TOKYO >> A team of scientists has developed technology that uses artificial intelligence to identify individuals by their gait, or walking pattern.
The technology, expected to be used in criminal investigations, is able to identify people based on surveillance camera images that captures them walking, even if only for a moment.
The method is called gait recognition. According to Osaka University professor Yasushi Yagi, who led the team, gait recognition has been used in criminal investigations in Japan since 2009, and has been introduced as evidence at trials.
For accurate results, it is necessary to have at least four steps’ worth of walking data, two steps with each foot. The team used data from videos of about 5,000 people walking and analyzed it with deep learning — machine-learning algorithms that detect patterns from large amounts of data. It succeeded in extrapolating four steps of walking data from a single gait image by examining such characteristics as the way a person steps forward and their posture.
The team said it could identify individuals with 80% accuracy based on this analysis.