This post is also available in: עברית (Hebrew)
A new system developed by MIT researchers uses a neural network and radio signals to track people through walls in real time. It doesn’t even need to have a direct line of sight to know how someone is walking, sitting, or waving their arms on the other side of a wall.
MIT says the RF-Pose tech can be embedded into a wireless device, which would theoretically allow soldiers to hook it up to their combat gear – like helmets and night-vision goggles. In the future, military personnel could use it on the battlefield to “see” hidden enemies by wearing augmented reality headsets, according to thesun.co.uk.
Other applications include the medical field, where the technology could track and analyze the way patients with muscle and nerve disorders get around. It could also enable motion capture in video games, or even help locate survivors in search-and-rescue missions.
To train an artificial intelligence‘s neural network to operate the mission, you need an extensive data set of pre-labeled items. That usually means using humans to do the labeling. RF-Pose is based on radio waves, and those are much harder for humans to label in a way that makes sense to computers.
The researchers collected examples of people walking with both wireless signal pings and cameras. The camera footage was processed to generate stick figures in place of the people, and the team matched that data up with the radio waves.
The technology works because the radio waves bounce off a person on the other side of a wall just like they do in the same room. This even works with multiple people crossing paths.
In the real world, there are clear privacy implications. It’s possible a future version of the technology could be configured only to track someone after they perform a specific movement to activate the system and “opt-in.”