Technology is all around us; devices capable of tracking us, listening to us, and observing us are everywhere. Many people don’t even notice their presence anymore because it has become an integral part of our lives.
A team of computer scientists at Germany’s Saarland University explores the dynamics of the relationship by building a creepy, human-eye-like webcam prototype called the Eyecam. On top of looking like a human eye, the webcam also realistically imitates unconscious eye movements like blinking or moving the eyebrow.
The project’s main objective is to spark up a conversation around sensing devices and highlight the privacy issues that these devices can bring up. “We want to draw attention to the fact that we are surrounded by sensing devices every day. That raises the question of how that affects us,” said Marc Teyssier, who led the team.
Eyecam is made up of three main parts:
- The (mechanical) musculoskeletal system
- The skin layer
- The eyeball with a seeing pupil, actuated eyelids, and an actuated eyebrow
Within the eyeball is a mini 720p/60fps video camera linked to a Raspberry Pi Zero board and six servo-motors positioned accurately to imitate the different eye muscles. These motors reproduce the movement of the eyelids closing and opening, the vertical and lateral motion of the eyeball, and the eyebrow moving.
The anthropomorphic device plugs into a computer’s USB port and is detected by the computer as an ordinary plug-and-play webcam. An integrated facial recognition algorithm can identify its owner, allowing it to outline emotions such as disappointment, irritation, and excitement. For example, if it detects the user is looking exhausted, it could make the eye look tired and droopy.
Teyssier explained:
Our application scenarios are fictional and are intended to encourage people to think about how we interact with technical devices today, but also in the future. The special thing about our experiments is that we can experience and relate our imagined scenarios with the help of a physically available prototype.
The scientists have made its ‘Eyecam’ readily available for anyone to build as an Open-Source on GitHub, ensuring that their ‘food for thought’ reaches as many people as possible. This month, the team presented a detailed paper on the project via the online ACM Conference on Human Factors in Computing Systems.
