

EP - 462

BT - 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2015

Y2 - 16 December 2015 through 19 December 2015

ER -

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

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this