Motion adaptive deinterlacing with modular neural networks

Hyunsoo Choi; Chulhee Lee

doi:10.1109/TCSVT.2011.2129190

Motion adaptive deinterlacing with modular neural networks

Hyunsoo Choi, Chulhee Lee

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article › peer-review

20 Citations (Scopus)

Abstract

In this letter, a motion adaptive deinterlacing algorithm based on modular neural networks is proposed. The proposed method uses different neural networks based on the amount of motion. Modular neural networks were selectively used depending on the differences between the adjacent fields. We also used motion vectors to select optimal input pixels from the adjacent fields. Motion estimation was used to find input blocks for the neural networks with minimum errors. Intra/inter-mode switching was employed to address inaccurate motion estimation problems.

Original language	English
Article number	5733392
Pages (from-to)	844-849
Number of pages	6
Journal	IEEE Transactions on Circuits and Systems for Video Technology
Volume	21
Issue number	6
DOIs	https://doi.org/10.1109/TCSVT.2011.2129190
Publication status	Published - 2011 Jun

Bibliographical note

Funding Information:
Manuscript received August 17, 2009; revised April 16, 2010 and August 27, 2010; accepted October 14, 2010. Date of publication March 17, 2011; date of current version June 3, 2011. This work was supported by the Korea Science and Engineering Foundation (KOSEF), under Grant 2009-0077978, funded by the Korean Government (MEST). This paper was recommended by Associate Editor M. Comer.

All Science Journal Classification (ASJC) codes

Media Technology
Electrical and Electronic Engineering

Access to Document

10.1109/TCSVT.2011.2129190

Cite this

@article{fa020f163e19481cb0faa72a6bc945f5,

title = "Motion adaptive deinterlacing with modular neural networks",

abstract = "In this letter, a motion adaptive deinterlacing algorithm based on modular neural networks is proposed. The proposed method uses different neural networks based on the amount of motion. Modular neural networks were selectively used depending on the differences between the adjacent fields. We also used motion vectors to select optimal input pixels from the adjacent fields. Motion estimation was used to find input blocks for the neural networks with minimum errors. Intra/inter-mode switching was employed to address inaccurate motion estimation problems.",

author = "Hyunsoo Choi and Chulhee Lee",

note = "Funding Information: Manuscript received August 17, 2009; revised April 16, 2010 and August 27, 2010; accepted October 14, 2010. Date of publication March 17, 2011; date of current version June 3, 2011. This work was supported by the Korea Science and Engineering Foundation (KOSEF), under Grant 2009-0077978, funded by the Korean Government (MEST). This paper was recommended by Associate Editor M. Comer.",

year = "2011",

month = jun,

doi = "10.1109/TCSVT.2011.2129190",

language = "English",

volume = "21",

pages = "844--849",

journal = "IEEE Transactions on Circuits and Systems for Video Technology",

issn = "1051-8215",

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

number = "6",

}

TY - JOUR

T1 - Motion adaptive deinterlacing with modular neural networks

AU - Choi, Hyunsoo

AU - Lee, Chulhee

N1 - Funding Information: Manuscript received August 17, 2009; revised April 16, 2010 and August 27, 2010; accepted October 14, 2010. Date of publication March 17, 2011; date of current version June 3, 2011. This work was supported by the Korea Science and Engineering Foundation (KOSEF), under Grant 2009-0077978, funded by the Korean Government (MEST). This paper was recommended by Associate Editor M. Comer.

PY - 2011/6

Y1 - 2011/6

N2 - In this letter, a motion adaptive deinterlacing algorithm based on modular neural networks is proposed. The proposed method uses different neural networks based on the amount of motion. Modular neural networks were selectively used depending on the differences between the adjacent fields. We also used motion vectors to select optimal input pixels from the adjacent fields. Motion estimation was used to find input blocks for the neural networks with minimum errors. Intra/inter-mode switching was employed to address inaccurate motion estimation problems.

AB - In this letter, a motion adaptive deinterlacing algorithm based on modular neural networks is proposed. The proposed method uses different neural networks based on the amount of motion. Modular neural networks were selectively used depending on the differences between the adjacent fields. We also used motion vectors to select optimal input pixels from the adjacent fields. Motion estimation was used to find input blocks for the neural networks with minimum errors. Intra/inter-mode switching was employed to address inaccurate motion estimation problems.

UR - http://www.scopus.com/inward/record.url?scp=79957998809&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957998809&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2011.2129190

DO - 10.1109/TCSVT.2011.2129190

M3 - Article

AN - SCOPUS:79957998809

SN - 1051-8215

VL - 21

SP - 844

EP - 849

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

IS - 6

M1 - 5733392

ER -

Motion adaptive deinterlacing with modular neural networks

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this