Shot boundary detection using co-occurrence of global motion in video stream

We propose a method of shot boundary detection based on the co-occurrence of global motion in video stream. In addition to the conventional features based on appearance and local motion, we apply ST (Space-Time) patch analysis for detecting global motion in video stream. And then we perform shot boundary detection by constructing AdaBoost classifiers which represent the co-occurrence of global motion and the conventional features. Experimental results show that our method had 3.8% higher F-measure value than that of the conventional method for gradual shot boundary detection.

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

[2]  Eli Shechtman,et al.  Space-time behavior based correlation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Hitoshi Sakano,et al.  Abrupt Shot Boundary Detection from Video Sequence Using Motion Direction Histogram Feature , 2002, MVA.

[4]  Takeshi Mita,et al.  Joint Haar-like features for face detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

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

[6]  Akio Nagasaka,et al.  Automatic Video Indexing and Full-Video Search for Object Appearances , 1991, VDB.

[7]  Hiraku Okada,et al.  Technical Report of IEICE , 2000 .