Image Processing Reference
In-Depth Information
6 Face Tracking
The use of our MS-RNN method for face tracking relies on the fact that the skin color is in-
variant to face orientation and is insensitive to partial occlusion. Also, our system proved in-
sensitive to variations of scene conditions, such as the presence of a complex background and
uncontrolled illumination. Based on these considerations, we applied the MS-RNN method at
any frames of video sequences and the Kalman filter algorithm [ 22 ] . Kalman filtering helps
to predict the next face-detection window and smooth the tracking trajectory. Face detection
is performed within a predicted window instead of an entire image region to reduce compu-
tation costs. The x y coordinates and height of the face region are initially set to the values
given by the face-detection process, while the velocity values of the state vector are set to 1.
The face motion model used in our tracking method can be defined by the following set of
space-state equations:
where x k represents the state vector at the time k , characterized by five parameters consisting
of the x y coordinates of the center point of the face region ( c x , c y ), the velocity in the x and y
directions ( v x , v y ), and the height H k of the face-bounded region. The width of the face-bounded
region is always assumed to be 0.75 times the size of the calculated height. The transition mat-
rix, Φ , which relates the current state to the predicted state after the time interval Δ t is given
The vector z k 3 represents the face position and height observed with the observation
Search WWH ::

Custom Search