Our individual walking styles, much like snowflakes, are unique. With this in mind, computer scientists have developed a powerful new footstep-recognition system using AI, and it could theoretically replace retinal scanners and fingerprinting at security checkpoints, including airports.
This browser does not support the video element.
Neural networks can find telltale patterns in a person’s gait that can be used to recognize and identify them with almost perfect accuracy, according to new research published in IEEE Transactions on Pattern Analysis and Machine Intelligence. The new system, called SfootBD, is nearly 380 times more accurate than previous methods, and it doesn’t require a person to go barefoot in order to work. It’s less invasive than other behavioral biometric verification systems, such as retinal scanners or fingerprinting, but its passive nature could make it a bigger privacy concern, since it could be used covertly.
“Each human has approximately 24 different factors and movements when walking, resulting in every individual person having a unique, singular walking pattern,” Omar Costilla Reyes, the lead author of the new study and a computer scientist at the University of Manchester, said in a statement.
To create the system, Reyes compiled a database consisting of 20,000 footstep signals from more than 120 individuals. It’s now the largest footsteps database in existence. Each gait was measured using pressure pads on the floor and a high-resolution camera. An artificially intelligent system called a deep residual neural network scoured through the data, analyzing weight distribution, gait speed, and three-dimensional measures of each walking style. Importantly, the system considers aspects of the gait, rather than the shape of the footprint.
“Focusing on non-intrusive gait recognition by monitoring the force exerted on the floor during a footstep is very challenging,” said Reyes. “That’s because distinguishing between the subtle variations from person to person is extremely difficult to define manually, that is why we had to come up with a novel AI system to solve this challenge from a new perspective.”
Previous attempts at footstep recognition involved the scanning of individuals without their shoes on, and a 3D-imaging technique that compared a person’s walking style to CCTV footage. The new technique is more accurate than both, though it does require the use of special floor pads.
To test the SfootBD system, Reyes’ team monitored participants in three different scenarios: airport security checkpoints, workplaces, and homes. The researchers also tested a control group of imposters to see if the AI could tell when someone was trying to fake another person’s gait (which it could). Results showed that, on average, the system was 100 percent accurate in identifying individuals, with an error rate of just 0.7 percent. That’s obviously an impressive result, and a sign that the technology could be effective in real-world situations.
This new system does have some limitations. As noted, SfootBD requires the use of floor pads and a high-res camera, so this form of surveillance and identification can’t be used just anywhere. What’s more, the tool is only as powerful as its database; the only individuals who can be identified are those whose distinctive gaits have been previously recorded and cataloged in the system. This approach is probably not very scalable, since collecting everyone’s walking style is an order of magnitude more difficult than, say, collecting photos for facial recognition. Finally, there are also issues of privacy and consent to consider, as this technology could be used surreptitiously.
So it’s a neat advance, but only time will tell how practical this method is for the real world.