A webcam is enough to produce a real-time 3-D model of a moving hand

June 11, 2018, Saarland University
Franziska Müller, Max Planck Institute for Informatics, has developed a software system that requires only the built-in camera of a laptop to produce a real-time 3-D model of a moving hand. Credit: Oliver Dietze

Capturing hand and finger movements within milliseconds is becoming increasingly important for many applications, from virtual reality to human-machine interaction and Industry 4.0. So far, its enormous technical demands have limited possible applications. Computer scientists at the Max Planck Institute for Informatics have now developed a software system involving the interaction of various neural networks that requires only the built-in camera of a laptop.

For the first time, the researchers will be presenting the program at stand G75 in hall 27 of the fair Cebit, which will take place in Hannover from June 11th onward.

When computer scientist Franziska Müller holds her in front of the laptop , the hand's virtual counterpart appears on the screen. This is overlaid by a colorful virtual hand skeleton. No matter what movements Müller's hand makes in front of the webcam, the colored bones of the model do the same. Müller demonstrates the she developed together with Professor Christian Theobalt and other researchers from the Max Planck Institute for Computer Science in Saarbrücken, Stanford University and the Spanish King Juan Carlos University. So far, no other software can do this with such a low-cost camera.

Since it works in almost every kind of filmed scene, it can be used anywhere, and thus trumps previous approaches that require a depth camera or multiple cameras. The algorithm the system uses transforms the two-dimensional information of the video image in real time into the three-dimensional movement model of the hand's bones. It is based on a so-called "," or CNN for short. The researchers have trained it to detect the bones of the hand. They have generated the necessary training data with another neural network. The result: The software calculates the exact 3-D poses of the hand's bones in milliseconds. Even if some of them are occluded, for example, by an apple held in the user's hand, the software compensates. However, the system still has trouble processing several hands working together, and solving this is the researchers' next goal.

Explore further: Tracking humans in 3-D with off-the-shelf webcams

More information: handtracker.mpi-inf.mpg.de/pro … ects/GANeratedHands/

Related Stories

Tracking humans in 3-D with off-the-shelf webcams

July 5, 2017

Many applications require that people and their movements are captured digitally in 3-D in real-time. Until now, this was possible only with expensive systems of several cameras, or by having people wear special suits. Computer ...

The hand as a joystick

May 26, 2011

You need a mouse and a keyboard, a touch-screen or a joystick to control a computer system. In the future, a new gesture command system will make it possible to use just the fingers of a hand.

Recommended for you

Security gaps identified in internet protocol IPsec

August 15, 2018

In collaboration with colleagues from Opole University in Poland, researchers at Horst Görtz Institute for IT Security (HGI) at Ruhr-Universität Bochum (RUB) have demonstrated that the internet protocol IPsec is vulnerable ...

Researchers find flaw in WhatsApp

August 8, 2018

Researchers at Israeli cybersecurity firm said Wednesday they had found a flaw in WhatsApp that could allow hackers to modify and send fake messages in the popular social messaging app.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.