Researchers Develop ‘Terminator’ Vision Tech That Mimics Human Eye

Arnold Schwarzenegger’s high-tech bionic eyes in The Terminator movies are no longer science fiction.

Researchers at the University of Central Florida (UCF) have developed a device for artificial intelligence (AI) that replicates the retina of a human eye.

The researchers say the technology has synapse-like devices that act like “smart pixels” in a camera by sensing, processing, and recognizing images simultaneously. And it could become available for use in the next five to 10 years.

The development could lead to advanced AI that can instantly recognize what it sees, like automatic descriptions of pictures taken by a camera or phone. The technology also has applications in self-driving vehicles and robotics.

The technology, which is detailed in a recent study in the journal ACS Nano, also outperforms the human eye in terms of the range of wavelengths it can see, from ultraviolet to visible light and on to the infrared spectrum.

Its ability to combine three different operations into one further contributes to its uniqueness. Currently available intelligent image technology, such as that found in self-driving cars, needs separate data processing, memorization, and sensing. The researchers say that by integrating the three procedures, the UCF-designed device is much faster than existing technology. With hundreds of the devices fitting on a one-inch-wide chip, the technology is also quite compact.

“It will change the way artificial intelligence is realized today,” says the research team’s principal investigator Tania Roy to UCF Today

“We had devices, which behaved like the synapses of the human brain, but still, we were not feeding them the image directly,” Roy says. “Now, by adding image sensing ability to them, we have synapse-like devices that act like ‘smart pixels’ in a camera by sensing, processing and recognizing images simultaneously.”

For self-driving vehicles, the versatility of the device will allow for safer driving in a range of conditions, including at night, as the technology can “see” in several wavelengths.

The key to this technology is the engineering of nanoscale surfaces to allow for multi-wavelength sensing and memory. In tests for the device, the researchers got 70 to 80 percent accuracy, which means there is a good chance that the technology can be added to hardware and work in AI for robots.

Image credits: Header photo courtesy of Daniel Juřena.