Researchers at MIT, who have found a way to
teach a radio vision system to recognize people’s actions by training it with
visible-light images. The new radio vision system can see what individuals are
up to in a wide range of situations where visible-light imaging fails. The
basic idea is to record video images of the same scene using visible light and
radio waves. Machine-vision systems are already able to recognize human actions
from visible-light images. So the next step is to correlate those images with
the radio images of the same scene. But the difficulty is in ensuring that the
learning process focuses on human movement rather than other features, such as
the background.
Researchers introduced an intermediate step in
which the machine generates 3D stick-figure models that reproduce the actions
of the people in the scene. In this way the system learns to recognize actions
in visible light and then to recognize the same actions taking place in the
dark or behind walls, using radio waves. The obvious applications are in
scenarios where visible-light images fail (i.e. in low light conditions and
behind closed doors). One problem with visible-light images is that people are
recognizable, which raises privacy issues. But a radio system does not have the
resolution for facial recognition. Identifying actions without recognizing
faces does not raise the same privacy fears.
More information: