Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICPR.2004.1334665
Title: Fast and robust search method for short video clips from large video collection
Authors: Yuan, J.
Tian, Q.
Ranganath, S. 
Issue Date: 2004
Source: Yuan, J., Tian, Q., Ranganath, S. (2004). Fast and robust search method for short video clips from large video collection. Proceedings - International Conference on Pattern Recognition 3 : 866-869. ScholarBank@NUS Repository. https://doi.org/10.1109/ICPR.2004.1334665
Abstract: In this paper a fast and robust method is proposed to search a large video collection for given short clips. Compared with existing video searching methods which use visual features only, our scheme performs a two-phase hierarchical matching technique using visual and audio features successively. Considering that video sampling rate (25 or 30 fps) is much lower than that of audio (8 to 48 kHz), a coarse search is implemented with sub-sampled video frames first, and then potential matches will be verified and accurately located using fine audio features. Both features are extracted directly from MPEG compressed video for computational efficiency. Experiments have been conducted on over 10.5 hours of video to search for re-occurrences of 83 TV commercials and one news lead-out clip. All the 220 instances are correctly detected with no false alarm. Our experiments also show that the proposed method is robust to variations of video bit rate, frame rate, frame size and color shifting.
Source Title: Proceedings - International Conference on Pattern Recognition
URI: http://scholarbank.nus.edu.sg/handle/10635/70298
ISBN: 0769521282
ISSN: 10514651
DOI: 10.1109/ICPR.2004.1334665
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

36
checked on Dec 6, 2017

WEB OF SCIENCETM
Citations

24
checked on Nov 18, 2017

Page view(s)

32
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.