高级检索
    于俊清, 何欢欢, 何云峰. 利用情感激励提取足球视频精彩镜头[J]. 计算机研究与发展, 2010, 47(10): 1823-1831.
    引用本文: 于俊清, 何欢欢, 何云峰. 利用情感激励提取足球视频精彩镜头[J]. 计算机研究与发展, 2010, 47(10): 1823-1831.
    Yu Junqing, He Huanhuan, He Yunfeng. Highlights Extraction for Soccer Video Based on Affection Arousal[J]. Journal of Computer Research and Development, 2010, 47(10): 1823-1831.
    Citation: Yu Junqing, He Huanhuan, He Yunfeng. Highlights Extraction for Soccer Video Based on Affection Arousal[J]. Journal of Computer Research and Development, 2010, 47(10): 1823-1831.

    利用情感激励提取足球视频精彩镜头

    Highlights Extraction for Soccer Video Based on Affection Arousal

    • 摘要: 足球视频精彩镜头的提取是足球视频检索和摘要生成的关键技术,有着很高的学术研究价值和广泛的应用前景.在系统分析现有足球视频精彩镜头提取方法的基础上,从观众情绪波动的视角出发,以Hanjalic情感曲线的理论思想为基础,设计了一个基于情感激励模型提取足球视频精彩镜头的系统.针对足球视频构建了一种新的特征——镜头激烈度,用此特征取代运动强度特征建立情感激励模型,从而改进了Hanjalic情绪激励曲线的生成方法,提高了系统的查全率、准确率和计算性能.结合足球领域知识,实现了更准确的精彩镜头定位方法,可以根据用户的实际观看时间自动筛选精彩镜头.实验结果验证了算法具有很好的检测效果.

       

      Abstract: In recent years, the football video retrieval and abstract techniques develop more and more rapidly. As one of the key technologies of video retrieval and abstract for soccer video, highlights extracting technique has high academic research value and wide application perspective. Based on the analysis of existing football video research methods, it is proposed that a highlights extracting system using affection arousal modeling from the angle of audiences emotional change, which is based on the theory of Hanjalics affection curve. The arousal features are extracted from football video to construct arousal modeling and generate arousal curve, then highlights can be extracted based on arousal curve. Compared with Hanjalics work, some improvements and further research are proposed based on Hanjalics excitement curve. A new feature, named shot intensity, is designed to construct arousal modeling instead of the motion intensity feature. This has improved the systems recall rate, accuracy and computing performance. Domain knowledge is applied in the highlights shot locating process to achieve high accuracy, and the highlights can also be automatically filtered according to the users required watching time. The experimental results indicate that the proposed approach is effective and the shot intensity can replace motion intensity to construct arousal model and the proposed algorithms are effective.

       

    /

    返回文章
    返回