Gesture recognition in cooking video based on image features and motion features using Bayesian network classifier - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 320

(4)
where SC is status changing, TU is tool using, CU is container using, FU is food using, Hd is
hand, and Hm is Human.
FIGURE 2 The second Bayesian network in our method.
The last BN represents the possibility of an action based on motion features of sequence of
images surround the current frame.
(5)
where MF is motion feature.
The probability of the i ith action class calculated by the first BN is called P NEXT ( A i ), by the
second BN is called P IMAGE ( A i ), and by the last one is called P MOTION ( A i ). We can compute the
probability of an action label based on P NEXT and P IMAGE only by multiply probabilities, or P NEXT
and P MOTION . After that, we combine these probability values to obtain the probability of the i th
action
(6)