We’re excited to bring Transform 2022 back in person on July 19 and pretty much July 20-28. Join AI and data leaders for insightful conversations and exciting networking opportunities. Register today!
Emza Visual Sense and Alif Semiconductor have demonstrated an optimized face detection model running on Alif’s Ensemble microcontroller based on Arm IP. The two found it suitable for improving low-power artificial intelligence (AI) on the edge.
The emergence of optimized silicon, models and AI and machine learning (ML) frameworks has made it possible to perform advanced AI inference tasks, such as eye tracking and facial identification at the edge, at low power consumption and at low cost. This opens up new use cases in areas such as industrial IoT and consumer applications.
Create Edge Devices magnitudes faster
Using Alif’s Ensemble multipoint control unit (MCU), which the Alif claims is the first MCU to use the Arm Ethos-U55 microNPU, the AI model ran “an order of magnitude” faster than a CPU-only one. solution with the M55 at 400 MHz. It seems Alif meant two orders of magnitude as the footnotes state that the powerful U55 needed 4ms compared to 394ms for the M55. The highly efficient U55 executed 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 trained a completely “refined” face detection model on the NPU that can be used for face detection, viewing angle estimation and face landmarks. Full application code has been added 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 measure runtime, CPU demand, and memory allocation before silicon is available.
“To unleash 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 is possible on the tiniest endpoints, and Emza’s contribution of optimized models to the Arm AI open-source repository will accelerate the development of edge AI.”
Emza claims its visual detection technology is already shipping in millions of products and with this demonstration it is extending its optimized algorithms to SoC vendors and OEMs.
“Looking at the dramatically expanding horizon for TinyML edge devices, Emza is focused on enabling new applications in a wide variety of markets,” said Yoram Zylberberg, CEO of Emza. “There is virtually no limit to the types of visual detection use cases that can be supported by new powerful, highly efficient hardware.”
The mission of VentureBeat is a digital city square for technical decision makers to gain knowledge about transformative business technology and transactions. Learn more about membership.