Video stabilization for a hand-held camera based on 3D motion model

J. M. Wang, H. P. Chou, Sei-Wang Chen, C. S. Fuh

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

20 Citations (Scopus)

Abstract

In this paper, a video stabilization technique is presented. There are four steps in the proposed approach. We begin with extracting feature points from the input image using the Lowe SIFT (Scale Invariant Feature Transform) point detection technique. This set of feature points is then matched against the set of feature points detected in the previous image using the Wyk et al. RKHS (Reproducing Kernel Hilbert Space) graph matching technique. We can calculate the camera motion between the two images with the aid of a 3D motion model. Expected and unexpected components are separated using a motion taxonomy method. Finally, a full-frame technique to fill up blank image areas is applied to the transformed image.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings
PublisherIEEE Computer Society
Pages3477-3480
Number of pages4
ISBN (Print)9781424456543
DOIs
Publication statusPublished - 2009 Jan 1
Event2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt
Duration: 2009 Nov 72009 Nov 10

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Other

Other2009 IEEE International Conference on Image Processing, ICIP 2009
CountryEgypt
CityCairo
Period09/11/709/11/10

Fingerprint

Hilbert spaces
Taxonomies
Stabilization
Cameras
Mathematical transformations

Keywords

  • 3D motion
  • Full-frame process
  • Motion taxonomy
  • RKHS graph matching
  • SIFT detection

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Wang, J. M., Chou, H. P., Chen, S-W., & Fuh, C. S. (2009). Video stabilization for a hand-held camera based on 3D motion model. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings (pp. 3477-3480). [5413831] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2009.5413831

Video stabilization for a hand-held camera based on 3D motion model. / Wang, J. M.; Chou, H. P.; Chen, Sei-Wang; Fuh, C. S.

2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. p. 3477-3480 5413831 (Proceedings - International Conference on Image Processing, ICIP).

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

Wang, JM, Chou, HP, Chen, S-W & Fuh, CS 2009, Video stabilization for a hand-held camera based on 3D motion model. in 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings., 5413831, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 3477-3480, 2009 IEEE International Conference on Image Processing, ICIP 2009, Cairo, Egypt, 09/11/7. https://doi.org/10.1109/ICIP.2009.5413831
Wang JM, Chou HP, Chen S-W, Fuh CS. Video stabilization for a hand-held camera based on 3D motion model. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society. 2009. p. 3477-3480. 5413831. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2009.5413831
Wang, J. M. ; Chou, H. P. ; Chen, Sei-Wang ; Fuh, C. S. / Video stabilization for a hand-held camera based on 3D motion model. 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. pp. 3477-3480 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{7c869ce8a0854ecfa174bd7545990ea3,
title = "Video stabilization for a hand-held camera based on 3D motion model",
abstract = "In this paper, a video stabilization technique is presented. There are four steps in the proposed approach. We begin with extracting feature points from the input image using the Lowe SIFT (Scale Invariant Feature Transform) point detection technique. This set of feature points is then matched against the set of feature points detected in the previous image using the Wyk et al. RKHS (Reproducing Kernel Hilbert Space) graph matching technique. We can calculate the camera motion between the two images with the aid of a 3D motion model. Expected and unexpected components are separated using a motion taxonomy method. Finally, a full-frame technique to fill up blank image areas is applied to the transformed image.",
keywords = "3D motion, Full-frame process, Motion taxonomy, RKHS graph matching, SIFT detection",
author = "Wang, {J. M.} and Chou, {H. P.} and Sei-Wang Chen and Fuh, {C. S.}",
year = "2009",
month = "1",
day = "1",
doi = "10.1109/ICIP.2009.5413831",
language = "English",
isbn = "9781424456543",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "3477--3480",
booktitle = "2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings",

}

TY - GEN

T1 - Video stabilization for a hand-held camera based on 3D motion model

AU - Wang, J. M.

AU - Chou, H. P.

AU - Chen, Sei-Wang

AU - Fuh, C. S.

PY - 2009/1/1

Y1 - 2009/1/1

N2 - In this paper, a video stabilization technique is presented. There are four steps in the proposed approach. We begin with extracting feature points from the input image using the Lowe SIFT (Scale Invariant Feature Transform) point detection technique. This set of feature points is then matched against the set of feature points detected in the previous image using the Wyk et al. RKHS (Reproducing Kernel Hilbert Space) graph matching technique. We can calculate the camera motion between the two images with the aid of a 3D motion model. Expected and unexpected components are separated using a motion taxonomy method. Finally, a full-frame technique to fill up blank image areas is applied to the transformed image.

AB - In this paper, a video stabilization technique is presented. There are four steps in the proposed approach. We begin with extracting feature points from the input image using the Lowe SIFT (Scale Invariant Feature Transform) point detection technique. This set of feature points is then matched against the set of feature points detected in the previous image using the Wyk et al. RKHS (Reproducing Kernel Hilbert Space) graph matching technique. We can calculate the camera motion between the two images with the aid of a 3D motion model. Expected and unexpected components are separated using a motion taxonomy method. Finally, a full-frame technique to fill up blank image areas is applied to the transformed image.

KW - 3D motion

KW - Full-frame process

KW - Motion taxonomy

KW - RKHS graph matching

KW - SIFT detection

UR - http://www.scopus.com/inward/record.url?scp=77951957271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951957271&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2009.5413831

DO - 10.1109/ICIP.2009.5413831

M3 - Conference contribution

AN - SCOPUS:77951957271

SN - 9781424456543

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3477

EP - 3480

BT - 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings

PB - IEEE Computer Society

ER -