Join or Sign in

Register for your free asmag.com membership or if you are already a member,
sign in using your preferred method below.

To check your latest product inquiries, manage newsletter preference, update personal / company profile, or download member-exclusive reports, log in to your account now!
Login asmag.comMember Registration
https://www.asmag.com/project/resource/index.aspx?aid=17&t=isc-west-2024-news-and-product-updates
INSIGHTS

How a cloud-based self-learning camera benefits users

How a cloud-based self-learning camera benefits users
Umbo CV, an exhibitor at ISC West earlier this year, is a start-up company based in San Francisco founded two years ago. Now it has its first product to show – a self-learning camera that the company said was first-of-its-kind in the industry.

Umbo CV, an exhibitor at ISC West earlier this year, is a start-up company based in San Francisco founded two years ago. Now it has its first product to show – a self-learning camera that the company said was first-of-its-kind in the industry.

Umbo was co-founded by CEO Shawn Guan, who has had a background in surveillance for some seven years before starting up the company. The other co-founders had backgrounds in software, machine learning, and artificial intelligence. Together they shared a vision of making video cameras that not just offer high resolution – which only works well in post-event investigation – but are also smart enough to help users detect threats early and deal with them accordingly. The result of was the Umbo SmartDome.

The camera has all the necessary features, for example data redundancy that stores video data both in the camera as well as in the cloud, 24-7 camera health monitoring, as well as a customizable management platform that looks after the well-being of the overall system.

But it is its learning ability that differentiates the camera, which is billed as a “cloud-first learning camera.” "It utilizes the cloud as its computing power to produce real artificial intelligence based on learning,” Guan said.

According to Guan, the technology is not based on pattern recognition. Instead, through a special algorithm, the camera “learns” what various objects – cars, trees, humans, and so on – look like in certain scenes and tells the user when something unusual is going on.

“Basically we teach the machine to recognize an event that's happened here that people care about,” Guan said. “You can think of it like it's a little kid. You want him to learn, and overtime it learns, and gets better and better at it. In short, what we are building right now is not anywhere in this industry. Not any company has it, not the way we build it."

According to Guan, the camera’s special features make it suitable for a wide range of vertical markets. “Our customer is pretty broad. Basically anyone who has issues that they are trying to solve right now with human, and that would be more efficiently done with machines, can use the camera to do a better job,” he said. “We can deploy it at jails, police stations, schools, retail shops, hotels ... the algorithm is generalized it doesn't matter where you put it.”

Currently, the company’s sales and marketing activities are split about half and half between the U.S. and non-US regions. Outside the U.S., the product has been shipped to Dubai, Europe, and Singapore, Guan said.

Subscribe to Newsletter
Stay updated with the latest trends and technologies in physical security

Share to: