C0NTR0LL: Gesture Recognition and Action Management System in Digital Games
Pose Estimation; Digital games; Virtual Rehabilitation; Machine learning.
In digital games, control is the element that integrates the player into the virtual world. With the emergence of recent input devices, it has become possible to capture human pose gestures through sensors, allowing a new form of interaction between manmachine. The application of machine learning techniques in the context of human pose
capture is highlighted and has been addressed in several areas. Pose recognition techniques
and devices have demonstrated great artifice when used in simulation in rehabilitation.
However, many of these devices have their limitations, which normally do not include the
health profile, often making their use in the context of rehabilitation unfeasible. Based
on this context, this work presents or creates a system that allows players and health
professionals the possibility to manage movements in games using a complete corporate
gesture experience, allowing these games to be adapted to the objectives expected by each
user profile. The results of this research contribute to future innovations, in the theoretical
and practical fields, promoting the development of serious digital games with different
objectives. In view of the results presented, consider whether C0NTR0LL shows the results
potentially used.