A Novel Sports Video Logo Detector Based on Motion Analysis

Replays are key cues for events detection in sport videos since they are the immediate consequence of highlights or important events happened in sports. In many sports videos, replays are usually sandwiched with two identical logo transitions, prompt the beginning and end of a replay. A logo transition is a kind of special digital video effects, usually contains 12-35 consecutive frames, describe a flying or variable object. In this paper, a novel automatic logo detection approach is proposed. It contains two main stages: a logo transition template is automatically learned by dynamic programming and unsupervised clustering, a key frame is also extracted; then the extracted key frame and the learned logo template are used jointly to detect logos in sports videos. The optical flow features are used to depict the motion characteristics of the logo transitions. Experiments on different types of sports videos show that the proposed approach can reliably detect logos in sports videos efficiently.

[1]  Baoxin Li,et al.  Automatic detection of replay segments in broadcast sports programs by detection of logos in scene transitions , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Surya Nepal,et al.  Automatic detection of 'Goal' segments in basketball videos , 2001, MULTIMEDIA '01.

[3]  Harry Shum,et al.  Generic slow-motion replay detection in sports video , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[4]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[5]  Qi Tian,et al.  Mean shift based video segment representation and applications to replay detection , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  S. B. Needleman,et al.  A general method applicable to the search for similarities in the amino acid sequence of two proteins. , 1970, Journal of molecular biology.

[7]  Yi-Ping Phoebe Chen,et al.  The power of play-break for automatic detection and browsing of self-consumable sport video highlights , 2004, MIR '04.

[8]  Peter J. L. van Beek,et al.  Detection of slow-motion replay segments in sports video for highlights generation , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[9]  David S. Doermann,et al.  Detection of slow-motion replay sequences for identifying sports videos , 1999, 1999 IEEE Third Workshop on Multimedia Signal Processing (Cat. No.99TH8451).

[10]  Peter H. Sellers,et al.  An Algorithm for the Distance Between Two Finite Sequences , 1974, J. Comb. Theory, Ser. A.

[11]  Hanqing Lu,et al.  Replay detection in broadcasting sports video , 2004, Third International Conference on Image and Graphics (ICIG'04).

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

[13]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .