Tracking movements is no surprise, however, the team of engineers from the Massachusetts Institute of technology (MIT) were able to create a device that is able to follow the man through the walls. Moreover, the device is not very bulky.
The device is called RF-Pose. In order to train the algorithm a new trick, the staff of the MIT tracked the movement of people by means of radar and video cameras. They fixed the walk, the conversation between people, the sitting posture, standing posture and expectations, and also opening doors. Then, using a not very sophisticated computer program, the image was transformed into a skeletal model of each recorded situation. These models, along with signals studied AI, and thus he learned to recognize the relationship between the radar display and what actions produced the moment the person or group of people.
As a result, experts from MIT have created an algorithm that is almost in real time can show the movement of people behind a wall or another obstacle. It is worth noting that at the moment the system is able to provide only a two-dimensional image, but over time the system can be optimized so that it could perform monitoring in three dimensions.
The plans of the founders is also included to teach the AI to recognize more complex movements like fine motor skills of hands and fingers, as now, the only possible monitoring of the movement of the limbs and trunk. The authors claim that their system may find application in various fields. From a logical observation of places of a mass congestion of people to medical institutions and places of detention.
Artificial intelligence has learned to detect people through walls
Vladimir Kuznetsov