Indexing, Object Segmentation, and Event Detection in News and Sports Videos - Multimedia Database Retrieval: Technology and Applications - page 203

Fig. 7.24 Motion feature

map

A 2D feature map is created by combining the two motion activity descriptors.
The motivation behind this is to create a feature set that can model both the intensity
of motion and the direction of motion, thus discriminating between high intensity
motion in the upward direction versus high intensity motion in the lateral direction.
As can be seen from Fig. 7.24 , the feature map provides a unique representation of
only 12 8 dimensions for both the intensity and direction of motion. In the feature

map, blue color corresponds to low values and red color corresponds to high values.

×

7.6.2.2 Audio Features Mapping

The motivation behind using audio descriptors is due to the fact that most sports
have a certain vocabulary associated with each event. Almost all the announcers
will utilize some of the vocabulary to describe similar events. Therefore we wanted
a compact representation of audio characteristics to describe the general tone and
pitch of the announcer. The objective is to analyze the similarity in the spoken
sounds between similar events.
Three MPEG-7 basic spectral audio features were used to achieve our objective,
namely: Audio Spectrum Envelope (ASE), Audio Spectrum Centroid (ASC) and
Audio Spectrum Flatness (ASF).
The ASE descriptor represents the power spectrum of an audio signal and can
be calculated by taking the Fast Fourier transform (FFT) of the audio signal which
is windowed using a Hamming window with an overlap of 50 % between adjacent