Machine learning can analyse how the signals from Wi-Fi transmitters are disrupted by human bodies to reveal what position people are sitting, standing or lying in
Technology
25 January 2023
Comparison of real poses and poses determined only from using Wi-Fi signals arxiv.org/abs/2301.00250
A person’s bodily outline can be worked out from the pattern of Wi-Fi signals moving across a room, which could help monitor older people at risk of hurting themselves if they fall or enable the detection of home intruders.
Indoor cameras and radar-based technologies can be used to detect a person’s body shape or what position they are in, but these can introduce a privacy risk, such as a camera feed being hacked, or involve specialised hardware and …
Source link The electrical gadget-filled world of the 21st century is full of surprises, and one of the latest is the discovery that Wi-Fi signals can be used to detect the outline of people’s bodies.
This intriguing concept was developed by a team of researchers from the Massachusetts Institute of Technology, whose paper about the topic has recently been published in Nature Scientific Reports. Through experimentation, the researchers were able to successfully use Wi-Fi signals to recognize the shape of a human body within a room, even when the person was moving.
The team used a specially designed algorithm created by MIT professor Dina Katabi to construct the figures by tracking radio signals sent by the person’s body. The algorithm could pick up the signals even after they had been reflected off them by walls, furniture, and other obstacles in the environment.
So how can this breakthrough be used? According to the researchers, Wi-Fi-based body modelling is a powerful tool that can have a wide range of applications in the areas of health monitoring, security, and user interface design.
One potential use could be in health monitoring, where information about heart rate and breathing patterns can be drawn from the detected body shapes. This could enable healthcare professionals to remotely monitor a person’s health without the need for intrusive wires or equipment.
Security applications are also possible. The technology could be used to detect people in areas where it is not advisable for them to be, such as restricted buildings. It could also be used as an aid in search-and-rescue operations, such as in the event of a natural disaster.
Finally, it could also revolutionize user interface design. Wi-Fi-based body modelling could be used to map motions, allowing users to control their devices with their body instead of a mouse or keyboard.
It’s clear that Wi-Fi-based body modelling has the potential to be quite transformative, and it’ll be interesting to see how the technology is developed and applied in the years to come.
