Segmentation in Soccer Video Based on Fusion Algorithm

DOI

10.2991/icmt-13.2013.62How to use a DOI?

Keywords

shot boundary detection·shot segmentation·sliding window·histogram·dual thresholds.

Abstract

According to the practical application of soccer video, the characteristics of the data structure and the shot conversion methods of soccer videos are described. A method of shot segmentation in soccer video based on fusion algorithm is proposed. In this method, the 2 histogram match based on gray histogram, sliding window algorithm with adaptive threshold and double sliding windows algorithm are combined to detect and segment the shot boundary. Experiment results show that the average recall rate of cut shot is 96.6% and the average precision rate is 94.9%; The average recall rate of gradual shot is 79.5% and the average precision rate is 81.4%.

Copyright

© 2013, 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  - Zhang Qiao
AU  - Shi Ping
PY  - 2013/11
DA  - 2013/11
TI  - Segmentation in Soccer Video Based on Fusion Algorithm
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 503
EP  - 508
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.62
DO  - 10.2991/icmt-13.2013.62
ID  - Qiao2013/11
ER  -