DeepHand – a new system for tracking the movements of hands in the virulent reality

DeepHand – a new system for tracking the movements of hands in the virulent reality
March 17 14:31 2018

DeepHand

The “arms race” of controllers in the sphere of virtual reality is in full swing. Recently in the “race” included the team of Purdue University, which developed a system of tracking hands DeepHand. The system uses a depth-scanning camera and deep-learning technology for the correct positioning of the hand in the virtual world.

The camera reads the position and the angle of the arm at various points and projects it onto the display with a special algorithm that quickly scans the database, choosing from the more than 2.5 million positions the most appropriate option.

To maximize the display of virtual motion, the program can predict possible states of the hand. The algorithm is also able to find out and display the positions of fingers and hands invisible to the camera.

In the process of creating DeepHand, researchers had to start with the recognition of gestures, gradually filling them with a database, which required a fairly powerful processor. Once all the “rough” work is completed, the system can be adapted for a normal computer.

  Categories:
view more articles

About Article Author

write a comment

0 Comments

No Comments Yet!

You can be the one to start a conversation.

Add a Comment

Your data will be safe! Your e-mail address will not be published. Also other data will not be shared with third person.
All fields are required.