Indexing, Object Segmentation, and Event Detection in News and Sports Videos - Multimedia Database Retrieval: Technology and Applications - page 198

Fig. 7.21 Comparison of motion vector magnitudes for different types of play

7.6.1.1 Play Event Detection Algorithm

The primary objective of the algorithm is to detect the key frame that can be used
as the starting point of the play event in the shot. The end point of the play event
does not have to be extracted, as in most American football video shots containing
play events, the shot usually terminates at the end of the play. In order to extract the
intensity of the motion descriptor, MPEG-1 video motion vectors are used. Only the
motion vectors from the P frames are analyzed in order to speed up the processing
time. In MPEG-7, the motion activity descriptor represents the standard deviation
of the motion vector magnitudes within a frame. This is given by the following
equation.

2

N
1

( MAG mv − μ )

∑ mv

˃ mv = (7.42)

N

where MAG mv is the magnitu de of t he motion vector with coordinates ( x , y ) , and

x 2

is calculated by MAG mv = + y 2 . μ mv is the mean of the motion vector and is

defined as:

N
1 MAG mv
N

μ mv = ∑

(7.43)

where N is the number of macro-blocks that have a motion vector coded in
the MPEG-1 stream. The number N varies from frame to frame, as not all the