Berenice Baker
Fujitsu is tapping AI-powered radio access networks developed in partnership with Nvidia to power video analytics that can detect whether someone is about to commit a criminal act or if a vulnerable person has fallen.
Radio access networks are a component of mobile telecommunications systems that connect individual devices to other parts of a network through radio connections. Adding the AI element reduces the latency, making them more effective for applications that require a real-time response.
The company is showcasing a number of applications powered by the technology at Mobile World Congress, underway in Barcelona through March 6.
One application could be CCTV monitoring, not just interpreting what is happening in an image but also interpreting what is happening or even predicting criminal intent or human emotions based on body movements.
Video analysis of this kind begins by superimposing a skeleton framework over video footage of a human and figuring out which parts are which and what they’re doing, according to Fujitsu head of wireless marketing Rob Hughes.
“We can even get to the point where we can interpret emotions, so yoAnother example would be preventing a common supermarket self-checkout fraud where someone takes the label of an inexpensive bottle of wine and scans it over the label for an expensive bottle of wine.
Related:Generative AI Transforming Telecommunications Landscape; Mobile World Congress 2025
“We can detect that motion of holding something over another thing and dispatch security personnel to deal with it,” said Hughes.
Fujitsu engineers are brainstorming other potential uses for AI-powered video analysis, including for augmented reality applications to support some of the oldest and most traditional jobs.
“One use case I've heard of is for logging companies to have cameras that will automatically judge and assess the width of a tree,” said Hughes.
“The guy is going along trying to decide which trees to cut, he's wearing goggles that process the image of the trees in front of him and give him instructions on whether or not that’s the right tree to cut.”u can tell where there's angry body language and not angry body language,” he said.
“One of the use cases here is security cameras. There are CCTV cameras everywhere, but you can't have human eyes watching everything. This could identify threatening behavior or a fight about to start so you can immediately dispatch security.”
Read more about:
Mobile World Congress 2025
About the Author
Berenice Baker
Editor, Enter Quantum
Berenice is the editor of Enter Quantum and co-editor of AI Business. Berenice has a background in IT and 20 years of experience as a technology journalist.
Sign Up for the Newsletter
The most up-to-date AI news and insights delivered right to your inbox!
Stay Updated!
