Monday, March 13, 2023
Live demo at the Renesas booth at Embedded World from March 14-16
Plumerai delivers a complete software solution for people detection. Our AI models are fast, highly accurate, and tiny. They even run on microcontrollers. Plumerai People Detection and the Plumerai Inference Engine have now been optimized for the Arm Cortex-M85 also, including extensive optimizations for the Helium vectorized instructions. We worked on this together with Renesas, an industry leader in microcontrollers. Renesas will show our people detection running on an MCU that is based on the Arm Cortex-M85 processor at the Embedded World conference this week.
Microcontrollers are an ideal choice for many applications: they are highly cost-effective and consume very little power, which enables new battery-powered applications. They are small in size, and require minimal external components, such that they can be integrated into small systems.
Plumerai People Detection runs with an incredible 13 fps on the Renesas Helium-enabled Arm Cortex-M85, greatly outperforming any other MCU solution. It speeds up the processing of Plumerai People Detection by roughly 4x compared to an Arm Cortex-M7 at the same frequency. The combination of Plumerai’s efficient software with Renesas’ powerful MCU opens up new applications such as battery-powered AI cameras that can be deployed anywhere.
Faster AI processing is crucial for battery-powered devices because it allows the system to go to sleep sooner and conserve power. Faster processing also results in higher detection accuracy, because the MCU can run larger AI models. Additionally, a high frame rate enables people tracking to help understand when people are loitering, enter specific areas, or to count them.
Renesas has quickly become a leader in the Arm MCU market, offering a feature rich family of over 250 different MCUs. Renesas will implement the new Arm processor within its RA (Renesas Advanced) Family of MCUs.
Contact us for more information about our AI solutions and to receive a demo for evaluation.