Imagimob demonstrates tinyML fall detection

Imagimob demonstrates tinyML fall detection

Imagimob has implemented the tinyML fall detection application running on Syntiant’s ultra-low-power NDP120 Neural Decision Processor.

The application has been developed in the Imagimob end-to-end tinyML development platform, which includes a built-in fall detection starter project. This project includes an annotated dataset with metadata (video) and a pre-trained ML-model (in h5 format) that is capable of detecting person falls from a belt-mounted device using IMU data.

The fall detection model is open to any developer to use and can be improved on by collecting more data. Developers can create production-ready deep learning tinyML applications and deploy and optimise them at the click of a button.

Anders Hardebring, CEO and Co-Founder at Imagimob, said: “The collaboration with Syntiant will be very valuable for our customers because it allows them to quickly develop and deploy powerful, production-ready deep learning models on the Syntiant NDP120.

“We see a lot of market demand in sound event detection, fall detection and anomaly detection.”

Fall detection for firefighters can identify fall events with high accuracy to improve their safety on the job.