Chinese computer vision startup Watrix recently unveiled its gait recognition product which will enable security departments to quickly search and recognize identities, making it one of the world’s first commercialized products for gait recognition.
Gait recognition is a technique that integrates computer vision, pattern recognition and video processing to identify people by analyzing their body shape and walking posture.
The latest product is highly effective when targets walk from a long distance or in weak light, cover their faces or wear different clothes, and will be a great supplement to current computer vision products.
“The product will greatly improve efficiency in security-related areas including police, customs and ports as it is able to scan a one-hour video and identify objects within 10 minutes, with the accuracy rate reaching 94 percent,” said Huang Yongzhen, CEO of Watrix.
It has been tested by public security officials for more than 1,000 hours and has been involved in the detection of more than 20 cases.
Huang disclosed that the company has already obtained intent orders totaling more than 135 million yuan ($19 million).
Watrix, which was founded in 2016, was incubated by the Institute of Automation of the Chinese Academy of Sciences. The startup, focusing on computer vision, can provide solutions for sectors including security, transportation and manufacturing.
It raised 100 million yuan in its initial round of fundraising earlier this month, with Shenzhen Hang Bong Investment and Development Co Ltd and Hua He Capital leading the investment.
“The technology has been commercialized in an array of fields including safety and security, as well as transportation. It is a promising market that is able to nurture companies valued at some 10 billion yuan or even 100 billion yuan,” said Zhou Shuhua, founding partner of Hua He Capital.
The startup also launched an intelligent searching machine to help railway staff detect flaws in railways as well as other abnormalities, which can help reduce maintenance costs by around 60 million yuan from each machine.