期刊文献+

武打片中的动作场景检测方法 被引量:5

An Approach to Action Scene Detection in Martial Arts Movies
下载PDF
导出
摘要 本文提出了一种简单有效的方法检测武打片中的动作场景:首先根据动作场景的节奏特点,从影片层次出发,使用镜头长度和MPEG-7运动活力描述符定义了镜头的步调函数来度量节奏,由此定位快节奏区域,找到动作场景的大体位置;之后根据动作场景的内容发展特点,从镜头层次出发,分析快节奏区域及周边的镜头的内容,根据视觉特征确定动作场景的边界点.两个层次(影片和镜头)信息的充分利用使得方法简单易操作,基于压缩视频的处理方法提高了运算速度,实验结果表明了该检测方法的有效性. This paper presents a simple and efficient approach to action scene detection in martial arts movies. Quick tempo is an important movie-level character for action scene. A shot pace function defined by shot length and MPEG-7 motion activity is used to measure the tempo. From the shot pace change curve, it is easy to locate the rough position of action scene. According to the character of action scene development, action scene boundary is detected at the shot level by analyzing the visual contents of shots within and around the above rough region. Two clues from the movie-level and shot-level make the method simple;working on compressed video directly makes the method very fast. Experimental resuits based on real-world movies verify its efficiency.
出处 《电子学报》 EI CAS CSCD 北大核心 2006年第5期915-920,共6页 Acta Electronica Sinica
基金 国家自然科学基金(No.60305009) 北京交通大学校基金(No.2004SM013)
关键词 动作场景 节奏 步调函数 压缩视频 action scene tempo pace function compressed video
  • 相关文献

参考文献16

  • 1Arijon D.Grammar of the film language[M].Silman-James Press,1976:483. 被引量:1
  • 2Swanberg D,Shu CF,Jain R.Knowledge guided parsing in video databases[A].Proc.of SPIE Conf.on Storage and Retrieval for Image and Video Databases[C].San Jose:SPIE Press,1993.173-187. 被引量:1
  • 3Yeung MM,Yeo B L,Liu B.Segmentation of video by clustering and graph analysis[J].Computer Vision and Image Understanding,1998,71(1):94-109. 被引量:1
  • 4Ngo CW,Ma YF,Zhang HJ.Automatic video summarization by graph modeling[A].Proc.Of IEEE ICCV'03[C].Washington:IEEE Computer Society Press,2003.104-109. 被引量:1
  • 5Sundaram H,Chang SF.Computable scenes and structures in films[J].IEEE Trans.on Multimedia,2002,4(4):482-491. 被引量:1
  • 6Chen SC,Shyu ML,Liao W,et al.Scene change detection by audio and video clues[A].Proc.of IEEE ICME'02[C].Lausanne:IEEE Computer Society Press,2002.365-368. 被引量:1
  • 7Alatan AA,Akansu AN,Wolf W.Multi-modal dialog scene detection using hidden markov models for content-based multimedia indexing[J].Multimedia Tools and Applications,2001,14(2):137-151. 被引量:1
  • 8Xie L,Xu P,Chang SF,et al.Structure analysis of soccer video with domain knowledge and hidden markov models[J].Pattern Recognition Letters,2004,25(7):767-775. 被引量:1
  • 9Chang P,Han M,Gong YH.Extract highlights from baseball game video with hidden markov models[A].Proc.of ICIP'02[C].New York:IEEE Press,2002.609-612. 被引量:1
  • 10Chen L,Ozsu M.Rule-based scene extraction from video[A].Proc.of IEEE ICIP'02[C].New York:IEEE Press,2002.737-740. 被引量:1

二级参考文献14

  • 1Gong Yihong, Sin Lim Teck, Chuan Chua Hock, et al.Automatic parsing of TV soccer programs [A]. In: Proceedings of International Conference on Multimedia Computing and Systems, Washington, DC, 1995. 167~174 被引量:1
  • 2Rui Yong, Gupta Anoop, Acero Alex. Automatically extracting highlights for TV baseball programs [A]. In: Proceedings of ACM Multimedia 2000, Los Angeles, CA, 2000. 105~ 115 被引量:1
  • 3Nam Jeho, Alghoniemy Masoud, Tewfik Ahmed H. Audiovisual content-based violent scene characterization [A]. In:Proceedings of IEEE International Conference on Image Processing, Chicago, 1998, 1:353~357 被引量:1
  • 4Koegel John F, Rutledge John L, Miner Richard, et al.Supporting realtime analysis of multimedia communication sessions [J]. SPIE Enabling Technologies for High-Bandwidth Applications, 1992, 1785:8~11 被引量:1
  • 5Peter Noll. Mpeg digital audio coding [J]. IEEE Signal Processing Magazine, 1997, 14(5): 59~81 被引量:1
  • 6Li S Z, Guo G D. Content-based audio classification and retrieval using SVM learning [A]. In: Proceedings of IEEE Pacific-Rim Conference on Multimedia, Sydney, Australia,2000. 23~28 被引量:1
  • 7Liu W Z, Huang J. Multimedia content analysis using audio and visual information [J]. IEEE Signal Processing Magazine,2000, 17(6): 12~36 被引量:1
  • 8Vapnik V. The Nature of Statistical Learning Theory [M].New York: Springer, 1995 被引量:1
  • 9Burges C J C, A tutorial on support vector machines for pattern recognition [J]. Data Mining, and Knowledge Discovery,1998, 2(2): 121~167 被引量:1
  • 10Hyun Jin Park, Yang Hyun Seung. Invariant object detection by evidence accumulation and Gabor features [J]. Pattern Recognition Letters, 2001, 22(8): 869~882 被引量:1

共引文献1

同被引文献16

引证文献5

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部