Please enable JavaScript to experience the full functionality of GMX.

Footstep-recognition developed for airports

Footstep-recognition could be the latest technology introduced to identify people at security checkpoints.

According to new research published by technical professional organisation IEEE, individual walking styles are as unique as fingerprints and retinas, prompting computer scientists to develop a new footstep-recognition system using Artificial Intelligence (AI).

The system, called SfootBD, means people's identity could theoretically be identified at passport control simply by how they strolled through the gate, rather than queuing up to have their eyes scanned.

SfootBD is almost 380 times more accurate than previous methods, and it doesn't require a person to be barefoot in order to work.

The AI technology was even able to tell when someone was faking their walk.

Omar Costilla Reyes, the lead author of the new study and a computer scientist at the University of Manchester, said in a statement: "Each human has approximately 24 different factors and movements when walking, resulting in every individual person having a unique, singular walking pattern."

This form of surveillance may be viewed as a privacy concern as it could be used covertly.

However, SfootBD requires the use of floor pads and a high-res camera, so it cannot be operated just anywhere.

And the system is not easy to scale up, as gathering the data to catalogue everyone's walking style is a far greater task than that of collecting photographs for facial-recognition.

Sponsored Content