引用本文: | 卜江,郑彬,廖东升.一种鲁棒的场地球类视频中的球门探测方法[J].国防科技大学学报,2013,35(5):85-90.[点击复制] |
BU Jiang,ZHENG Bin,LIAO Dongsheng.A robust goalmouth detection method in field-ball game video[J].Journal of National University of Defense Technology,2013,35(5):85-90[点击复制] |
|
|
|
本文已被:浏览 7173次 下载 6048次 |
一种鲁棒的场地球类视频中的球门探测方法 |
卜江, 郑彬, 廖东升 |
(国防科技大学 人文与社会科学学院,湖南 长沙 410074)
|
摘要: |
在场地球类视频中,球门常常会伴随着精彩片段而出现。因此,球门探测是体育视频摘要的基础,同时也是视频高层语义概念探测的研究热点。目前,利用机器学习方法进行视频中的对象探测是非常有前途的研究领域。基于此,提出一种基于模糊决策树的球门探测算法,用来探测场地球类视频中球门帧的出现,为了提高分类准确性,在模糊决策树训练的过程中加入了平衡处理。实验结果表明,与基于阈值和决策树的算法相比,该算法可以得到更好的分类结果(F-measure>95%),并且可以从所建立的树中推导出模糊规则来解释分类模型。 |
关键词: 球门探测 模糊决策树 场地球类视频 平衡处理 |
DOI: |
投稿日期:2013-03-28 |
基金项目:国防科技大学校预研项目(JZ12-08-08);国家部委资助项目;国家自然科学基金资助项目 |
|
A robust goalmouth detection method in field-ball game video |
BU Jiang, ZHENG Bin, LIAO Dongsheng |
(College of Humanities and Social Sciences, National University of Defense Technology, Changsha 410073, China)
|
Abstract: |
Recently, goalmouth detection has become the basis of highlight summarization and a hot topic in high-level semantic concept detection, as the appearance of goalmouth indicates a high likelihood of exciting action in field-ball game video. In addition, machine learning for object detection is a promising research frontier. A robust method is proposed to detect the presence of goalmouth frame in field-ball game video based on fuzzy decision trees. Balance process was added in training procedure. The experimental results show that our algorithm (F-measure>95%) can improve the classification performance in comparison with the threshold-based algorithm and the decision tree-based algorithm. Fuzzy rules can also be easily deduced from the constructed tree to interpret the classification model. |
Keywords: goalmouth detection fuzzy decision tree field-ball game video balance process |
|
|