Contact-free sensing for collective activity recognition

We are surrounded by a multitude of communicating sensing devices. Furnished with wearables to serve our very needs, we traverse sensor-rich environments of smart cities. Through new open standards and novel protocols this loose collection of devices increasingly evolves into a superorganism of wearables and environmental devices. All these devices share a single ubiquitous sensor type: the RF-interface. Ubiquitously available signals from e.g. FM-radio, WiFi or UMTS can be exploited as sensor for presence, location, crowd-size, activity or gestures [4, 1, 2]. On-site training of these systems will soon be replaced by offline-raytracing techniques [3] and recognition accuracies will further increase with the Channel State Information (CSI) on recent OFDM receivers. In contrast to RSSI, CSI features channel response information as a PHY layer power feature, revealing amplitudes and phases of each subcarrier (cf. Figure 2). Exemplary, enabled by this superorganism of wireless devices, we envision the advance of sentiment sensing, smart city architectures as well as autonomous intelligent spaces.