acm-header
Sign In

Communications of the ACM

ACM TechNews

These Cameras Can Spot Shoplifters Even Before They Steal


View as: Print Mobile App Share:
A demonstration of Vaaks crime detection system.

A Japanese startup has developed software that can identify potential shoplifters on video surveillance footage.

Credit: Akio Kon/Bloomberg

Japanese startup Vaak has developed artificial intelligence (AI) software that looks for potential shoplifters on video surveillance footage.

The software searches for indicators such as fidgeting, restlessness, and other potentially suspicious body language.

Last year, Vaak helped catch a shoplifter at a convenience store in Yokohama, Japan. The startup had set up its software in the shop as a test case, and was able to identify previously undetected shoplifting activity.

The ability to detect and analyze unusual human behavior also has other applications.

Vaak is developing a video-based self-checkout system, and wants to use the video to collect information on how consumers interact with items in the store to help shops display products more effectively.

The software could also be used in public spaces to detect other kinds of suspicious behavior.

From Bloomberg
View Full Article

 

Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account