Gait recognition is to identify humans based on their gait features. Compared with other biometrics such as face, iris, palm print and finger print, gait features are still  obtainable and recognizable at a distance with a low-resolution video. Therefore, with characteristics of non-contact, long distance (50 meters), cross-view (360°) recognition range and hard to disguise, gait recognition fills the market gap of long distance identification in public security industry.

Gait Recognition in Mission: Impossible – Rogue Nation (2015)

Watrix is so far the only commercialized gait recognition company in the world. It developed the world’s most advanced gait recognition technology. The average recognition rate can reach 94.1%, much better than the previous best result (less than 65%). Watrix also built the world’s largest gait database, whose capacity is dozens of times larger than the second. And the company took a leading position in all aspects of this technology, such as target detection, segmentation, recognition and tracking, etc. In this way, it can recognize people from 50 meters away using ordinary 2K camera and has less correlation with face information and lighting conditions.

In the CCTV program “Machine V.S Human Intelligence” (2017), Watrix beat the “Super Brain” Memory Master  by the name of Meng Yuan in identifying target suspect, target dog and dog silhouette. Watrix’s gait recognition technology was praised as “smarter than human” by Qizhi Yao, the Turing Award Winner. Finally, the team was solely awarded as “2017 Intelligence Pioneer Team” by CCTV Channel 1.

Watrix Gait Recognition Platform


SHUI DI SHEN JIAN

all-in-one (AIO) PC searching for targets with gait recognition tech

SHUI DI SHEN JIAN, all-in-one (AIO) PC searching for targets with gait recognition technology, developed by WATRIX, was launched on 26th Oct. 2018.

SHUI DI SHEN JIAN targets  suspects by monitoring their posture as the suspects walk from a distance of up to 50 meters.. It can  assist  public security department in identifying suspects.

Different from facial recognition, the gait recognition technology is more flexible. It is capable of identifying targets from any angle regardless of if they cover their faces or wear different clothes or walk outside at night, without suspects being aware.

The portable machine, weighing about 15 kilograms, can replace manual workers by quickly spotting suspects while they are walking. Users need to upload videos onto the machine first and offer the machine an example video of the target, then the machine can complete a search through one hour of video in 10 minutes. Its accuracy is about 94 percent.

At present, SHUI DI SHEN JIAN has been piloted in the public security system for more than 1,000 hours, being used in the detection of more than 20 cases. It had retrieved 2,000G of public security videos so far.