Robust global motion estimation for video stabilization

Tae Shick Wang, Seok Jae Kang, Keun Yung Byun, Tae Chan Kim, Sung-Jea Ko

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

1 Citation (Scopus)

Abstract

Global motion estimation is an important task for video stabilization. Since the global motion is heavily related to the motion of the background (BG), the moving foreground (FG) objects can cause inaccurate global motion estimation. In this paper, we propose a robust global motion estimation method for video stabilization. The proposed method iteratively finds the feature points (FPs) in the BG and estimates the global motion using the BG FPs. The experimental results show that the proposed method can estimate the global motion even when the moving FG objects occupy a large part of image.

Original languageEnglish
Title of host publication1st IEEE Global Conference on Consumer Electronics 2012, GCCE 2012
Pages623-624
Number of pages2
DOIs
Publication statusPublished - 2012 Dec 1
Event1st IEEE Global Conference on Consumer Electronics, GCCE 2012 - Tokyo, Japan
Duration: 2012 Oct 22012 Oct 5

Other

Other1st IEEE Global Conference on Consumer Electronics, GCCE 2012
CountryJapan
CityTokyo
Period12/10/212/10/5

Fingerprint

Motion estimation
Stabilization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Wang, T. S., Kang, S. J., Byun, K. Y., Kim, T. C., & Ko, S-J. (2012). Robust global motion estimation for video stabilization. In 1st IEEE Global Conference on Consumer Electronics 2012, GCCE 2012 (pp. 623-624). [6379934] https://doi.org/10.1109/GCCE.2012.6379934

Robust global motion estimation for video stabilization. / Wang, Tae Shick; Kang, Seok Jae; Byun, Keun Yung; Kim, Tae Chan; Ko, Sung-Jea.

1st IEEE Global Conference on Consumer Electronics 2012, GCCE 2012. 2012. p. 623-624 6379934.

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

Wang, TS, Kang, SJ, Byun, KY, Kim, TC & Ko, S-J 2012, Robust global motion estimation for video stabilization. in 1st IEEE Global Conference on Consumer Electronics 2012, GCCE 2012., 6379934, pp. 623-624, 1st IEEE Global Conference on Consumer Electronics, GCCE 2012, Tokyo, Japan, 12/10/2. https://doi.org/10.1109/GCCE.2012.6379934
Wang TS, Kang SJ, Byun KY, Kim TC, Ko S-J. Robust global motion estimation for video stabilization. In 1st IEEE Global Conference on Consumer Electronics 2012, GCCE 2012. 2012. p. 623-624. 6379934 https://doi.org/10.1109/GCCE.2012.6379934
Wang, Tae Shick ; Kang, Seok Jae ; Byun, Keun Yung ; Kim, Tae Chan ; Ko, Sung-Jea. / Robust global motion estimation for video stabilization. 1st IEEE Global Conference on Consumer Electronics 2012, GCCE 2012. 2012. pp. 623-624
@inproceedings{ac17bf1d52dd4f03b0e21ed0db7b52a5,
title = "Robust global motion estimation for video stabilization",
abstract = "Global motion estimation is an important task for video stabilization. Since the global motion is heavily related to the motion of the background (BG), the moving foreground (FG) objects can cause inaccurate global motion estimation. In this paper, we propose a robust global motion estimation method for video stabilization. The proposed method iteratively finds the feature points (FPs) in the BG and estimates the global motion using the BG FPs. The experimental results show that the proposed method can estimate the global motion even when the moving FG objects occupy a large part of image.",
author = "Wang, {Tae Shick} and Kang, {Seok Jae} and Byun, {Keun Yung} and Kim, {Tae Chan} and Sung-Jea Ko",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/GCCE.2012.6379934",
language = "English",
isbn = "9781467315005",
pages = "623--624",
booktitle = "1st IEEE Global Conference on Consumer Electronics 2012, GCCE 2012",

}

TY - GEN

T1 - Robust global motion estimation for video stabilization

AU - Wang, Tae Shick

AU - Kang, Seok Jae

AU - Byun, Keun Yung

AU - Kim, Tae Chan

AU - Ko, Sung-Jea

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Global motion estimation is an important task for video stabilization. Since the global motion is heavily related to the motion of the background (BG), the moving foreground (FG) objects can cause inaccurate global motion estimation. In this paper, we propose a robust global motion estimation method for video stabilization. The proposed method iteratively finds the feature points (FPs) in the BG and estimates the global motion using the BG FPs. The experimental results show that the proposed method can estimate the global motion even when the moving FG objects occupy a large part of image.

AB - Global motion estimation is an important task for video stabilization. Since the global motion is heavily related to the motion of the background (BG), the moving foreground (FG) objects can cause inaccurate global motion estimation. In this paper, we propose a robust global motion estimation method for video stabilization. The proposed method iteratively finds the feature points (FPs) in the BG and estimates the global motion using the BG FPs. The experimental results show that the proposed method can estimate the global motion even when the moving FG objects occupy a large part of image.

UR - http://www.scopus.com/inward/record.url?scp=84872360902&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872360902&partnerID=8YFLogxK

U2 - 10.1109/GCCE.2012.6379934

DO - 10.1109/GCCE.2012.6379934

M3 - Conference contribution

AN - SCOPUS:84872360902

SN - 9781467315005

SP - 623

EP - 624

BT - 1st IEEE Global Conference on Consumer Electronics 2012, GCCE 2012

ER -