A bit more than a year ago, I published a news writeup that covered an alternative (i.e. non-vision-based) gesture interface derived from the partnership work of Microsoft Research and the University of Washington. I wrote:
SoundWave [is] a proof-of-concept system that leverages a computer's microphone and speaker combo to implement rudimentary gesture control. Doppler shifts, akin to those harnessed by sonar and astronomers, are at the root of the scheme. The speaker emits tones in the 18-22 kHz frequency range, which are spectrally affected by hand movement. A microphone picks up the audio, and software subsequently compares the source to the altered output, thereby discerning hand distance, location and speed and direction of gesture movement.
Waves are waves, to put it (over-)simply, so it makes sense that alternative frequency ranges might also be harnessed to similar effect. Enter WiSee, another University of Washington research project, in this case harnessing conventional Wi-Fi hardware (a router and several wireless LAN clients):
WiSee is a novel interaction interface that leverages ongoing wireless transmissions in the environment (e.g., WiFi) to enable whole-home sensing and recognition of human gestures. Since wireless signals do not require line-of-sight and can traverse through walls, WiSee can enable whole-home gesture recognition using few wireless sources (e.g., a Wi-Fi router and a few mobile devices in the living room).
WiSee is the first wireless system that can identify gestures in line-of-sight, non-line-of-sight, and through-the-wall scenarios. Unlike other gesture recognition systems like Kinect, Leap Motion or MYO, WiSee requires neither an infrastructure of cameras nor user instrumentation of devices. We implement a proof-of-concept prototype of WiSee and evaluate it in both an office environment and a two-bedroom apartment. Our results show that WiSee can identify and classify a set of nine gestures with an average accuracy of 94%.
WiSee takes advantage of the technology trend of MIMO, the fact that wireless devices today carry multiple antennas (which are primarily used to improve capacity). A WiSee/WiSee-enabled receiver would use these multiple antennas in a different way to focus only on the user in control, thus eliminating interference from other people.
Here's another intriguing quote, from the research team's to-be-presented paper (PDF):
Over a 24-hour period, WiSee’s average false positive rate—events that detect a gesture in the absence of the target human—is 2.63 events per hour when using a preamble with two gesture repetitions. This goes down to 0.07 events per hour, when the number of repetitions is increased to four.
For more information, see the research team's website, along with the following additional coverage:
