引用本文: | 陈剑赟,李云浩,吴玲达,等.辅助足球视频切分的音频自动分类与分段[J].国防科技大学学报,2004,26(6):49-53.[点击复制] |
CHEN Jianyun,LI Yunhao,WU Lingda,et al.Automatic Audio Classification and Segmentation for Soccer Video Structuring[J].Journal of National University of Defense Technology,2004,26(6):49-53[点击复制] |
|
|
|
本文已被:浏览 6290次 下载 5181次 |
辅助足球视频切分的音频自动分类与分段 |
陈剑赟, 李云浩, 吴玲达, 老松扬, 白亮 |
(国防科技大学 人文与管理学院,湖南 长沙 410073)
|
摘要: |
视频伴随音轨的自动分类与分段是辅助视频切分的一种有效手段。从足球视频的特征入手,归纳总结出足球视频中三类主要的音频类型,既而提出了基于HMM并且结合一定平滑策略的音频自动分类和分段的框架,在实现音频分类分段的同时完成了足球视频的切分。初步的实验结果验证了该方法的有效性和鲁棒性。 |
关键词: 音频分类与分段 HMM 足球视频 视频切分 |
DOI: |
投稿日期:2004-06-28 |
基金项目:国家自然科学基金资助项目(60473117) |
|
Automatic Audio Classification and Segmentation for Soccer Video Structuring |
CHEN Jianyun, LI Yunhao, WU Lingda, LAO Songyang, BAI Liang |
(College of Humanities and Management,National Univ. of Defense Technology,Changsha 410073, China)
|
Abstract: |
Automatic classification and segmentation of the sound track is an effective approach for video structuring. We use this method to parse soccer video. Firstly, based on the characteristics of soccer video, the paper summarizes three audio classes for soccer video, namely game-audio, advertisement-audio and studio-audio. Then it proposes a framework of audio classification and segmentation using Hidden Markov Model and combining some smoothing rules. We develop a 26-coefficients feature stream for HMM model. And the experimental studies indicate that the proposed framework is effective and robust. |
Keywords: audio classification and segmentation HMM soccer video video structuring |
|
|
|
|
|