One of the challenges Metaverse is to identify a person after the aesthetic changes that may occur there, for this reason, a group of researchers has developed a system to recognize someone without scanning their face, it is only necessary to body movements.

Those responsible for this project are scientists from the University of Berkeley, Germany’s RWTH Aachen and the company Unanimous AI.

“We’ve known for a long time that movement reveals information about people, but recent research has shown that movement patterns are so unique to an individual that they can be biometrically identifiable, just like face or hand recognition. Fingerprints,” Vivek. Nair, one of the authors of the study, told The Register about this.

You may be interested in: Video | Mark Zuckerberg tested new virtual reality glasses

How does identification work?

According to researchers, studies dating back to the 1970s show that people can recognize a friend based on their body movements. So they took this idea as the basis of a project to determine how transferable it could be Metaverse And know who is behind the avatar.

Biomechanics It is a feature that each person has, just like a footprint or a face, which is why it was one of the techniques used in the project.

You may also be interested in: ChatGPT: This was the first virtual audience in Metaverse

To achieve these results, they took 55,541 users and trained the recognition model for 5 minutes per person, collecting all possible data. However, they claim that for a company with a large budget, this process will be much more efficient.

After training, they were able to identify the analyte in 10 seconds with 73.20% accuracy, but when they extended the time to 100 seconds, it increased to 94.33%. So, in just a minute and a half, they were able to recognize a person in metaversion just by seeing their hands and head movements, without seeing their face.

The virtual space they used for the experiment was the Beat Saber game and the Meta Quest 2 glasses. In addition, they obtained a total of 2.66 million records played by users to compile a data set of 3.96 TB after 713,000 game sessions.

You may be interested: more than half of the world’s population wants to watch movies and play games in Metaverse

This large amount of data was key because they needed to look at different aspects of the body, such as the orientation of the head and hands, the time they reacted to game stimuli, performance and accuracy.

Information that can be obtained thanks to the advancement of virtual reality glasses, which allows you to estimate the height, height, length of the arms and the distance between the eyes, which provides special characteristics of the person.

You may also be interested in: They create the first metaverse to save Afro-Colombian culture and traditions

“It really changes the way we think about ‘privacy’ in the metaverse, because just by moving around in VR… you could identify yourself!” Nair said.

Finally, the project opens doors to new forms of knowledge within metaverse, However, it also evaluates the privacy policies of users in these spaces.