Robust TV Commercial Detection Based on Audiovisual Features

Shih Hung Lee; Chia H. Yeh; C. C. Jay Kuo

doi:10.1117/12.486775

Robust TV Commercial Detection Based on Audiovisual Features

Shih Hung Lee^*, Chia H. Yeh, C. C. Jay Kuo

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

Abstract

A robust TV commercial detection system is proposed in this research. Even though several methods were investigated to address the TV commercial detection problem and interesting results were obtained before, most previous work focuses on features within a short temporal window. These methods are suitable for on-line detection, but often result in higher false alarm rates as a trade-off. To reduce the false alarm rate, we explore audiovisual features in a larger temporal window. Specifically, we group shots into scenes using audio data processing, and then obtain features that are related to commercial characteristics from scenes. Experimental results are given to demonstrate the effectiveness of the proposed system.

Original language	English
Pages (from-to)	147-158
Number of pages	12
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5108
DOIs	https://doi.org/10.1117/12.486775
Publication status	Published - 2003
Externally published	Yes
Event	PROCEEDINGS OF SPIE SPIE - The International Society for Optical Engineering: Visual Information Processing XII - Orlando, FL, United States Duration: 2003 Apr 21 → 2003 Apr 21

Keywords

Audio Classification
Audiovisual Analysis
Commercial Break
Content Analysis

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.486775

Cite this

@article{6ad889335a6c4f1cb673215b2812e808,

title = "Robust TV Commercial Detection Based on Audiovisual Features",

abstract = "A robust TV commercial detection system is proposed in this research. Even though several methods were investigated to address the TV commercial detection problem and interesting results were obtained before, most previous work focuses on features within a short temporal window. These methods are suitable for on-line detection, but often result in higher false alarm rates as a trade-off. To reduce the false alarm rate, we explore audiovisual features in a larger temporal window. Specifically, we group shots into scenes using audio data processing, and then obtain features that are related to commercial characteristics from scenes. Experimental results are given to demonstrate the effectiveness of the proposed system.",

keywords = "Audio Classification, Audiovisual Analysis, Commercial Break, Content Analysis",

author = "Lee, {Shih Hung} and Yeh, {Chia H.} and {Jay Kuo}, {C. C.}",

year = "2003",

doi = "10.1117/12.486775",

language = "English",

volume = "5108",

pages = "147--158",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "PROCEEDINGS OF SPIE SPIE - The International Society for Optical Engineering: Visual Information Processing XII ; Conference date: 21-04-2003 Through 21-04-2003",

}

TY - JOUR

T1 - Robust TV Commercial Detection Based on Audiovisual Features

AU - Lee, Shih Hung

AU - Yeh, Chia H.

AU - Jay Kuo, C. C.

PY - 2003

Y1 - 2003

N2 - A robust TV commercial detection system is proposed in this research. Even though several methods were investigated to address the TV commercial detection problem and interesting results were obtained before, most previous work focuses on features within a short temporal window. These methods are suitable for on-line detection, but often result in higher false alarm rates as a trade-off. To reduce the false alarm rate, we explore audiovisual features in a larger temporal window. Specifically, we group shots into scenes using audio data processing, and then obtain features that are related to commercial characteristics from scenes. Experimental results are given to demonstrate the effectiveness of the proposed system.

AB - A robust TV commercial detection system is proposed in this research. Even though several methods were investigated to address the TV commercial detection problem and interesting results were obtained before, most previous work focuses on features within a short temporal window. These methods are suitable for on-line detection, but often result in higher false alarm rates as a trade-off. To reduce the false alarm rate, we explore audiovisual features in a larger temporal window. Specifically, we group shots into scenes using audio data processing, and then obtain features that are related to commercial characteristics from scenes. Experimental results are given to demonstrate the effectiveness of the proposed system.

KW - Audio Classification

KW - Audiovisual Analysis

KW - Commercial Break

KW - Content Analysis

UR - http://www.scopus.com/inward/record.url?scp=0344082689&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0344082689&partnerID=8YFLogxK

U2 - 10.1117/12.486775

DO - 10.1117/12.486775

M3 - Conference article

AN - SCOPUS:0344082689

SN - 0277-786X

VL - 5108

SP - 147

EP - 158

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - PROCEEDINGS OF SPIE SPIE - The International Society for Optical Engineering: Visual Information Processing XII

Y2 - 21 April 2003 through 21 April 2003

ER -

Robust TV Commercial Detection Based on Audiovisual Features

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this