The Objectifier Trains Your Devices to Respond to Your Daily Routine

Why must we as humans learn the language of our machines, when the machines could learn to understand ours instead? This was the basis of CIID design student Bjørn Karmann’s graduation project, which empowers people to train objects in their daily lives to respond to their unique behaviors.

The “Objectifier” uses the combination of computer vision and neural networks to learn your habits and gestures to then operate appliances throughout your environment. For example, you can trigger your radio with your favorite dance move, have the lamp shut off when you close a book, or power up the coffeemaker when you place a mug next to it. Just connect your inanimate item to the Objectifier and use the companion training app to show it when it should turn on/off.

It gives an experience of training an artificial intelligence; a shift from a passive consumer to an active, playful director of domestic technology. Interacting with Objectifier is much like training a dog — you teach it only what you want it to care about. Just like a dog, it sees and understands its environment.It gives an experience of training an artificial intelligence; a shift from a passive consumer to an active, playful director of domestic technology.

The Objectifier is equipped with a Raspberry Pi and Pi Camera, and was brought to life using a variety of software including Wekinator for machine learning, Processing, and openFrameworks, with ml4A providing apps for working with machine learning.

As with any project, the latest device is the sixth iteration in a series of prototypes — Karmann notes that the Objectifier is much smaller, friendlier and smarter than its predecessors. You can read more about this impressive project and see some of its earlier versions here.