学进去

Love the way you walk

Listen carefully to the footsteps in the family home, and you can probably work out who is walking about. The features most commonly used to identify people are faces, voices and fingerprints. But the way they walk is also a giveaway.

Researchers have used video cameras and computers to analyze people’s gaits, and are now quite good at it. But translating such knowledge into a practical identification system can be tricky. Cameras are often visible, are difficult to set up, require good lighting and may have their view blocked by other people. A team led by Dr. Ozanyan and Dr. Scully have been looking for a better way to recognize gait. Their answer: pressure-sensitive mats.

Such mats are nothing new. They have been part of security systems. But Ozanyan and Scully use a complicated version that can record the amount of pressure applied in different places as someone walks across it. These measurements form a pattern unique to the walker. The researchers turned to an artificial-intelligence system to recognize such patterns, and it seemed to work. In a study in 2018, they tested the system on a database of footsteps of 127 people. They found its error rate in identifying who was who was a mere 0.7%. And Scully says even without a database of footsteps to work with, the system can determine someone’s sex and, with reasonable accuracy, a subject’s age.

One application of the mat-based gait-recognition system might be in health care, particularly for the elderly. A mat placed in a nursing home or an old person’s own residence could monitor changes in an individual’s gait that indicates certain illnesses. That would provide early warning of someone being at greater risk of falling over.

Gait analysis might also be used as a security measure in the workplace, monitoring access to restricted areas, such as parts of military bases, server farms or laboratories dealing with dangerous materials.

Perhaps the most interesting use of the mats, though, would be in public places, such as airports. For that to work, the footsteps of those to be recognized would need to have been stored in a database, which would be harder to arrange than the collection of photographs and fingerprints that existing airport security systems rely on. Many aircrew or preregistered frequent flyers would welcome anything that speeded up one of the most tiresome parts of modern travel.