Generic Summarization Technology for Consumer Video

This paper addresses automatic summarization technology for efficiently browsing video compressed by MPEG, which is a widely used for various consumer applications. By analyzing semantically important low- and mid-level features on compressed domain, the proposed method can universally summarize the MPEG video in the form of either video skim or highlight. Since all the summarization processes are performed completely on compressed domain, very fast summarization is achieved; only 20% of real-time playback in the case of SDTV. We develop the MPEG video summarization software which is capable of summarizing video and editing automatically created summary video.

[1]  A. Murat Tekalp,et al.  Two-stage hierarchical video summary extraction to match low-level user browsing preferences , 2003, IEEE Trans. Multim..

[2]  Masaru Sugano,et al.  MPEG content summarization based on compressed domain feature analysis , 2003, SPIE ITCom.

[3]  Anoop Gupta,et al.  Automatically extracting highlights for TV Baseball programs , 2000, ACM Multimedia.

[4]  Wolfgang Effelsberg,et al.  Video abstracting , 1997, CACM.

[5]  Xin Liu,et al.  Video summarization with minimal visual content redundancies , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[6]  Regunathan Radhakrishnan,et al.  Motion activity-based extraction of key-frames from video shots , 2002, Proceedings. International Conference on Image Processing.

[7]  Bernard Mérialdo,et al.  Using content models to build audio-video summaries , 1998, Electronic Imaging.

[8]  Tsuhan Chen,et al.  Multimedia content classification using motion and audio information , 1997, Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97.

[9]  Noboru Babaguchi,et al.  Generation of personalized abstract of sports video , 2001, IEEE International Conference on Multimedia and Expo, 2001. ICME 2001..

[10]  Qian Huang,et al.  Automated generation of news content hierarchy by integrating audio, video, and text information , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[11]  Alan Hanjalic,et al.  An integrated scheme for automated video abstraction based on unsupervised cluster-validity analysis , 1999, IEEE Trans. Circuits Syst. Video Technol..

[12]  Akio Yoneyama,et al.  Universal scene change detection on MPEG-coded data domain , 1997, Electronic Imaging.

[13]  Shih-Fu Chang,et al.  Structural and semantic analysis of video , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).