MINMAX optimal video summarization

Zhu Li; Guido M. Schuster; Aggelos K. Katsaggelos

doi:10.1109/TCSVT.2005.854230

MINMAX optimal video summarization

Zhu Li^*, Guido M. Schuster, Aggelos K. Katsaggelos

^*Corresponding author for this work

Electrical and Computer Engineering

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

90 Scopus citations

Abstract

The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth and/or power are limited. In this paper, our work is based on a MINMAX optimization formulation with viewing time, frame skip and bit rate constraints. New metrics for missing frame and video summary distortions are introduced. Optimal algorithm based on dynamic programming is presented along with experimental results.

Original language	English (US)
Pages (from-to)	1245-1256
Number of pages	12
Journal	IEEE Transactions on Circuits and Systems for Video Technology
Volume	15
Issue number	10
DOIs	https://doi.org/10.1109/TCSVT.2005.854230
State	Published - Oct 2005

Keywords

Dynamic programming
Rate-distortion optimization
Video analysis
Video summarization

ASJC Scopus subject areas

Media Technology
Electrical and Electronic Engineering

Access to Document

10.1109/TCSVT.2005.854230

Cite this

@article{cb280c369de1488fa5d4c3323f82deca,

title = "MINMAX optimal video summarization",

abstract = "The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth and/or power are limited. In this paper, our work is based on a MINMAX optimization formulation with viewing time, frame skip and bit rate constraints. New metrics for missing frame and video summary distortions are introduced. Optimal algorithm based on dynamic programming is presented along with experimental results.",

keywords = "Dynamic programming, Rate-distortion optimization, Video analysis, Video summarization",

author = "Zhu Li and Schuster, {Guido M.} and Katsaggelos, {Aggelos K.}",

note = "Funding Information: Dr. Li received a scholarship for graduate study from the Hong Kong University of Science and Technology (HKUST) in 1995.",

year = "2005",

month = oct,

doi = "10.1109/TCSVT.2005.854230",

language = "English (US)",

volume = "15",

pages = "1245--1256",

journal = "IEEE Transactions on Circuits and Systems for Video Technology",

issn = "1051-8215",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - MINMAX optimal video summarization

AU - Li, Zhu

AU - Schuster, Guido M.

AU - Katsaggelos, Aggelos K.

N1 - Funding Information: Dr. Li received a scholarship for graduate study from the Hong Kong University of Science and Technology (HKUST) in 1995.

PY - 2005/10

Y1 - 2005/10

N2 - The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth and/or power are limited. In this paper, our work is based on a MINMAX optimization formulation with viewing time, frame skip and bit rate constraints. New metrics for missing frame and video summary distortions are introduced. Optimal algorithm based on dynamic programming is presented along with experimental results.

AB - The need for video summarization originates primarily from a viewing time constraint. A shorter version of the original video sequence is desirable in a number of applications. Clearly, a shorter version is also necessary in applications where storage, communication bandwidth and/or power are limited. In this paper, our work is based on a MINMAX optimization formulation with viewing time, frame skip and bit rate constraints. New metrics for missing frame and video summary distortions are introduced. Optimal algorithm based on dynamic programming is presented along with experimental results.

KW - Dynamic programming

KW - Rate-distortion optimization

KW - Video analysis

KW - Video summarization

UR - http://www.scopus.com/inward/record.url?scp=27844564276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27844564276&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2005.854230

DO - 10.1109/TCSVT.2005.854230

M3 - Article

AN - SCOPUS:27844564276

SN - 1051-8215

VL - 15

SP - 1245

EP - 1256

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

IS - 10

ER -

MINMAX optimal video summarization

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this