| 融合视音频特征的影片摘要生成方法 |
| |
| 引用本文： | 栾悉道,谢毓湘,李琛,牛晓.融合视音频特征的影片摘要生成方法[J].计算机应用研究,2017,34(1). |
| |
| 作者姓名： | 栾悉道 谢毓湘 李琛 牛晓 |
| |
| 作者单位： | 长沙学院,国防科技大学,国防科技大学,国防科技大学 |
| |
| 基金项目： | 国家自然科学基金资助项目 |
| |
| 摘 要： | 提出了融合视音频特征的影片摘要生成算法。以特写人脸检测、紧张、激烈镜头检测作为选取重要视频片段的依据。针对影片语音端点难以检测的问题，利用影片字幕文件提取影片语音首尾时间以及语音内容，从而实现了影片语音端点的准确检测。实验证明，该方法生成的影片摘要具有较好的有效性。
|
| 关 键 词： | 视频摘要 人脸检测 端点检测 视音频特征融合 |
| 收稿时间： | 2015/11/11 0:00:00 |
| 修稿时间： | 2016/11/29 0:00:00 |
A Movie Summarization Method Based on Audio-Visual Feature Fusion |
| |
| Luan Xidao,Xie Yuxiang,Li Chen and Niu Xiao.A Movie Summarization Method Based on Audio-Visual Feature Fusion[J].Application Research of Computers,2017,34(1). |
| |
| Authors: | Luan Xidao Xie Yuxiang Li Chen and Niu Xiao |
| |
| Affiliation: | Changsha Univeristy,,National Univeristy of Defense Technology,National Univeristy of Defense Technology |
| |
| Abstract: | A movie summarization method based on audio-visual feature fusion is proposed. In this paper, we choose video clips which have close-up faces and atwitter shots as the important clips. To solve the problem of difficulty in movie speech endpoint detection, a method of speech endpoint detection based on subtitles of motion pictures is introduced, which can detect the start and end time of captions exactly. Compared with other summarization algorithms, the proposed method is proved to be effective for movie summarization. |
| |
| Keywords: | video summarization face detection endpoint detection audio-visual feature fusion |
|
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
|
