Imagimob Launches "Ready Models" for Quick Edge AI Deployments on Microcontrollers

On-device edge artificial intelligence (edge AI) specialist Imagimob has announced the launch of Ready Models — complete machine learning (ML) solutions to real-world problems which are ready to deploy on existing microcontroller hardware.

"If you look at the edge AI space right now, you can probably count on one hand how many companies provide off-the-shelf models for any one solution," claims Imagimob's Sam Al-Attiyah in support of the company's latest launch. "Our Ready Models are built upon eight years of expertise and thoroughly tested out in the field in different environments, so they are validated in terms of performance. And the fact that we are running them on small edge devices is really unique."

The Ready Model range launches with four machine learning models targeting audio detection, including one which can pick out the sound of a crying baby for smarter baby monitors, another which alerts pedestrians to the sound of sirens, and two more offering coughing and snoring detection for wearables. The company has also confirmed other Ready Models in the work for audio sensors, along with others for radar sensors, inertial measurement units (IMUs), and capacitive sensors.

The biggest selling point of the Ready Models is right there in the name: they're ready, offering the ability to deploy models with "zero or limited engineering or AI competence." "This is a much easier way for companies to begin their ML journeys — they don’t have to make such a big investment to start using it on their edge devices," claims Anders Hardebring, Imagimob's chief executive officer.

"Depending on the skillset and expertise in a company, developing a custom model for production typically takes six months to a year. With our Ready Models, they can have new Edge AI features up and running essentially overnight."

Details on the Ready Models are available on the Imagimob website — though pricing is only provided on application.