Fusion of Foreground Object, Spatial and Frequency Domain Motion Information for Video Summarization

MD. Salehin; Manoranjan Paul

doi:10.1007/978-3-319-30285-0_26

Fusion of Foreground Object, Spatial and Frequency Domain Motion Information for Video Summarization

MD. Salehin, Manoranjan Paul

Research output: Book chapter/Published conference paper › Conference paper › peer-review

5 Citations (Scopus)

1 Downloads (Pure)

Abstract

Surveillance video camera captures a large amount of continuous video stream every day. To analyze or investigate any significant events from the huge video data, it is laborious and boring job to identify these events. To solve this problem, a video summarization technique combining foreground objects as well as motion information in spatial and frequency domain is proposed in this paper. We extract foreground object using background modeling and motion information in spatial domain and frequency domain. Frame transition is applied for obtaining motion information in spatial domain. For acquiring motion information in frequency domain, phase correlation (PC) technique is applied. Later, foreground objects and motions in spatial and frequency domain are fused and key frames are extracted. Experimental results reveal that the proposed method performs better than the state-of-the-art method.

Original language	English
Title of host publication	PSIVT 2015
Editors	Fay Huang, Akihiro Sugimoto
Place of Publication	Germany
Publisher	Springer
Pages	319-331
Number of pages	13
Volume	9555
DOIs	https://doi.org/10.1007/978-3-319-30285-0_26
Publication status	Published - 2015
Event	7th Pacific Rim Symposium on Image and Video Technology - Faculty of Engineering, University of Auckland, Auckland, New Zealand Duration: 23 Nov 2015 → 27 Nov 2015 http://www.psivt.org/psivt2015/ (Conference website) https://web.archive.org/web/20160404030704/http://psivt.org/psivt2015/docs/PsivtProgramFinal.pdf (Conference program) https://web.archive.org/web/20160313115108/http://www.psivt.org/psivt2015/docs/PSIVT_Handboook.pdf (Detailed program)

Publication series

Name
ISSN (Print)	1611-3349

Conference

Conference	7th Pacific Rim Symposium on Image and Video Technology
Country/Territory	New Zealand
City	Auckland
Period	23/11/15 → 27/11/15
Other	PSIVT provides a forum for researchers to present the latest research and developments in image and video technology. Both academic and industrial research contributions are encouraged so as to stimulate discussion for the mutual benefit of both. Researchers, artists, developers, educators, performers, and practitioners of image and video technology from the Pacific Rim and around the world are invited to participate.
Internet address	http://www.psivt.org/psivt2015/ (Conference website) https://web.archive.org/web/20160404030704/http://psivt.org/psivt2015/docs/PsivtProgramFinal.pdf (Conference program) https://web.archive.org/web/20160313115108/http://www.psivt.org/psivt2015/docs/PSIVT_Handboook.pdf (Detailed program)

Access to Document

10.1007/978-3-319-30285-0_26

Cite this

@inproceedings{3262a86f0aa442dd9d6d3528bc4ed1d1,

title = "Fusion of Foreground Object, Spatial and Frequency Domain Motion Information for Video Summarization",

abstract = "Surveillance video camera captures a large amount of continuous video stream every day. To analyze or investigate any significant events from the huge video data, it is laborious and boring job to identify these events. To solve this problem, a video summarization technique combining foreground objects as well as motion information in spatial and frequency domain is proposed in this paper. We extract foreground object using background modeling and motion information in spatial domain and frequency domain. Frame transition is applied for obtaining motion information in spatial domain. For acquiring motion information in frequency domain, phase correlation (PC) technique is applied. Later, foreground objects and motions in spatial and frequency domain are fused and key frames are extracted. Experimental results reveal that the proposed method performs better than the state-of-the-art method.",

keywords = "Background modelling, Motion information, Phase correlation, Video summarization",

author = "MD. Salehin and Manoranjan Paul",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = Germany: Springer, 2015. editor/s (773b) = Fay Huang & Akihiro Sugimoto; Event dates (773o) = 23 - 27 Nov, 2015; Parent title (773t) = Pacific-Rim Symposium on Image and Video Technology. ISSNs: 1611-3349; ; 7th Pacific Rim Symposium on Image and Video Technology ; Conference date: 23-11-2015 Through 27-11-2015",

year = "2015",

doi = "10.1007/978-3-319-30285-0_26",

language = "English",

volume = "9555",

publisher = "Springer",

pages = "319--331",

editor = "Fay Huang and Akihiro Sugimoto",

booktitle = "PSIVT 2015",

address = "United States",

url = "http://www.psivt.org/psivt2015/, https://web.archive.org/web/20160404030704/http://psivt.org/psivt2015/docs/PsivtProgramFinal.pdf, https://web.archive.org/web/20160313115108/http://www.psivt.org/psivt2015/docs/PSIVT_Handboook.pdf",

}

TY - GEN

T1 - Fusion of Foreground Object, Spatial and Frequency Domain Motion Information for Video Summarization

AU - Salehin, MD.

AU - Paul, Manoranjan

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = Germany: Springer, 2015. editor/s (773b) = Fay Huang & Akihiro Sugimoto; Event dates (773o) = 23 - 27 Nov, 2015; Parent title (773t) = Pacific-Rim Symposium on Image and Video Technology. ISSNs: 1611-3349;

PY - 2015

Y1 - 2015

N2 - Surveillance video camera captures a large amount of continuous video stream every day. To analyze or investigate any significant events from the huge video data, it is laborious and boring job to identify these events. To solve this problem, a video summarization technique combining foreground objects as well as motion information in spatial and frequency domain is proposed in this paper. We extract foreground object using background modeling and motion information in spatial domain and frequency domain. Frame transition is applied for obtaining motion information in spatial domain. For acquiring motion information in frequency domain, phase correlation (PC) technique is applied. Later, foreground objects and motions in spatial and frequency domain are fused and key frames are extracted. Experimental results reveal that the proposed method performs better than the state-of-the-art method.

AB - Surveillance video camera captures a large amount of continuous video stream every day. To analyze or investigate any significant events from the huge video data, it is laborious and boring job to identify these events. To solve this problem, a video summarization technique combining foreground objects as well as motion information in spatial and frequency domain is proposed in this paper. We extract foreground object using background modeling and motion information in spatial domain and frequency domain. Frame transition is applied for obtaining motion information in spatial domain. For acquiring motion information in frequency domain, phase correlation (PC) technique is applied. Later, foreground objects and motions in spatial and frequency domain are fused and key frames are extracted. Experimental results reveal that the proposed method performs better than the state-of-the-art method.

KW - Background modelling

KW - Motion information

KW - Phase correlation

KW - Video summarization

U2 - 10.1007/978-3-319-30285-0_26

DO - 10.1007/978-3-319-30285-0_26

M3 - Conference paper

VL - 9555

SP - 319

EP - 331

BT - PSIVT 2015

A2 - Huang, Fay

A2 - Sugimoto, Akihiro

PB - Springer

CY - Germany

T2 - 7th Pacific Rim Symposium on Image and Video Technology

Y2 - 23 November 2015 through 27 November 2015

ER -

Fusion of Foreground Object, Spatial and Frequency Domain Motion Information for Video Summarization

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this