Researchers from Rutgers University demonstrated the readily available WiFi signals from low-cost devices can penetrate into baggage without any dedicated devices or signals.
With their model they utilized channel state information (CSI) from normal Wi-Fi Devices to be used in detecting suspicious objects, the CSI is a channel property of a communication link that describes how the signal propagates from the transmitter to receiver.
Object Classification – Wi-Fi devices
The system classified into two major components
It first detects the existence of dangerous objects and identifies it’s type based on reconstructed CSI complex value.
Then it calculates the risk level of the object by examining the dimensions of the object based on the reconstructed CSI complex of the signals reflected from the object.
They said that Our system only requires a WiFi device with 2 to 3 antennas and can be integrated into existing WiFi networks with low costs and deployment efforts, making it more scalable and practical than the approaches using dedicated instruments.
Researchers said our system can detect over 95% of suspicious objects in different types of bags and successfully identify 90% dangerous material types.
Researchers evaluated 15 metal and liquid objects and 6 types of bags in a 6-month period. Each experiment is repeated 5 times by changing object’s position and orientation.
They said Our system can be easily deployed to many places that still have no pre-installed security check infrastructures and require high-manpower to conduct security checks such as theme parks, museums, stadiums, metro/train stations, and scenic locations.
Professor Yingying Chen said in an interview to CBS local that their new prototype detection is a game changer and We feel really excited and we realized this could be very useful.
More technical details can be found in the paper “Towards In-baggage Suspicious Object Detection Using Commodity WiFi” published by researchers.