Japan Utilizing Gait Recognition in Crime Investigations

May 6, 2018

Tokyo- Gait recognition technology, a method to identify people by characteristics shown unconsciously in the ways they walk, is being utilized in criminal investigations in Japan.

The technology enables the identification of individuals even from images taken from a distance and low-resolution footage. A video image of only two strides is sufficient to identify with high accuracy the person, based on his or her arm swings, the length of stride and other characteristics.

Researchers are also working to further improve the accuracy of the technology, with the use of artificial intelligence.

On a street in Tokyo's upscale Ginza district in April 2017, a man was robbed of some 40 million yen during the daytime soon after he converted gold into cash.

In the case, police collected footage from some 740 security cameras, mainly those installed in the Japanese capital, according to informed sources. The gait recognition technology helped identify three of the four men arrested in the case although they wore a face mask or helmet when they committed the crime.

The technology can identify people even if they pretend to be others, because they "show their own unique gait patters unconsciously," said Hironori Yamauchi, a senior official of the Japan Image Analysis Association and professor emeritus at Ritsumeikan University.

The National Police Agency's National Research Institute of Police Science introduced the gait recognition system in 2013 on a trial basis and used it in investigations of some 60 cases. Analyzed data were presented as evidence during trials on some cases.

Yasushi Yagi, professor at Osaka University's Institute of Scientific and Industrial Research, which developed the gait recognition system, has newly created technology to identify with 96 pct accuracy a person walking in different directions in video images.

The new technology, announced in November last year, builds on an AI technology known as deep learning for processing large volumes of data. The AI learned gait patterns of some 10,000 people of various ages.

Yagi said that he hopes to develop a system for tracking terror suspects based on gait patterns registered in advance using the new technologies, with the aim of employing it in large-scale events such as the 2020 Tokyo Olympics and Paralympics.

"In the future, I also want to apply the technologies to check health of people from the ways they walk," he added. Jiji Press