Site icon Wonderful Engineering

Japanese Startup Designs AI That Can Detect Theft Before It Takes Place

Vaak, a Japanese tech startup, claims that it has created an artificial intelligence software, VaakEye, that can analyze footage from surveillance cameras for ascertaining suspicious behavior and prevent shoplifting before it actually takes place.

If this sounds like a movie, that is probably because it most certainly is; Minority Report. The famous movie starring Tom Cruise was released back in 2002. The movie explored the idea of preventing a future crime before the perpetrator performed any act that was even remotely criminal. The movie, when it was released, was merely an amazing sci-fi idea, however; thanks to the amazing speed at which technology has progressed, we already have an early version of the technology that was showcased in the movie.

VaakEye is capable of detecting shoplifting before it can actually take place. It does so by analyzing the footage from surveillance cameras for any suspicious movements that might otherwise be too discrete for shop owners to detect. The algorithm then ascertains if there is enough chance of a person shoplifting and provides an alert via a smartphone app so that the crime can be prevented.

VaakEye first surfaces in the news back in December 2018 when it picked up on shoplifting activity that was previously undetected at a convenience store located in Yokohama. The suspect was an 80-year old man that was caught a few days later following the theft of a hat. As of now, Vaak is testing VaakEye in a couple of stores situated in Tokyo area. However, it has plans for installing VaakEye in 100,000 stores all over Japan during the course of the next three years.

Vaak founder Ryo Tanaka said while recalling the first time VaakEye was able to detect potential shoplifters, ‘I thought then, “Ah, at last!” We took an important step closer to a society where crime can be prevented with AI.’ VaakEye is based on an intricate algorithm that uses over 100,000 hours of surveillance of footage with more than 100 different factors for harnessing deep learning. The factors include the person’s face, clothes, movement, overall behavior, and even factors the weather conditions and the area where the shop is located.

30-year-old Tanaka has plans for enhancing the VaakEye’s functionality. He said, ‘We’re still just discovering all the market potential. We want to keep expanding the scope of the company.’ What do you think of this amazing artificial intelligence software? Do let us know!

Exit mobile version