Leti unveils face recognizing image sensor

May 25, 2021 // By Peter Clarke
Leti unveils face recognizing image sensor
French research institute CEA-Leti has announced an autonomous image sensor that can be 'always-on' and used to activate appliances by face or gesture recognition.

Called µWAI (micro-WAY) and the size of a 1€ coin, the imager includes sensor, ASIC and a battery. The module has an optimized algorithmic pipeline, in which results from a sequence of elementary algorithms are used to provide low-power wake-up modes and compact silicon implementation to keep costs down.

The smart image sensor features auto-exposure for lighting conditions and 88dB dynamic range, as well as motion detection and feature extraction, and AI-based object recognition.

This allows the imager to open up systems for just a few pJ/pixel/frame. A typical discrete camera plus processor implementation would require about 10^4 more energy than µWAI, Leti said.

"The recognition engine is optimized to recognize faces when movement is detected. CEA-Leti’s team is working hand-in-hand with STMicroelectronics to develop specific smart-imager products as we consider extending the technology to other use cases," said Antoine Dupret, CEA-Leti’s industrial partnership manager

The unit consumes 3 to 6 microwatts and should achieve a five-year, always-on CR1025 battery lifetime.

Applications and functions include automatic switching and face identification in mobile devices, contact-less smart switching of household appliances and sport-and-entertainment devices in smart homes. µWAI also provides face recognition, people counting, alarm triggering in smart buildings, vehicle-interior situation awareness, driver identification, parking-situation awareness and a smart-unlocking system in automobiles.

Related links and articles:

www.leti-cea.com

News articles:

MEMS startup ramps microphone production with Tower

Deep learning processor for always-on audio, sensor apps

AI SoC enables smart tiny edge devices


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.