Massimo Banzi, Andrea Richetta Promise to Showcase the Arduino UNO Q's Smarts in a Live Build

Massimo Banzi and Andrea Richetta from Arduino are preparing to live stream a practical project that showcases the capabilities of the "dual-brain" Arduino UNO Q single-board computer: a smart doorbell running a fully-local computer vision model.

"Go on your favorite online shopping platform, and you’ll find any number of smart doorbell options. Click to purchase, have it delivered, install it, download some app. But where’s the fun in that? And also, don’t you wonder how that thing works," the Arduino team asks by way of introduction to the planned live-build. "That thing that watches you and your loved ones go in and out, learning to recognize friends and delivery people, helping you check on your home even while you are gone. If you are thinking about the security of the place where you live, why not be more hands-on about your privacy while you’re at it?"

These are not rhetorical questions: Arduino is hoping to position its Arduino UNO Q as ideal for exactly these kind of practical hands-on projects, and aims to prove its chops with a live build starring Massimo Banzi and Andrea Richetta, based on a design Banzi has previously showcased on the SuperModerno YouTube channel.

The Arduino UNO Q, launched at the same time as Arduino announced its acquisition by Qualcomm, is a dramatic departure from the norm for the UNO family. Rather than a simple microcontroller development board like its predecessors, it's a fully-fledged single-board computer that combines a Linux-capable 2GHz Qualcomm Dragonwing QRB2210 quad-core Arm Cortex-A53 system-on-chip with an STMicroelectronics STM32U585 Cortex-M33 coprocessor running at up to 160MHz handling real-time workloads. Combined, the two make up what the company calls a "dual-brain" architecture — complete with an integrated development environment that allows the two halves to communicate and cooperate.

The DIY doorbell project pairs the Arduino UNO Q with a camera to deliver something very similar to a commercial smart doorbell system. Rather than sending your video off to a third-party server for analysis, though, it runs a small computer vision model locally on-device — bringing person and object recognition into the fold without sacrificing privacy.

The live-build session is scheduled to stream on September 22nd at 3pm CET/9am ET, with interested parties invited to sign up on YouTube to be notified when the stream starts.