WiFi device identifies a person through a wall
Market Expertz | October 01, 2019
A team of researchers in the lab of Yasamin Mostofi, Professor, UC Santa Barbara, has determined if a person behind a wall is the same one appearing in given video footage with the help of only a pair of WiFi transceivers outside. The innovative video-WiFi cross-modal gait-based person identification system, known as XModal-ID, could potentially be used in various applications such as for surveillance and security, and smart homes. Mostofi says that their proposed approach makes it possible to determine if the person behind the wall is the same one seen in the video footage, by using merely a pair of off-the-shelf WiFi transceivers outside.
This approach relies on only the received power measurements of a WiFi link and does not require any prior WiFi or video training information of the person to be identified. It also does not need to have previous knowledge of the operation area, adds Mostofi. In the experiment, on the WiFi transmitter and one WiFi receiver are behind walls, outside a room where the person is walking. The transmitter emits a wireless signal, the received power of which is measured by the receiver. Then, with the help of video footage of a person from another area and the received wireless power measurements, the receiver can identify if it is the same person behind the wall as seen in the video. This approach builds upon earlier work of the Mostofi Lab, which is credited with innovations such as everyday radio frequency signals like WiFi for a decade.
The proposed methodology and the results of the experiment will be presented at the 25th International Conference on Mobile Computing and Networking (MobiCom) to be held on the 22nd of October. The project was financed by a couple of grants awarded by the National Science Foundation for through-wall imaging and occupancy assessment.