A new Raspberry Pi camera project has been posted to the Hackster.io website by maker Ricardo de Azambuja using a Raspberry Pi Zero together with the Raspberry Pi Camera Module V2 and a Google Coral USB Accelerator to create a low-power customizable Internet of Things smart camera.
The Coral USB Accelerator offers an easy way to add an Edge TPU coprocessor to your project, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port. The on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS using low-power.
“Maple Syrup Pi Camera is part of my research project,” Ricardo tells us. “I’m one of the 25 TRAIN@Ed Research Fellows at University of Edinburgh. I am working on a project focused on helping local tourist attractions to better manage tourist flow, still GDPR compliant by design. My solution is to process information in the camera without ever saving or transmitting personal data. In addition to that, I wanted something open-source that could be customised, and as low-power as possible, allowing it to run a full day on an off-the-shelf power bank. Raspberry Pi Zero W is my go-to IoT device and, together with the Google Coral USB Accelerator, it has become my powerhouse for machine learning inference.”
For full details on how to build your very own Maple Syrup Pi smart camera jump over to the Hackster.io website by following the link below where Ricardo de Azambuja has kindly published full instructions, component list and code.
Source : RPiF : Ricardo de Azambuja
Latest Geeky Gadgets Deals
Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.
