We look forward to presenting Transform 2022 in person again on July 19th and virtually from July 20th to 28th. Join us for insightful conversations and exciting networking opportunities. Register today!
Emza Visual Sense and Alif Semiconductor have demonstrated an optimized facial recognition model running on Alif’s Arm IP-based Ensemble microcontroller. The two found it suitable for enhancing low-power artificial intelligence (AI) at the edge.
The advent of optimized silicon, models, and AI and machine learning (ML) frameworks has made it possible to run advanced AI inference tasks like eye tracking and face recognition at the edge with low power consumption and low cost. This opens up new use cases in areas such as industrial IoT and consumer applications.
Manufacture Edge devices orders of magnitude faster
By using Alif’s Ensemble Multipoint Control Unit (MCU), which Alif says is the first MCU to use the Arm Ethos-U55 microNPU, the AI model ran “an order of magnitude” faster than a CPU-only solution with the M55 at 400MHz. It seems Alif meant two orders of magnitude as the footnotes say the high performance U55 took 4ms compared to 394ms for the M55. The highly efficient U55 ran the model in 11 ms. The Ethos-U55 is part of Arm’s Corstone 310 subsystem, for which it launched new solutions in April.
Emza said it has trained a full “sophisticated” face recognition model on the NPU that can be used for face recognition, yaw face angle estimation and facial features. The full application code has been contributed to Arm’s open-source AI repository called ML Embedded Eval Kit, making it the first Arm AI ecosystem partner to do so. The repository can be used to gauge runtime, CPU demand, and memory allocation before silicon is available.
“To realize the potential of endpoint AI, we need to make it easier for IoT developers to access higher performance, less complex development flows, and optimized ML models,” said Mohamed Awad, Vice President of IoT and Embedded at Arm. “Alif’s MCU is helping to redefine what’s possible at the smallest endpoints, and Emza’s contribution of optimized models to the Arm AI open-source repository will accelerate edge AI development.”
Emza claims its visual sensing technology is already shipping in millions of products, and with this demonstration, it extends its optimized algorithms to SoC vendors and OEMs.
“With the dramatically expanding horizon for TinyML edge devices, Emza is focused on enabling new applications across a broad range of markets,” said Yoram Zylberberg, CEO of Emza. “There is virtually no limit to the types of visual sensing use cases that can be supported by new powerful, highly efficient hardware.”
VentureBeat’s mission is intended to be a digital marketplace for technical decision makers to acquire knowledge about transformative enterprise technology and to conduct transactions. Learn more about membership.