Fujitsu is collaborating with Nvidia to integrate AI-powered radio access networks into video analytics, offering the ability to detect potential criminal activity or identify vulnerable individuals in distress, such as someone who has fallen. Radio access networks, which connect devices to mobile telecommunications systems via radio connections, are being enhanced with AI to reduce latency and improve real-time responsiveness in critical applications.
At the Mobile World Congress in Barcelona, Fujitsu is showcasing a range of innovative applications powered by this advanced technology. One of the standout uses involves CCTV monitoring, where the system not only interprets what is happening in a video feed but also analyzes body movements to predict criminal intent or detect emotional cues.
Rob Hughes, Fujitsu’s head of wireless marketing, explained that the video analysis starts by creating a skeleton framework over the footage of a human subject, helping the AI understand which body parts are in motion and what actions they are performing. This can extend to interpreting emotions—such as identifying angry body language—and even predicting potential threats.
“This technology could transform security monitoring,” Hughes noted. “While CCTV cameras are ubiquitous, it’s impossible to have human eyes watching everything. With AI, we can spot threatening behavior or anticipate a fight before it happens, enabling us to alert security personnel instantly.”
Another practical application showcased by Fujitsu addresses common retail theft tactics, such as self-checkout fraud. For example, when a person uses the label of an inexpensive item to scan an expensive product, the AI-powered system can detect the motion of one object being held over another and trigger a security alert.
“We can track that motion in real-time, allowing us to dispatch security personnel immediately,” Hughes added.
Fujitsu engineers are also exploring additional uses for AI-enhanced video analysis, including augmented reality applications to assist in traditional industries. One innovative example is for logging companies, where cameras could automatically assess the width of trees to guide workers in determining which ones to cut.
“As an example, a logger wearing AR goggles could receive real-time feedback on whether a tree is suitable for cutting,” Hughes explained. “The goggles would process the image and provide instructions, streamlining decision-making and improving efficiency.”
By integrating AI with radio access networks, Fujitsu is not only enhancing security and fraud detection but also revolutionizing traditional job processes with automation and real-time analytics, pushing the boundaries of what’s possible with video technology.
By Impact Lab
