Scientists manipulate Wi-Fi for gesture recognition

A gesture recognition system based on disruption to Wi-Fi signals enables gesture control without sensors or cameras. University of Washington computer scientists used an adapted Wi-Fi router and a few wireless devices to allow users to control electronics and appliances from different rooms with simple gestures. "WiSee", technology will be presented at the 19th Annual International Conference on Mobile Computing and Networking.

“This is repurposing wireless signals that already exist in new ways,” said lead researcher Shyam Gollakota, a UW assistant professor of computer science and engineering. “You can actually use wireless for gesture recognition without needing to deploy more sensors.”

Because Wi-Fi signals can travel through walls and aren’t bound by line-of-sight or sound restrictions then WiSee technology doesn’t require users to be in the same room as the device.

The UW researchers built a “smart” receiver device that essentially listens to all of the wireless transmissions coming from devices throughout a home or office, including smartphones, laptops and tablets.

A standard Wi-Fi router can be adapted to detect frequency changes caused by shifts resulting from gestures.

This functions as a receiver and can account for gaps in wireless signals when devices aren’t transmitting.

The technology can identify nine different whole-body gestures, ranging from pushing, pulling and punching to full-body bowling. The researchers tested these gestures with five users in a two-bedroom apartment and an office environment. Out of the 900 gestures performed, WiSee accurately classified 94% of them.