Whether it is facial recognition tech that is (allegedly) able to pick a wanted criminal out of a crowd of thousands or aerial drones which use image recognition smarts to predict fights before they take place, there is no doubt that we are living through a major paradigm shift for automated surveillance technology. But this kind of tech can have more grounded, everyday applications, too — like helping prevent shoplifters stealing goods from their local mom-and-pop corner store.
That is something seemingly demonstrated by a new artificial intelligence security camera called the “A.I. Guardman,” built by Japanese telecommunication company NTT East and startup Earth Eyes Corp. The camera uses a special pose detection system to identify behavior it deems to be suspicious. In the event that this kind of behavior is spotted, it sends an alert to the store owner’s smartphone, allowing them to take action.
While it’s seemingly not been the subject of any specific peer-reviewed papers, the camera has reportedly been shown to be capable of reducing shoplifting by up to 40 percent. Positive-sounding numbers are to be expected from a marketing department, but the technology in this case comes from a reputable source: Being based on open-source technology first developed by Carnegie Mellon University.
As noted, technology such as this is not unheard of. Heck, while it is a bit less advanced, we have even covered homebrew hacks such as a home security camera system designed to set off the garden sprinklers whenever a neighbor’s cat enters uninvited. What is promising about this technology, however, is the fact that it is a plug-and-play system which can be easily installed by shopkeepers without them necessarily having to have much technical knowledge.
Figures given to The Verge suggest that the camera will go on sale at the end of next month, priced in the vicinity of $2,150, with an extra $40 monthly subscription to cover the necessary cloud computing-based video analysis. NTT is planning to roll the camera out in 10,000 stores over the next three years.
In other words, we suggest that you get your shoplifting done as soon as possible. (Note to would-be shoplifters: We’re kidding!)
- Analog A.I.? It sounds crazy, but it might be the future
- Nvidia’s latest A.I. results prove that ARM is ready for the data center
- Can A.I. beat human engineers at designing microchips? Google thinks so
- The future of A.I.: 4 big things to watch for in the next few years
- Google’s LaMDA is a smart language A.I. for better understanding conversation