Your Video Can ID You Through Walls


Researchers in the lab of UC Santa Barbara
professor Yasamin Mostofi have enabled, for the first time, determining whether the person
behind a wall is the same individual who appears in given video footage, using only a pair
of WiFi transceivers outside. This novel video-WiFi cross-modal gait-based
person identification system could have a variety of applications, from surveillance
and security to smart homes. For instance, consider this scenario. Law enforcement has a video footage of a robbery. They are suspicious that the robber is hiding
in a house. Can a pair of WiFi transceivers outside of
the house identify the person in the house and determine if it is the same person as
in the robbery video? The researchers proved that it is possible. This new technique can determine if the person
behind the wall is the same as the one in a video footage, by using only a pair of off-the-shelf
WiFi transceivers outside. This system only uses the received power measurements
of a pair of WiFi transceivers. It does not need any prior WiFi or video training
data of the person to be identified. And, it does not need any prior knowledge
of the operation area or person’s track. It can identify people through walls. Identifying a person through walls from candidate
video footage is a considerably challenging problem. The way each one of us move is unique. In other words, as a person moves, the way
different body parts move with respect to each other can be a unique identifier of the
person. This new system is able to properly capture
and compare the gait information content of the video and WiFi signals to establish if
they belong to the same person.

, , , , , , ,

Post navigation

Leave a Reply

Your email address will not be published. Required fields are marked *