Original article ISPreview UK:Read More
Over the years we’ve seen various different uses for wireless WiFi signals being developed, such as the ability to see through walls (here) or to act as a motion sensing alarm system (here). Now a team of Italian researchers have figured out how to identify individual people by the biometric identifier they give off when walking through Wi-Fi signals.
According to a new research paper from a team at the La Sapienza University of Rome, the Wi-Fi Sensing method they’ve developed – called ‘WhoFi‘ – can essentially identify people based on the way that their bodies interfere with Wi-Fi signals as they pass through an area.
“The core insight is that as a Wi-Fi signal propagates through an environment, its waveform is altered by the presence and physical characteristics of objects and people along its path. These alterations, captured in the form of Channel State Information (CSI), contain rich biometric information,” said the paper. “Unlike optical systems that perceive only the outer surface of a person, Wi-Fi signals interact with internal structures, such as bones, organs, and body composition, resulting in person-specific signal distortions that act as a unique signature.”
In addition, and rather unlike existing visual ID systems (cameras etc.), Wi-Fi based ID systems are not affected by changes in visual illumination, can penetrate walls and occlusions, and also “offer a privacy-preserving mechanism for sensing” (i.e. you don’t need a visual picture of somebody).
Summary from the Research Paper
Person Re-Identification is a key and challenging task in video surveillance. While traditional methods rely on visual data, issues like poor lighting, occlusion, and suboptimal angles often hinder performance. To address these challenges, we introduce WhoFi, a novel pipeline that utilizes Wi-Fi signals for person re-identification. Biometric features are extracted from Channel State Information (CSI) and processed through a modular Deep Neural Network (DNN) featuring a Transformer-based encoder.
The network is trained using an in-batch negative loss function to learn robust and generalizable biometric signatures. Experiments on the NTU-Fi dataset show that our approach achieves competitive results compared to state-of-the-art methods, confirming its effectiveness in identifying individuals via Wi-Fi signals.
The research paper itself should be considered more of a starting point for further development, which proves that the concept may finally be viable. The next step will be to turn theory into a practical solution that works outside the lab. We should point out that the idea above has been experimentally researched before, but accuracy was a big problem, and the new paper largely seems to solve this issue.