Multi dimension query of sports video for cloud service environment

DOI

10.2991/icence-16.2016.161How to use a DOI?

Keywords

Sports Video, Least Squares Support Vector Machine, Divider Design, Features Extraction, Evidence Theory

Abstract

A kind of sports video classification method (D-S PT-LSSVM) combined with least squares support vector machine (LSSVM) and evidence theory has been proposed for the shortages of low accuracy rate and weak stability etc. of sports video with single features. First, four kinds of features of color, texture, brightness and motion vectors reflecting sports video category have been extracted; second, basic probability assignment has been constructed by taking the LSSVM initial category results of four kinds of single features as independent evidence and finally simulation experiment has been made. Simulation results have shown that the accuracy rate of sports video classification of D-S PT-LSSVM is as high as 97.9%; compared with reference method, the specific sports video classification of D-S PT-LSSVM is with advantages of high accuracy rate and good stability etc.

Copyright

© 2016, 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)

TY  - CONF
AU  - Kun Lv
AU  - Qingbin Wang
PY  - 2016/09
DA  - 2016/09
TI  - Multi dimension query of sports video for cloud service environment
BT  - Proceedings of the 2nd International Conference on Electronics, Network and Computer Engineering (ICENCE 2016)
PB  - Atlantis Press
SP  - 877
EP  - 882
SN  - 2352-538X
UR  - https://doi.org/10.2991/icence-16.2016.161
DO  - 10.2991/icence-16.2016.161
ID  - Lv2016/09
ER  -