Robust video stabilization based on mesh grid warping of rolling-free features

Yeong Jun Koh, Jae Young Sim, Chang-Su Kim

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

2 Citations (Scopus)

Abstract

A robust video stabilization algorithm, which reduces shaky camera movements and rolling-shutter distortions in video sequences, is proposed in this work. We first extract feature trajectories through a video sequence, and then transform the feature positions into rolling-free smoothed positions. Then, we set a mesh grid on each frame and warp each grid cell by matching the original features to the smoothed ones. For robust warping, we formulate a cost function based on the confidence of each feature and the reliability of each grid cell. The cost function consists of a data term, a structure-preserving term, and a regularization term. By minimizing the cost function, we find the optimal grid positions in the warped frame and transform each grid cell accordingly. Experimental results show that the proposed algorithm stabilizes videos and removes rolling-shutter distortions more efficiently than conventional algorithms.

Original languageEnglish
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5781-5785
Number of pages5
ISBN (Print)9781479957514
DOIs
Publication statusPublished - 2014 Jan 28

Fingerprint

Cost functions
Stabilization
Camera shutters
Cameras
Trajectories

Keywords

  • mesh grid warping
  • rolling-shutter distortion
  • video enhancement
  • Video stabilization

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Koh, Y. J., Sim, J. Y., & Kim, C-S. (2014). Robust video stabilization based on mesh grid warping of rolling-free features. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 5781-5785). [7026169] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7026169

Robust video stabilization based on mesh grid warping of rolling-free features. / Koh, Yeong Jun; Sim, Jae Young; Kim, Chang-Su.

2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 5781-5785 7026169.

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

Koh, YJ, Sim, JY & Kim, C-S 2014, Robust video stabilization based on mesh grid warping of rolling-free features. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7026169, Institute of Electrical and Electronics Engineers Inc., pp. 5781-5785. https://doi.org/10.1109/ICIP.2014.7026169
Koh YJ, Sim JY, Kim C-S. Robust video stabilization based on mesh grid warping of rolling-free features. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 5781-5785. 7026169 https://doi.org/10.1109/ICIP.2014.7026169
Koh, Yeong Jun ; Sim, Jae Young ; Kim, Chang-Su. / Robust video stabilization based on mesh grid warping of rolling-free features. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 5781-5785
@inproceedings{5dd9074fcc304321b9e491b3f8c5ed30,
title = "Robust video stabilization based on mesh grid warping of rolling-free features",
abstract = "A robust video stabilization algorithm, which reduces shaky camera movements and rolling-shutter distortions in video sequences, is proposed in this work. We first extract feature trajectories through a video sequence, and then transform the feature positions into rolling-free smoothed positions. Then, we set a mesh grid on each frame and warp each grid cell by matching the original features to the smoothed ones. For robust warping, we formulate a cost function based on the confidence of each feature and the reliability of each grid cell. The cost function consists of a data term, a structure-preserving term, and a regularization term. By minimizing the cost function, we find the optimal grid positions in the warped frame and transform each grid cell accordingly. Experimental results show that the proposed algorithm stabilizes videos and removes rolling-shutter distortions more efficiently than conventional algorithms.",
keywords = "mesh grid warping, rolling-shutter distortion, video enhancement, Video stabilization",
author = "Koh, {Yeong Jun} and Sim, {Jae Young} and Chang-Su Kim",
year = "2014",
month = "1",
day = "28",
doi = "10.1109/ICIP.2014.7026169",
language = "English",
isbn = "9781479957514",
pages = "5781--5785",
booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Robust video stabilization based on mesh grid warping of rolling-free features

AU - Koh, Yeong Jun

AU - Sim, Jae Young

AU - Kim, Chang-Su

PY - 2014/1/28

Y1 - 2014/1/28

N2 - A robust video stabilization algorithm, which reduces shaky camera movements and rolling-shutter distortions in video sequences, is proposed in this work. We first extract feature trajectories through a video sequence, and then transform the feature positions into rolling-free smoothed positions. Then, we set a mesh grid on each frame and warp each grid cell by matching the original features to the smoothed ones. For robust warping, we formulate a cost function based on the confidence of each feature and the reliability of each grid cell. The cost function consists of a data term, a structure-preserving term, and a regularization term. By minimizing the cost function, we find the optimal grid positions in the warped frame and transform each grid cell accordingly. Experimental results show that the proposed algorithm stabilizes videos and removes rolling-shutter distortions more efficiently than conventional algorithms.

AB - A robust video stabilization algorithm, which reduces shaky camera movements and rolling-shutter distortions in video sequences, is proposed in this work. We first extract feature trajectories through a video sequence, and then transform the feature positions into rolling-free smoothed positions. Then, we set a mesh grid on each frame and warp each grid cell by matching the original features to the smoothed ones. For robust warping, we formulate a cost function based on the confidence of each feature and the reliability of each grid cell. The cost function consists of a data term, a structure-preserving term, and a regularization term. By minimizing the cost function, we find the optimal grid positions in the warped frame and transform each grid cell accordingly. Experimental results show that the proposed algorithm stabilizes videos and removes rolling-shutter distortions more efficiently than conventional algorithms.

KW - mesh grid warping

KW - rolling-shutter distortion

KW - video enhancement

KW - Video stabilization

UR - http://www.scopus.com/inward/record.url?scp=84943745091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943745091&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7026169

DO - 10.1109/ICIP.2014.7026169

M3 - Conference contribution

AN - SCOPUS:84943745091

SN - 9781479957514

SP - 5781

EP - 5785

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -