Robust digital image stabilization using feature tracking

Chuntao Wang, Jin Hyung Kim, Keun Yung Byun, Sung-Jea Ko

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

3 Citations (Scopus)

Abstract

This paper presents a new robust digital image stabilization (DIS) algorithm which uses well-tracked feature points to estimate the motion between two consecutive frames. The motion prediction with the Kalman filter is incorporated into the Kanade-Lucas-Tomasi (KLT) tracker to further speed up the tracking process. A new scheme is proposed to adaptively update the Kalman filter. Simulation results show that the proposed algorithm can speed up the tracking process and obtain more stabilized performance.

Original languageEnglish
Title of host publicationDigest of Technical Papers - IEEE International Conference on Consumer Electronics
DOIs
Publication statusPublished - 2009 Sep 25
Event2009 International Conference on Consumer Electronics, ICCE 2009 - Las Vegas, NV, United States
Duration: 2009 Jan 102009 Jan 14

Other

Other2009 International Conference on Consumer Electronics, ICCE 2009
CountryUnited States
CityLas Vegas, NV
Period09/1/1009/1/14

Fingerprint

Kalman filters
Stabilization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Wang, C., Kim, J. H., Byun, K. Y., & Ko, S-J. (2009). Robust digital image stabilization using feature tracking. In Digest of Technical Papers - IEEE International Conference on Consumer Electronics [5012257] https://doi.org/10.1109/ICCE.2009.5012257

Robust digital image stabilization using feature tracking. / Wang, Chuntao; Kim, Jin Hyung; Byun, Keun Yung; Ko, Sung-Jea.

Digest of Technical Papers - IEEE International Conference on Consumer Electronics. 2009. 5012257.

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

Wang, C, Kim, JH, Byun, KY & Ko, S-J 2009, Robust digital image stabilization using feature tracking. in Digest of Technical Papers - IEEE International Conference on Consumer Electronics., 5012257, 2009 International Conference on Consumer Electronics, ICCE 2009, Las Vegas, NV, United States, 09/1/10. https://doi.org/10.1109/ICCE.2009.5012257
Wang C, Kim JH, Byun KY, Ko S-J. Robust digital image stabilization using feature tracking. In Digest of Technical Papers - IEEE International Conference on Consumer Electronics. 2009. 5012257 https://doi.org/10.1109/ICCE.2009.5012257
Wang, Chuntao ; Kim, Jin Hyung ; Byun, Keun Yung ; Ko, Sung-Jea. / Robust digital image stabilization using feature tracking. Digest of Technical Papers - IEEE International Conference on Consumer Electronics. 2009.
@inproceedings{774b14be349442928cea8680366a1b54,
title = "Robust digital image stabilization using feature tracking",
abstract = "This paper presents a new robust digital image stabilization (DIS) algorithm which uses well-tracked feature points to estimate the motion between two consecutive frames. The motion prediction with the Kalman filter is incorporated into the Kanade-Lucas-Tomasi (KLT) tracker to further speed up the tracking process. A new scheme is proposed to adaptively update the Kalman filter. Simulation results show that the proposed algorithm can speed up the tracking process and obtain more stabilized performance.",
author = "Chuntao Wang and Kim, {Jin Hyung} and Byun, {Keun Yung} and Sung-Jea Ko",
year = "2009",
month = "9",
day = "25",
doi = "10.1109/ICCE.2009.5012257",
language = "English",
isbn = "9781424425594",
booktitle = "Digest of Technical Papers - IEEE International Conference on Consumer Electronics",

}

TY - GEN

T1 - Robust digital image stabilization using feature tracking

AU - Wang, Chuntao

AU - Kim, Jin Hyung

AU - Byun, Keun Yung

AU - Ko, Sung-Jea

PY - 2009/9/25

Y1 - 2009/9/25

N2 - This paper presents a new robust digital image stabilization (DIS) algorithm which uses well-tracked feature points to estimate the motion between two consecutive frames. The motion prediction with the Kalman filter is incorporated into the Kanade-Lucas-Tomasi (KLT) tracker to further speed up the tracking process. A new scheme is proposed to adaptively update the Kalman filter. Simulation results show that the proposed algorithm can speed up the tracking process and obtain more stabilized performance.

AB - This paper presents a new robust digital image stabilization (DIS) algorithm which uses well-tracked feature points to estimate the motion between two consecutive frames. The motion prediction with the Kalman filter is incorporated into the Kanade-Lucas-Tomasi (KLT) tracker to further speed up the tracking process. A new scheme is proposed to adaptively update the Kalman filter. Simulation results show that the proposed algorithm can speed up the tracking process and obtain more stabilized performance.

UR - http://www.scopus.com/inward/record.url?scp=70349290967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349290967&partnerID=8YFLogxK

U2 - 10.1109/ICCE.2009.5012257

DO - 10.1109/ICCE.2009.5012257

M3 - Conference contribution

AN - SCOPUS:70349290967

SN - 9781424425594

BT - Digest of Technical Papers - IEEE International Conference on Consumer Electronics

ER -