Companies team to provide fastest and lowest-power IoT face detection

30-07-2021 | Maxim | New Technologies

Maxim Integrated Products its MAX78000 ultra-low-power neural-network microcontroller detects and localises faces in video and images using Xailient’s proprietary Detectum neural network. Xailient’s neural network draws 250x lower power (at only 280 microJoules) than traditional embedded solutions. At 12ms per inference, the network performs in real-time and is quicker than the most efficient face-detection solution available for the edge.

The company’s microcontroller paired with Xailient’s neural network enhances overall power efficiency and battery life of hybrid edge/cloud applications that use a low-power ‘listening’ mode, which then wakes more complex systems when a face is detected.

Xailient’s Detectum neural network includes focus, zoom and visual wake-word technologies to detect and localise faces in video and images at 76x faster rates than conventional software solutions, at similar or better accuracy. In addition, the flexible network can be extended to applications other than facial recognition, such as livestock inventory and monitoring, parking spot occupancy, inventory levels and more.

“With the Xailient Detectum neural network, the MAX78000 is capable of both classification and localisation, so in addition to seeing faces in the image or video, you can also determine where those faces are in the image’s field of view,” said Robert Muchsel, Maxim Integrated Fellow and architect of the MAX78000 microcontroller. “Advanced applications include person, vehicle and object counting, presence or obstruction detection, as well as path mapping and footfall heatmaps.”

“AI is on track to be the second-largest carbon-emitting industry,” said Dr Shivy Yohanandan, Xailient CTO and inventor of Xailient’s Detectum neural network technology. “Replacing 14 legacy Internet protocol cameras that use traditional cloud AI with edge-based cameras equipped with the Maxim Integrated MAX78000 paired with Xailient’s neural network has the equivalent carbon impact of taking one gasoline-powered car off the road.”

By Natasha Shek