TRECVID2005 Experiments in The Hong Kong Polytechnic University: Shot Boundary Detection Based on a Multi-Step Comparison Scheme

In this paper, we describe our experiments for TRECVID 2005 for the shot boundary detection task. Our approach is based on a multi-step comparison of the video frames. By measuring the difference between frames at varying distances apart, a distance map is generated and used to determine the existence of a transition and its type. The contents of the frames in a video shot are similar. If the difference between two consecutive frames is relatively large, a cut should happen. During a gradual transition, the difference between two consecutive frames is relatively small; therefore differences between the more distant frames are needed. While the comparative step size or the distance between two frames is equal to or larger than the length of transition, the difference between the frames during the transition will be much larger than that within the same video shot. In a distance map, a cut will appear as a triangle, a flash as two straight lines, and a gradual transition as a trapezoid. Based on the distance map, the different transitions can be detected and classified easily.

[1]  Chong-Wah Ngo,et al.  A robust dissolve detector by support vector machine , 2003, ACM Multimedia.

[2]  Ramin Zabih,et al.  A feature-based algorithm for detecting and classifying production effects , 1999, Multimedia Systems.

[3]  Zheng Tan,et al.  A unified shot boundary detection method based on linear prediction with Bayesian cost functions , 2005, Proceedings of 2005 IEEE International Workshop on VLSI Design and Video Technology, 2005..

[4]  Rainer Lienhart,et al.  Reliable dissolve detection , 2001, IS&T/SPIE Electronic Imaging.

[5]  Zheng Tan,et al.  An efficient scene break detection based on linear prediction , 2004, Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004..

[6]  Jesús Bescós,et al.  Real-time shot change detection over online MPEG-2 video , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  Christian Petersohn.  Fraunhofer HHI at TRECVID 2004: Shot Boundary Detection System , 2004, TRECVID.

[8]  Charles A. Bouman,et al.  Storage and Retrieval for Image and Video Databases VII , 1998 .

[9]  Kyoungro Yoon,et al.  Dissolve transition detection algorithm using spatio-temporal distribution of MPEG macro-block types (poster session) , 2000, ACM Multimedia.

[10]  Tie-Yan Liu,et al.  A new cut detection algorithm with constant false-alarm ratio for video segmentation , 2004, J. Vis. Commun. Image Represent..

[11]  In So Kweon,et al.  Detecting cuts and dissolves through linear regression analysis , 2003 .

[12]  Alan Hanjalic,et al.  Shot-boundary detection: unraveled and resolved? , 2002, IEEE Trans. Circuits Syst. Video Technol..

[13]  Soo-Chang Pei,et al.  Efficient MPEG Compressed Video Analysis Using Macroblock Type Information , 1999, IEEE Trans. Multim..

[14]  Nuno Vasconcelos,et al.  Statistical models of video structure for content analysis and characterization , 2000, IEEE Trans. Image Process..

[15]  Rainer Lienhart,et al.  Comparison of automatic shot boundary detection algorithms , 1998, Electronic Imaging.

[16]  Adnan M. Alattar.  Detecting and compressing dissolve regions in video sequences with a DVI multimedia image compression algorithm , 1993, 1993 IEEE International Symposium on Circuits and Systems.

[17]  Boon-Lock Yeo,et al.  Rapid scene analysis on compressed video , 1995, IEEE Trans. Circuits Syst. Video Technol..

[18]  Atreyi Kankanhalli,et al.  Automatic partitioning of full-motion video , 1993, Multimedia Systems.

[19]  Patrick Bouthemy,et al.  A unified approach to shot change detection and camera motion characterization , 1999, IEEE Trans. Circuits Syst. Video Technol..

[20]  Chong-Wah Ngo,et al.  Video partitioning by temporal slice coherency , 2001, IEEE Trans. Circuits Syst. Video Technol..