Optical flow-based representation for video action detection - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 280

based video representation. In [ 42 ], optical flow histograms are used for characterizing the
motion of a soccer player in a soccer video. A motion descriptor based on optical flow is pro-
posed and a similarity measure for this descriptor is described. The study of Barron et al. [ 17 ]
uses optical low by spliting it into horizontal and vertical channels. The histogram is calcu-
lated on these channels. Each channel is integrated over the angularly divided bins of optical
flow vectors. In Ref. [ 14 ] , HOOF is simply used according to angular segments for each frame.
The feature vectors are constructed with these angular values and combined for all frames of
the video segment. The essential part for contribution here is the classification method. The
classification is done with a proposed novel time-series classification method including a met-
ric for comparing optical flow histograms. The study in Ref. [ 21 ] proposes an optical flow
based representation which groups the optical flow vectors of whole video segment according
to angular values. Then, average histogram is computed for each of these angular groups. The
resulting histogram is the feature vector.
In our approach, histogram-based optical flow approaches are enriched with a newly
deined velocity concept, Weighted Frame Velocity . The idea, here, is originated from the inad-
equacy of optical flow histograms for interpreting information. Using optical flow histogram
is discarded as the most important drawback of using histograms in segment representation
is that the histogram similarity does not always mean the real similarity for motion character-
ization. Optical flow vectors are divided into angular groups and according to these groups,
optical flow vectors are summed and integrated with the new velocity concept instead of a
histogram-based approach.
Estimating the optical flow vectors for each frame is the first step. Then, Equation (6) giving
the generic representation is adapted to segment representation. In this aspect, Φ is the oper-
ator defining the relations between the optical flow vectors and giving their meaning for rep-
resenting the video segment composed of the set of optical flow vectors S ( V ).
In our adaptation of the above representation to segment representation, the description of
Φ is important. The parameters used in the definition are shown in Table 1 .
Table 1
Segment Representation Model Parameters
Parameter Definition
F Set of frames in the video segment
S ( V f ) Set of optical flow vectors in frame f
S ( V f , α , β ) Set of optical flow vectors having angle between α − β in frame f
A ( α , β ) Weighted frame velocity of the whole segment direction having angle between α − β
τ f ( α , β ) Threshold function for optical flow vectors having angle between α − β in frame f
V ( r , ∠ φ ) Optical flow vector having magnitude r and angle φ
The parameters above are the basic building blocks for constructing the representation mod-
el and the descriptor operator Φ . The following definitions are done for this purpose. The
deinition of S ( V f , α , β ) is made as follows: