We don’t realize it, but there’s an invisible world of pulsating movement and color all around us. Now a team of researchers has found a way to amplify this unseen world using video. Dubbed “Eulerian Video Magnification,” the technology can be used to monitor a sleeping newborn’s breathing, the pulse of hospital patients and even industrial machines.
“Once we amplify these small motions, there’s like a whole new world you can look at,” MIT computer scientist William Freeman told the New York Times.
The system works by concentrating on a single pixel in a video. The program identifies subtle, frame-by-frame changes in color or motion, then amplifies them 100 times. A video of a person’s face that might normally look pink shifts toward bright red when subjected to the algorithm. Such a program could reveal subtle changes in a person’s pulse and make them immediately visible to a nurse or doctor.
Besides monitoring pulses, scientists say their system could also be used to monitor spatial patterns of blood flow to check for any asymmetries that could indicate disease. Freeman says in the following video he hopes this will be a useful diagnostic for medical doctors.
Additionally, the system could be used in search and rescue operations where first responders and EMTs could tell from a distance if trapped victims were still breathing. Scientists also say the movement enhancement features could be useful in the manufacturing and oil expedition sector. For example, an enhanced video feed could detect the small movements — invisible to the naked eye — of bolts or machine parts that could indicate a looming malfunction.
Michael Rubinstein, a doctoral student and co-author on the project, said the team has been flooded with emails inquiring about the system’s availability. Heath care professionals obviously expressed interest as did law enforcement agencies curious about the tech’s lie detection capabilities. Even gamblers raised a brow, wondering if the system could be incorporated into Google Glass to help give them an edge.
“People wanted to be able to analyze their opponent during a poker game or blackjack and be able to know whether they’re cheating or not, just by the variation in their heart rate,” he said.
And the coolest part? Freeman, Rubinstein and company posted the source code online and it’s free to use for non-commercial purposes. Have a video clip you’d like to see run through the program? You can do so here, compliments of Quanta Research Cambridge, a manufacturer of laptop computers that helped finance the project,
Credit: MIT CSAIL