Maxim Integrated’s new MAX78000 ultra-low power neural-network microcontroller detects and localizes faces in video and images using Xailient’s proprietary Detectum neural network. Xailient’s neural network draws 250x lower power (at just 280 microJoules) than conventional embedded solutions available in the market, and at 12 milliseconds (ms) per inference, the network performs in real time and is much faster as compared to the most efficient face-detection solution available for the edge.
The MAX78000 microcontroller paired with Xailient’s neural network improves overall power efficiency and battery life of hybrid edge/cloud applications that employ a low-power ‘listening’ mode which then awakens more complex systems when a face is detected. It is the ideal solution for battery-powered AI systems like home cameras, industrial grade smart security cameras and retail solutions that require face detection.
The Xailient’s Detectum neural network includes focus, zoom and visual wake-word technologies to detect and localize faces in video and images at 76x faster rates than conventional software solutions. Moreover, it offers high accuracy and the flexible network can be used in livestock inventory and monitoring, parking spot occupancy, inventory levels and more. Xailient’s neural network and Maxim Integrated’s ultra-low power MAX78000 microcontroller can extend the operating time of coin cell battery-powered, hybrid edge/cloud applications for many years. Besides, detecting faces in an image in just 12ms provides that flexibility between response time and accuracy.
The MAX78000 is available at Maxim Integrated’s website for $8.50 (1000-up, FOB USA); also available from authorized distributors and customers can also order the MAX78000EVKIT# evaluation kit that is available for $168. The Detectum neural network, series models, tools, services as well as focus, zoom and visual wake word technologies are available directly from Xailient website.