The period between the 1970s and the early 2000s was known as the “dark age of artificial intelligence.” Due to less sophisticated computational power, slow processing and a lack of data, what was once thought of as a technology that could change human lives turned out to be no more than an idea for science fictions, a concept that didn’t live up to its full potential.
Yet, with the concept of machine learning taking shape in the early 2000s, things have changed. Machines that learn by themselves to gain intelligence – so much so that even a top human go player was defeated by Google’s AlphaGo earlier this year – have revived an interest in AI, prompting companies to devote huge R&D resources into this area. In fact, the growth potential for AI is not to be ignored. A recent study by Bank of America Merrill Lynch pointed out that the broad market for artificial intelligence is estimated to grow to US$153 billion by 2020, consisting of $83 billion for robotics and $70 billion for AI-based analytics.
So how is artificial intelligence tied to security? The key is data. As we all know, security is heavily data-driven, especially in this day and age where most security devices have gone IP and generate data over the network. In fact, it is said that approximately 60 percent of all big data is video content. Analyzing and making sense of this data with minimum human efforts is what makes artificial intelligence relevant in security.
In general, artificial intelligence is used in security in three ways. The first is multi-trait recognition, whereby the computer helps identify particular objects or individuals by various traits that they possess, for example their sex, age, hairstyle and physique, among others. When done effectively and accurately, this not only helps save cost and human efforts but also reduces the time it takes to apprehend a suspect after an incident.
Another way in which AI is used in security is gait recognition, whereby the system identifies people by how they walk. Compared to other biometrics, gait recognition holds an advantage in that it is non-invasive and does not involve the act of touching on the part of the identified subject. It can be used in access control and can especially come in handy when identifying particular individuals in low-resolution video.
The third deep learning AI technology used in security is the 3D camera, although it’s more for management purposes. These cameras are deployed in certain areas, for example parks or tourist attractions, where the visitor’s height determines the kind of ticket he should buy. While traditional measuring tools can be used, they take longer time and can be less than accurate. A better solution would be 3D cameras, which obtain depth and color information at the scene, establish a correlation between the depth information and the X and Y axes, and do a 3D reconstruction of the individual to obtain his or her height.
With data from security devices becoming huge and overwhelming, artificial intelligence is needed to help users analyze and extract meanings out of this data. Indeed, data is the engine that propels artificial intelligence forward in security.