Improved global motion estimation via motion vector clustering for video stabilization

Bo Hao Chen; Andrey Kopylov; Shih Chia Huang; Oleg Seredin; Roman Karpov; Sy Yen Kuo; K. Robert Lai; Tan Hsu Tan; Munkhjargal Gochoo; Damdinsuren Bayanduuren; Cihun Siyong Gong; Patrick C.K. Hung

doi:10.1016/j.engappai.2016.05.004

Improved global motion estimation via motion vector clustering for video stabilization

Bo Hao Chen, Andrey Kopylov, Shih Chia Huang, Oleg Seredin, Roman Karpov, Sy Yen Kuo, K. Robert Lai, Tan Hsu Tan, Munkhjargal Gochoo, Damdinsuren Bayanduuren, Cihun Siyong Gong, Patrick C.K. Hung

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

19 Citations (Scopus)

Abstract

Video stabilization technique is often used in handheld multimedia devices, whereas the difficulties in the accurate extraction aspect of global motion vectors restrict its development. This paper proposes a novel video stabilization approach that is based on the shortest spanning path clustering algorithm for effective and reliable estimation of the global motion vectors. As demonstrated in our experimental results, the proposed approach achieves superior stabilized effectiveness compared with the other state-of-the-art approaches based on both qualitative and quantitative measurements.

Original language	English
Pages (from-to)	39-48
Number of pages	10
Journal	Engineering Applications of Artificial Intelligence
Volume	54
DOIs	https://doi.org/10.1016/j.engappai.2016.05.004
Publication status	Published - Sept 1 2016
Externally published	Yes

Keywords

Motion vector clustering
Shortest spanning path
Video stabilization

ASJC Scopus subject areas

Control and Systems Engineering
Artificial Intelligence
Electrical and Electronic Engineering

Access to Document

10.1016/j.engappai.2016.05.004

Cite this

Chen, B. H., Kopylov, A., Huang, S. C., Seredin, O., Karpov, R., Kuo, S. Y., Robert Lai, K., Tan, T. H., Gochoo, M., Bayanduuren, D., Gong, C. S., & Hung, P. C. K. (2016). Improved global motion estimation via motion vector clustering for video stabilization. Engineering Applications of Artificial Intelligence, 54, 39-48. https://doi.org/10.1016/j.engappai.2016.05.004

@article{2c2d86d133fb453c87ff7605391f71f1,

title = "Improved global motion estimation via motion vector clustering for video stabilization",

abstract = "Video stabilization technique is often used in handheld multimedia devices, whereas the difficulties in the accurate extraction aspect of global motion vectors restrict its development. This paper proposes a novel video stabilization approach that is based on the shortest spanning path clustering algorithm for effective and reliable estimation of the global motion vectors. As demonstrated in our experimental results, the proposed approach achieves superior stabilized effectiveness compared with the other state-of-the-art approaches based on both qualitative and quantitative measurements.",

keywords = "Motion vector clustering, Shortest spanning path, Video stabilization",

author = "Chen, {Bo Hao} and Andrey Kopylov and Huang, {Shih Chia} and Oleg Seredin and Roman Karpov and Kuo, {Sy Yen} and {Robert Lai}, K. and Tan, {Tan Hsu} and Munkhjargal Gochoo and Damdinsuren Bayanduuren and Gong, {Cihun Siyong} and Hung, {Patrick C.K.}",

note = "Funding Information: This work was supported by the Ministry of Science and Technology, Taiwan , and Russian Foundation for Basic Research, Russia , under Grant nos. MOST 105-2923-E-027-001-MY3 , MOST 103-2221-E-027-031-MY2 , MOST 103-2221-E-027-030-MY2 , MOST 103-2923-E-002-011-MY3 , MOST 104-2221-E-027-020 , MOST 105-2218-E-155-003 , MOST 104-3115-E-155-002 , MOST 105-2811-E-027-001 , RFBR 16-57-52042, and RFBR 14-07-00527. Publisher Copyright: {\textcopyright} 2016 Elsevier Ltd.All rights reserved.",

year = "2016",

month = sep,

day = "1",

doi = "10.1016/j.engappai.2016.05.004",

language = "English",

volume = "54",

pages = "39--48",

journal = "Engineering Applications of Artificial Intelligence",

issn = "0952-1976",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Improved global motion estimation via motion vector clustering for video stabilization

AU - Chen, Bo Hao

AU - Kopylov, Andrey

AU - Huang, Shih Chia

AU - Seredin, Oleg

AU - Karpov, Roman

AU - Kuo, Sy Yen

AU - Robert Lai, K.

AU - Tan, Tan Hsu

AU - Gochoo, Munkhjargal

AU - Bayanduuren, Damdinsuren

AU - Gong, Cihun Siyong

AU - Hung, Patrick C.K.

N1 - Funding Information: This work was supported by the Ministry of Science and Technology, Taiwan , and Russian Foundation for Basic Research, Russia , under Grant nos. MOST 105-2923-E-027-001-MY3 , MOST 103-2221-E-027-031-MY2 , MOST 103-2221-E-027-030-MY2 , MOST 103-2923-E-002-011-MY3 , MOST 104-2221-E-027-020 , MOST 105-2218-E-155-003 , MOST 104-3115-E-155-002 , MOST 105-2811-E-027-001 , RFBR 16-57-52042, and RFBR 14-07-00527. Publisher Copyright: © 2016 Elsevier Ltd.All rights reserved.

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Video stabilization technique is often used in handheld multimedia devices, whereas the difficulties in the accurate extraction aspect of global motion vectors restrict its development. This paper proposes a novel video stabilization approach that is based on the shortest spanning path clustering algorithm for effective and reliable estimation of the global motion vectors. As demonstrated in our experimental results, the proposed approach achieves superior stabilized effectiveness compared with the other state-of-the-art approaches based on both qualitative and quantitative measurements.

AB - Video stabilization technique is often used in handheld multimedia devices, whereas the difficulties in the accurate extraction aspect of global motion vectors restrict its development. This paper proposes a novel video stabilization approach that is based on the shortest spanning path clustering algorithm for effective and reliable estimation of the global motion vectors. As demonstrated in our experimental results, the proposed approach achieves superior stabilized effectiveness compared with the other state-of-the-art approaches based on both qualitative and quantitative measurements.

KW - Motion vector clustering

KW - Shortest spanning path

KW - Video stabilization

UR - http://www.scopus.com/inward/record.url?scp=84969833548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969833548&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2016.05.004

DO - 10.1016/j.engappai.2016.05.004

M3 - Article

AN - SCOPUS:84969833548

SN - 0952-1976

VL - 54

SP - 39

EP - 48

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

ER -

Improved global motion estimation via motion vector clustering for video stabilization

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this