A novel performance metric for the video stabilization method

Md Alamgir Hossain; Eui Nam Huh

doi:10.1007/978-3-030-19063-7_38

A novel performance metric for the video stabilization method

Md Alamgir Hossain, Eui Nam Huh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Video stabilization methods cannot compensate entire unwanted motions of an unstable video. In this paper, we present a new performance metric which can effectively measure the stability of a video. Our hypothesis is that in case of non dynamic background, the background motion is zero without the foregrounds of a stable video when a video taken by a fixed camera. Firstly, the foregrounds of a stabilized video are discarded, then, each background pixel motion is determined between the two consecutive background frames in two directions separately, afterwards, an average motion of each pixel is computed. These mean motions determine the stability of a video. The more unstable video will have more background motions. The background motion is a criterion to evaluate the stability of a video. The experimental results prove the efficacy of our proposed approach.

Original language	English
Title of host publication	Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019
Editors	Sukhan Lee, Hyunseung Choo, Roslan Ismail
Publisher	Springer Verlag
Pages	486-496
Number of pages	11
ISBN (Print)	9783030190620
DOIs	https://doi.org/10.1007/978-3-030-19063-7_38
Publication status	Published - 2019
Event	13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019 - Phuket, Thailand Duration: 4 Jan 2019 → 6 Jan 2019

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	935
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019
Country/Territory	Thailand
City	Phuket
Period	4/01/19 → 6/01/19

Bibliographical note

Publisher Copyright:
© Springer Nature Switzerland AG 2019.

Keywords

Mean Displacement Error
Video quality assessment
Video stabilization performance metric

Access to Document

10.1007/978-3-030-19063-7_38

Cite this

Hossain, M. A., & Huh, E. N. (2019). A novel performance metric for the video stabilization method. In S. Lee, H. Choo, & R. Ismail (Eds.), Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019 (pp. 486-496). (Advances in Intelligent Systems and Computing; Vol. 935). Springer Verlag. https://doi.org/10.1007/978-3-030-19063-7_38

@inproceedings{99bed8a02aab42ceb316bfede1f1945f,

title = "A novel performance metric for the video stabilization method",

abstract = "Video stabilization methods cannot compensate entire unwanted motions of an unstable video. In this paper, we present a new performance metric which can effectively measure the stability of a video. Our hypothesis is that in case of non dynamic background, the background motion is zero without the foregrounds of a stable video when a video taken by a fixed camera. Firstly, the foregrounds of a stabilized video are discarded, then, each background pixel motion is determined between the two consecutive background frames in two directions separately, afterwards, an average motion of each pixel is computed. These mean motions determine the stability of a video. The more unstable video will have more background motions. The background motion is a criterion to evaluate the stability of a video. The experimental results prove the efficacy of our proposed approach.",

keywords = "Mean Displacement Error, Video quality assessment, Video stabilization performance metric",

author = "Hossain, {Md Alamgir} and Huh, {Eui Nam}",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2019.; 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019 ; Conference date: 04-01-2019 Through 06-01-2019",

year = "2019",

doi = "10.1007/978-3-030-19063-7_38",

language = "English",

isbn = "9783030190620",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "486--496",

editor = "Sukhan Lee and Hyunseung Choo and Roslan Ismail",

booktitle = "Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019",

address = "Germany",

}

Hossain, MA & Huh, EN 2019, A novel performance metric for the video stabilization method. in S Lee, H Choo & R Ismail (eds), Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019. Advances in Intelligent Systems and Computing, vol. 935, Springer Verlag, pp. 486-496, 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019, Phuket, Thailand, 4/01/19. https://doi.org/10.1007/978-3-030-19063-7_38

A novel performance metric for the video stabilization method. / Hossain, Md Alamgir; Huh, Eui Nam.
Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019. ed. / Sukhan Lee; Hyunseung Choo; Roslan Ismail. Springer Verlag, 2019. p. 486-496 (Advances in Intelligent Systems and Computing; Vol. 935).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A novel performance metric for the video stabilization method

AU - Hossain, Md Alamgir

AU - Huh, Eui Nam

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2019.

PY - 2019

Y1 - 2019

N2 - Video stabilization methods cannot compensate entire unwanted motions of an unstable video. In this paper, we present a new performance metric which can effectively measure the stability of a video. Our hypothesis is that in case of non dynamic background, the background motion is zero without the foregrounds of a stable video when a video taken by a fixed camera. Firstly, the foregrounds of a stabilized video are discarded, then, each background pixel motion is determined between the two consecutive background frames in two directions separately, afterwards, an average motion of each pixel is computed. These mean motions determine the stability of a video. The more unstable video will have more background motions. The background motion is a criterion to evaluate the stability of a video. The experimental results prove the efficacy of our proposed approach.

AB - Video stabilization methods cannot compensate entire unwanted motions of an unstable video. In this paper, we present a new performance metric which can effectively measure the stability of a video. Our hypothesis is that in case of non dynamic background, the background motion is zero without the foregrounds of a stable video when a video taken by a fixed camera. Firstly, the foregrounds of a stabilized video are discarded, then, each background pixel motion is determined between the two consecutive background frames in two directions separately, afterwards, an average motion of each pixel is computed. These mean motions determine the stability of a video. The more unstable video will have more background motions. The background motion is a criterion to evaluate the stability of a video. The experimental results prove the efficacy of our proposed approach.

KW - Mean Displacement Error

KW - Video quality assessment

KW - Video stabilization performance metric

UR - http://www.scopus.com/inward/record.url?scp=85066826094&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-19063-7_38

DO - 10.1007/978-3-030-19063-7_38

M3 - Conference contribution

AN - SCOPUS:85066826094

SN - 9783030190620

T3 - Advances in Intelligent Systems and Computing

SP - 486

EP - 496

BT - Proceedings of the 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019

A2 - Lee, Sukhan

A2 - Choo, Hyunseung

A2 - Ismail, Roslan

PB - Springer Verlag

T2 - 13th International Conference on Ubiquitous Information Management and Communication, IMCOM 2019

Y2 - 4 January 2019 through 6 January 2019

ER -

A novel performance metric for the video stabilization method

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this