THU-intel at rushes summarization of TRECVID 2008

Video summary is an active research field to help users to grasp a whole video's content for efficient browsing and editing. In this paper, we describe our THU-Intel rushes summarization system in TRECVID2008. In our approach, we first extract low-level audiovisual features and parse the video into shots, sub-shots and 1-second video clips. Then we remove junk video clips with color-bar, near uniform-color and clapboard frames etc. To select video clips with main objects and events, we evaluate each clip's representative score by multimodal features of color, edge, motion, and audio etc. Finally, we construct the rushes video summary by iteratively selecting the most representative video clips and removing similar ones. Extensive experiments are carried out on 40 testing rushes videos. Good results demonstrate the effectiveness of the proposed method.

[1]  Tao Wang,et al.  Caption-aided speech detection in videos , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[3]  Nobuyuki Yagi,et al.  Estimation of camera parameters from image sequence for model-based video coding , 1994, IEEE Trans. Circuits Syst. Video Technol..

[4]  Anindya Sarkar,et al.  Feature fusion and redundancy pruning for rush video summarization , 2007, TVS '07.

[5]  Paul Over,et al.  The trecvid 2007 BBC rushes summarization evaluation pilot , 2007, TVS '07.

[6]  Jun Wu,et al.  Tsinghua University at TRECVID 2004: Shot Boundary Detection and High-Level Feature Extraction , 2004, TRECVID.

[7]  Wei-Hao Lin,et al.  Clever Clustering vs . Simple Speed-Up for Summarizing BBC Rushes , 2007 .

[8]  Werner Bailer,et al.  Skimming rushes video using retake detection , 2007, TVS '07.

[9]  Chong-Wah Ngo,et al.  Rushes video summarization by object and event understanding , 2007, TVS '07.

[10]  Yung-Yu Chuang,et al.  NTU TRECVID-2007 fast rushes summarization system , 2007, TVS '07.

[11]  Wei-Hao Lin,et al.  Clever clustering vs. simple speed-up for summarizing rushes , 2007, TVS '07.

[12]  Paul Over,et al.  The trecvid 2008 BBC rushes summarization evaluation , 2008, TVS '08.

[13]  Yue Gao,et al.  THU-ICRC at rush summarization of TRECVID 2007 , 2007, TVS '07.

[14]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[16]  Shingo Uchihashi,et al.  Video Manga: generating semantically meaningful video summaries , 1999, MULTIMEDIA '99.

[17]  Aggelos K. Katsaggelos,et al.  Rate-distortion optimal video summary generation , 2005, IEEE Transactions on Image Processing.

[18]  Ba Tu Truong,et al.  Generating comprehensible summaries of rushes sequences based on robust feature matching , 2007, TVS '07.