A segment-based advertisement search method from TV stream

Author

Zhao, Zhicheng ; Liu, Xiaodan

Author_Institution

Beijing Univ. of Posts & Telecommun., Beijing, China

Volume

2

fYear

2010

fDate

21-24 May 2010

Abstract

Searching of video clip from TV streams has significant commercial values, for example, the application of advertisement tracking in different TV channels. In this paper, a segment-based advertisement searching method is proposed. Robust visual features are first extracted to overcome some video transformations, and then two search strategies are presented for long AD clips and short ones. The experimental results indicate that the average search time of one query clip from a 24-hour TV stream is about 1 second, and the mean recall for 9 channels exceeds 98% while 100% precision is achieved. The evaluation results of copy detection task at TRECVID show the robustness and effectiveness.

Keywords

content-based retrieval; copyright; television; video retrieval; TRECVID; TV stream; copy detection task; query clip; robust visual features; segment based advertisement search method; video clip searching; video transformations; Colored noise; Copyright protection; Feature extraction; Gunshot detection systems; Histograms; Monitoring; Robustness; Search methods; Streaming media; TV; Advertisement; TV stream; copy detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Future Computer and Communication (ICFCC), 2010 2nd International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-5821-9

Type

conf

DOI

10.1109/ICFCC.2010.5497581

Filename

5497581