NEW “GAIT RECOGNITION” TECH ID’S PEOPLE BY HOW THEY WALK

 

CHINA IS AT IT AGAIN

We are seeing a trend in the Artificial Intelligence industry. China is outspending the rest of the world by billions of dollars in order to drive innovation forward. However, just like the AI news anchor which we covered last week China is once again pushing technology that the world just isn’t ready for. Chinese authorities have begun deploying a new tool that uses people’s body shapes and how they walk in order to identify them even when their faces are not visible to the camera.

This technology is already being used on the streets of Bejing and Shanghai and is already raising some serious privacy concerns. The CEO of Watrix, the company who developed this software, says that its system can identify people from up to 165 feet away, even with their back turned or face covered. This can fill a gap in facial recognition, which needs close-up, high-resolution images of a person’s face to work. That’s wishful thinking but now that you no longer need people’s cooperation in order to identify them there is a lot of potential to violate basic human rights and there must be a line drawn somewhere before this gets out of hand.

gait recognition

Watrix CEO Huang Yongzhen demonstrates the potential of their new gait recognition software.

HOW DOES IT WORK?

Gait recognition is based on the notion that each person has a distinctive and idiosyncratic way of walking, which can easily be discerned from a biomechanic viewpoint. Human movement does consist of synchronized movements of hundreds of muscles and joints, though basic movement patterns are similar, gait does vary from one person to another in terms of timing and magnitude. Gait recognition groups spatial-temporal parameters, such as step length, step width, walking speed and cycle time with kinematic parameters, such as joint rotation of the hip, knee and ankle, mean joint angles of the hip, knee and ankle and thigh, trunk and foot angles. Also considered is the correlation between step length and the height of an individual.

Sophisticated machine learning algorithms are able to discern the patterns of movement people exhibit while walking and match them up to an identity in a database. It works so well in fact that it cannot be fooled by simply limping or hunching over because the body as a whole is being analyzed. There aren’t many good ways of fooling this technology just yet. Experts point out that this is unobtrusive compared to other forms of biometric identification such as fingerprint or iris recognition which makes it advantageous. It is a double edged sword because it also presents many potential problems.

gait recognition

A SLOWER ROLL OUT THAN EXPECTED

This technology isn’t exactly new. It has been researched all over the world dating back to 2013 when countries like the US, the UK, and Japan were taking a serious look at it and its possible benefits. There have been some computational limitations on the roll out of this technology because it takes more powerful computers to perform the analysis since it needs many images of a person’s gait to build a model as opposed to other biometric forms of identification.

Watrix’s software extracts a persons silhouette from a video and analyses the movement to build a model of how the person walks. It isn’t capable of identifying people in real-time yet. Users must upload video into the program, which takes about 10 minutes to search through an hour of video. It doesn’t require special cameras, the software can use footage from surveillance cameras to analyze gait. The software still isn’t quite as fast and accurate as facial recognition it is still viewed as being good enough for commercial use boasting a 94 percent accuracy rate.

LIMITATIONS AND CONCERNS OF GAIT RECOGNITION TECH

So as you can see there are still some limitations to this. The only real reason why this is being pushed forward in China so quickly relative to other parts of the world is because of China’s need to exert social control on its population. Chinese officials justify the use of this technology by pointing out that perhaps it could identify elderly individuals that have fallen. Or that it can make life safer and more convenient for everyone. Those justifications are easy to hide behind when you are a part of a governing body with the power to identify people just with the way they walk.

Companies like Google and Facebook in the US have also received a lot of backlash for the facial recognition products they intend to create. Facial recognition, like gait recognition is capable of operating from afar without the user’s consent which is not the case when identifying someone with only their fingerprints. These large tech companies have been self regulating for a long time now and it is starting to get out of hand. The ethical concerns of technology like this are beyond the scope of this post and will be covered sometime in the near future but it is important to remember that we have not completely fallen the rabbit hole just yet.

Leave a Reply

Your email address will not be published. Required fields are marked *