Imagimob AB (Stockholm, Sweden has announced an agreement to integrate its TinyML development platform with Syntiant’s NDP120 neural decision processor.
This will enable developers to use the Imagimob platform to create production-ready deep learning tinyML applications, and to optimize and deploy the ML models using the NDP120. The combination supports a range of applications, such as sound-event detection, keyword spotting, fall detection, anomaly detection, gesture detection and other use cases.
The NDP120 brings always-on voice and sensor neural processing to multiple types of consumer and industrial products. Packaged with the Syntiant Core 2, the company’s second generation deep neural network, the NDP120 supports Ok Google and Hey Google hotwords at under 280 microwatts power consumption and can run multiple applications simultaneously at under 1mW.
The Imagimob platform contains a built-in fall detection starter project, which includes an annotated dataset with metadata (video), and a pre-trained ML-model that detects person falls from a belt-mounted inertial measurement unit (IMU).
“We see a lot of market demand in sound-event detection, fall detection and anomaly detection,” said Anders Hardebring, CEO and co-founder at Imagimob, in a statement.
“Studies suggest that there are more than 35 million falls in the US alone that require some kind of medical attention, so there is significant opportunity for applications across both consumer and industrial use cases,” said Kurt Busch, CEO of Syntiant, in the same statement.
Imagimob was founded in 2013 and has served customers in automotive, manufacturing, healthcare, and lifestyle industries. It moved into AI in 2020 with a development platform for machine learning on edge devices.
Related links and articles: