Creating and sharing knowledge for telecommunications

Gesture Recognition by Electromagnetic-Wave Reflection

Garcia, M. ; Topa, A.

Gesture Recognition by Electromagnetic-Wave Reflection, Proc Encuentro Ibérico de Electromagnetismo Computacional - EIEC , Baeza, Spain, Vol. 1, pp. 1 - 2, May, 2015.

Digital Object Identifier: 0

 

Abstract
Gestures enable a new interaction technique for computing embedded in the environment. Commercially available sensors facilitate gesture-based interaction using depth sensing and computer vision. However, the burden of installation and cost make most vision-based sensing devices hard to deploy at scale. To overcome these limitations, a part of this sensing has been moved onto the body and the need for environmental sensors has be reduced. However, even on-body approaches are limited to what people are willing to carry and may be infeasible in some scenarios.
This paper addresses gesture recognition systems that leverage wireless signals to enable sensing and recognition of human gestures. Since wireless signals do not require line-of-sight and can traverse through walls, gesture recognition can be achieved without requiring human body sensing devices. This can be achieved by looking at the Doppler shifts and multi-path distortions that occur with these wireless signals from human motion in the environment.
Doppler shift occurs whenever a wave source moves relative to the observer. In the context of wireless signals, if we consider the multi-path reflections from the human body as waves from a source, then a human performing a gesture, results in a pattern of Doppler shifts at the wireless receiver.
Human gestures result in very small Doppler shifts that can be hard to detect from typical wireless transmissions (e.g., Wi-Fi). A 0.5 m/s gesture results in a 17 Hz Doppler shift on a 5 GHz Wi-Fi transmission. Typical wireless transmissions have orders of magnitude higher bandwidth (20 MHz for Wi-Fi). Thus, for gesture recognition, we need to detect Doppler shifts of a few Hertz from the 20 MHz Wi-Fi signal. By transforming the received signal into a narrowband pulse with a bandwidth of a few Hertz, this problem can be addressed. The receiver must track the frequency of this narrowband pulse to detect the small Doppler shifts resulting from human gestures.
Multiple people can affect the wireless signals at the same time. The multiple input multiple output (MIMO) capability can be used to focus on gestures from a particular user. MIMO provides throughput gains by enabling multiple transmitters to concurrently send packets to a MIMO receiver. If we consider the wireless reflections from each human as signals from a wireless transmitter, then they can be separated using a MIMO receiver.
Algorithms to extract gesture information from communication-based wireless signals need to be developed. These algorithms extract the instantaneous Doppler shifts from wideband OFDM transmissions that are typical to most modern communication systems including Wi-Fi.