tracking
provides information about the spatial coordinates of a person's point of attention in real-time using the distance to the
, the position of the head, and the pupil of the
. The
attempts at
tracking began at the end of the 19th century by a professor of psychology and education at Western Pennsylvania University to develop an effective
of the reading process when learning a language. () Nowadays,
tracking
has found application in many fields, including medicine, psychology, marketing, and simulators.().
ready-made solutions already exist, they have some disadvantages: the need for special equipment (Tobii
Tracker), high cost (Tobii Aware), or dependence on external
.
research is aimed at creating a
tracking
accessible to everyone who has devices with a reasonable
.
,
will find application among the audience using computers, laptops, and mobile
. According to Drewes H. (),
tracking already helps motor impaired people interact with a computer, and for ordinary people, it will make it more comfortable,
, when typing text or as an alternative to a mouse or touchpad for mobile
. Commercially successful areas,
as the video game market, are
interested in the emergence of a mass
tracking
. Veronica S. claims that "Recent innovations in the video game industry include alternative input modalities to provide an enhanced, more immersive user experience.
,
control has recently been explored as an input modality in video games." ().
to the wide application, computers and mobile
have several other advantages: high computing power, high-resolution cameras, and their static position on the device, which allows for high-precision calibration ().
, the development of an accurate
tracking
requires solving two critical problems: unstable
and poor image quality from the front
. Due to the lack of infrared optical sensors in ordinary cameras, which provides robustness inexpensive devices (Tobii
Tracker 5) to changes in shooting environment
, the accuracy of
estimation will be affected by lighting,
defocusing, as well as through view and scale changes. (). According to Shreya G., appearance-based and model-based methods are used in the development of
-tracking algorithms. (). Appearance-based models
a large amount of data and depend on the
of collecting
data (laboratory or in the wild),
they are extremely sensitive to changes in light and noise in the image ().
, model-based algorithms, according to Anuradha K., "
a geometric model of the human
to estimate the center of the cornea, optical and visual axes of the
and estimate the
coordinates as points of intersection where the visual axes meet the scene"().
, the model-based
will be used to solve the problem with inconsistent
.
, the model-based
is extremely dependent on the
resolution, which does not allow for the high accuracy of the
. According to Fukuda T. () to reduce the cost of budget devices
as laptops and
, manufacturers
cheap
modules whose resolution is too low to
the
with free head movements and independent face distance from the
. To solve
problem, the
will
the SRGAN model ().