Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)

Features Extraction and Selection Based on Rough Set and SVM in Abrupt Shot Detection

Authors
Yu Wu1, Jialiang Han
1Institute of Artificial Intelligence,Chongqing University of Posts and Telecommunications
Corresponding Author
Yu Wu
Available Online October 2007.
DOI
10.2991/iske.2007.35How to use a DOI?
Keywords
Rough Set, Motion information, abrupt shot, SVM
Abstract

Rough Set based reduction algorithm is taken as a method for feature selection in abrupt shot boundary detection. First, some information of macro blocks is extracted in P frame of MPEG video sequence. Then the information of the motion-activity, the type of macro blocks and the motion-distribution are got after analyzing MPEG compressed-domain. Combined these information with the difference of pixel and the difference of histogram the abrupt shot detection can be achieved. Our simulation experimental results show that the detection model combined Rough Set with SVM is effective in features selection. Some useful features for abrupt shot detection are discovered.

Copyright
© 2007, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
Series
Advances in Intelligent Systems Research
Publication Date
October 2007
ISBN
978-90-78677-04-8
ISSN
1951-6851
DOI
10.2991/iske.2007.35How to use a DOI?
Copyright
© 2007, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Yu Wu
AU  - Jialiang Han
PY  - 2007/10
DA  - 2007/10
TI  - Features Extraction and Selection Based on Rough Set and SVM in Abrupt Shot Detection
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 201
EP  - 208
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.35
DO  - 10.2991/iske.2007.35
ID  - Wu2007/10
ER  -