Information Technology Reference
In-Depth Information
Fig. 5.2 Eye detection algorithm: limitations due to vertical angle change. ( a ) Head tilting
forward—eyes still located properly. ( b ) Head tilting forward—eyes lost in the following frame
Fig. 5.3
Successful initial face and eyes detection
After proper positioning of the cameraphone, the main detection algorithm will
locate the drivers face and consecutively drivers eyes. Figure 5.3 shows typical
successful initial face and eyes detection.
In certain circumstances, when the phone position is off or the lighting conditions
are significantly brighter or darker then normal, the system might not be able to
initially locate face and eyes of the driver. In those cases, additional drivers help
might be requested to manually extrapolate locations of key components. Driver
will be exposed to very simple user interface where he will point towards location
of his/her face by simply touching the area of the screen where face is located.
He/she might also be required to keep their eyes closed and consequently open for
certain duration of time in order to allow system to learn how to distinguish between
those two states, a process that is explained in more detail in section “Eye Model
Analysis”.
Once all the required information has been acquired, the extraction of key
features begins. This process takes a few seconds, during which each camera frame
Search WWH ::




Custom Search