When did Wi-Fi become Spy-Fi?

The term body mapping is one that conjures images of a person’s outline drawn onto either a piece of paper or computer. Words and indicators are placed about the image – for example, if a vulnerable person sustained injuries or is in pain, a professional might use the body map to pinpoint the area of the injury or pain and detail it. A body map is, ultimately, a way to ensure, usually vulnerable, people are safe.

Now, as healthcare settings are increasingly shifting from clinics to households, the research team hope Wi-Fi body detection technology will be used to ensure the elderly and infirm are safe within their homes, without invading their privacy. It can also be used to detect suspicious activity in the household.

In a paper published by the University, they state: “Placing these sensors [Radar and LiDAR] in non-public areas raises significant privacy concerns. To address these limitations, recent research has explored the use of Wi-Fi antennas.”

When Wi-Fi becomes Spy-Fi

Human pose estimation is not something new. For many years scientists and researchers have tried to find a way to utilise the benefits of technology such as RGB cameras, LiDAR, and radar, to map people’s movements, but at a lower-cost, power consumption and without the results being negatively impaired by lighting and dense objects, such as furniture, blocking images.

“Radar and LiDAR technologies … need specialised hardware that is expensive and power-intensive.

“Advances in computer vision and machine learning techniques have led to significant development in 2D and 3D human pose estimation from RGB cameras, LiDAR, and radars. However, human pose estimation from images is adversely affected by occlusion and lighting, which are common in many scenarios of interest.”

Now the Carnegie Mellon research team believe they have a cost-effective, widely-available and power-friendly solution – Wi-Fi.

“Research has explored the use of Wi-Fi antennas (1D sensors) for body segmentation and key-point body detection. This paper further expands on the use of the Wi-Fi signal in combination with deep learning architectures, commonly used in computer vision, to estimate dense human pose correspondence.”

The Carnegie Mellon University research team further comment in their paper: “We developed a deep neural network that maps the phase and amplitude of Wi-Fi signals to UV coordinates within 24 human regions. The results of the study reveal that our model can estimate the dense pose of multiple subjects, with comparable performance to image-based approaches, by utilising Wi-Fi signals as the only input. This paves the way for low-cost, broadly accessible, and privacy-preserving algorithms for human sensing.”

The paper argues that, bar putting cameras in people’s private residences, which would be considered an intrusion of their privacy, utilising publicly available Wi-Fi is the best alternative to ensure privacy is upheld. However, whether utilising publicly available means, or putting cameras into private residences, being able to see through walls is still a big concern when it comes to invading people’s personal space.

Personal safety is a paramount objective, but there is a very fine line between privacy and intrusion, and if people believe they are being spied on rather than helped, then it will only seek to demoralise their faith in technology.