The popularity of Internet of Things (IoT) devices (without tradition human-computer interfaces) has made gesture recognition an advantageous form of human-computer interaction - especially in smart home applications. However, conventional gesture recognition approaches have issues that limit their pervasive use. For example, wearable devices (e.g. watches and wristbands) with inertial sensors can be inconvenient to always wear; radio frequency systems are cost prohibitive for large-scale deployment; and vision-based systems require favorable lighting and introduce privacy concerns.
Recently, WiFi infrastructure, and associated WiFi-enabled mobile and IoT devices have become ubiquitous, and correspondingly, have enabled many context-aware and location-based services.
To address the opportunities for gesture recognition and take advantage of the popularity of WiFi, researchers at UC Berkeley developed a gesture recognition system based on analyzing signals from existing WiFi-enabled devices. This novel WiFi-enabled, device-free gesture recognition system can identify human gestures with consistent high accuracy and has robust environmental dynamics.
Smart home services