Wi-Fi device can see through walls...
Forget X-rays, now you can see
through walls using WI-FI: Device captures silhouettes and can even identify
people when they're stood behind CONCRETE
·
The RF Capture device was
developed by researchers at MIT
·
Wireless signals travel through
the wall and reflect off the body behind it
·
This creates a silhouette from
which body parts can be identified
·
Silhouettes can then be compared
to a database of bodies to identify who they belong to - and it can even
identify which hand their moving
·
·
X-ray
vision is a staple of sci-fi films and comic books and now researchers have
turned this concept into a reality.
Using a
wireless transmitter fitted behind a wall, computer scientists have developed a
device that can map a nearby room in 3D while scanning for human bodies.
Using the
signals that bounce and reflect off these people, the device creates an
accurate silhouette and can even use this silhouette to identify who that
person is.
+3
Using a
wireless transmitter fitted behind a wall, computer scientists have developed a
device that can map a nearby room in 3D while scanning for human bodies. Using
the signals that reflect off these people, the device creates an accurate
silhouette (pictured) and can even use this silhouette to identify who that
person is
The
device is called RF Capture and it was developed by researchers at MIT's
Computer Science and Artificial Intelligence Lab (CSAIL).
It has
long been thought that wireless signals, such as Wi-Fi, can be used to see
things that are invisible to the naked eye.
·
With this
in mind the researchers have been developing technologies that use wireless
signals to track human motion since 2013.
As part
of its latest research, the team has shown that these technologies can detect
gestures and body movements as subtle as the rise and fall of a person's chest
from the other side of a house.
HOW RF
CAPTURE WORKS
The device transmits wireless signals that travel through the wall
and reflect off a person's body back to the device.
It begins by scanning the 3D space to capture wireless reflections
of objects in the room, including the human body.
Since only a subset of body parts reflect the signal back at any
given point in time, the device then monitors how these reflections vary as
someone moves and walks.
It can intelligently stitch the person's reflections across time
to reconstruct his silhouette into a single image.
Once captured, these reflections are analysed.
To differentiate between people, the team repeatedly tested and
trained the device on different subjects, using metrics such as height and
shape to create concrete 'silhouette fingerprints' for each person.
The team continued that the emitted radiation is approximately
10,000 times lower than that of a standard phone.
This
could allow a mother to monitor a baby's breathing, for example, or help a
firefighter determine if there are survivors inside a burning
building.
The RF
Capture device transmits wireless signals that travel through a wall and
reflect off a person's body back to the device.
It begins
by scanning the 3D space to capture wireless reflections of objects in the
room, including any human bodies.
Since
only a small number of body parts reflect the signal back at any given point in
time, the device monitors how these reflections vary as someone moves and
walks.
It can
then intelligently stitch the person's reflections across time to reconstruct
their silhouette into a single image.
Once
captured, these reflections are analysed.
To
differentiate between people, the team repeatedly tested and trained the device
on different subjects, using metrics such as height and shape to create
concrete 'silhouette fingerprints' for each person.
During
tests, the device was able to trace a person's hand as he wrote in mid-air, and
could even distinguish between 15 different people through a wall with nearly
90 per cent accuracy.
In other
words, from the opposite side of a building RF Capture can determine where that
person is, who they are, and even which hand they are moving.
3
The
device is called RF Capture and it was developed by researchers at MIT's
Computer Science and Artificial Intelligence Lab (CSAIL). It begins by
scanning the 3D space to capture wireless reflections of objects in the next
room, including any human bodies (pictured)
Since
only a small number of body parts reflect the signal back at any given point in
time, the device then monitors how these reflections vary as someone moves and
walks (illustrated). It can intelligently stitch the person's reflections
across time to reconstruct this silhouette into a single image
The
researchers said the technology could have major implications for everything
from gaming and film-making to emergency-response and elder-care.
'The data
you get back from these reflections is very minimal,' said researcher Dina
Katabi, director of Wireless@MIT.
'However,
we can extract meaningful signals through a series of algorithms we developed
that minimize the random noise produced by the reflections.
'We're
working to turn this technology into an in-home device that can call 911 if it
detects that a family member has fallen unconscious.
'You
could also imagine it being used to operate your lights and TVs, or to adjust
your heating by monitoring where you are in the house.'
During
tests, the device was able to trace a person's hand as he wrote in mid-air and
could even distinguish between 15 different people through a wall with nearly
90% accuracy. In other words, from the opposite side of a building RF Capture
can determine where that person is, who they are, and even which hand they are
moving
Future
versions could be integrated into games, allowing people to interact with a
game from different rooms or even trigger distinct actions based on which hand
they move.
'The
possibilities are vast,' added PhD student Fadel Adib.
'We're
just at the beginning of thinking about the different ways to use these
technologies.'
The
results are published in the paper,
Capturing the Human Figure Through a Wall, which has been accepted to the
SIGGRAPH Asia conference taking place next month.
Other
co-authors include MIT professor Frédo Durand, PhD student Chen-Yu Hsu and
undergraduate intern Hongzi Mao.
Comments
Post a Comment