Recently, Renesas Electronics Corporation expanded its existing RZ/V family of microprocessors to add a new device that enables AI processing of image data from multiple cameras. This data process offers improved accuracy of image recognition for machine vision AI applications. The new hardware platform, RZ/V2MA microprocessor, is equipped with two 64-bit Arm Cortex cores and delivers high computing performance with an operating frequency of 1GHz.
Renesas RZ/V2MA MPU comes with high-speed interfaces, including Ethernet, USB, and PCIe expansion ports that allow image input from multiple camera sources. Alongside the DRP-AI accelerator, the RZ/V2MA MPU also includes an OpenCV accelerator that allows rule-based image processing. This brings high accuracy for image recognition for a wide range of applications, such as AI-equipped gateways, video servers, security gates, POS terminals, and robotic arms.
“With the new DRP-AI TVM tool, we are offering designers the option to expand AI frameworks and AI models that can be converted to executable formats, allowing them to bring the latest image recognition capabilities to embedded devices using new AI models,” said Shigeki Kato, Vice President of Renesas’ Enterprise Infrastructure Business Division.
Other AI capabilities include the addition of DRP-AI TVM, an open-source deep learning compiler of Apache TVM technology. The DRP-AI translation is designed to convert the AI models into DRP-AI executables, while the DRP-AI TVM compiler lets the DRP-AI accelerator work in combination with the CPU. At the time of writing, Renesas supports ONNX and PyTorch AI models and has plans to support TensorFlow in the future.
The company has also developed a vision AI gateway solution, which is an AI-object detection and recognition platform that uses multiple cameras to collect and transmit data wirelessly. The solution uses the newly announced RZ/V2MA MPU in combination with other Renesas products such as power ICs, VersaClock clock generator, and communication modules for Wi-Fi, Bluetooth, and LTE. This solution provides users with flexible connectivity options and an optimized power supply system that has been tested to accelerate the development of AI devices.
“Renesas’ RZ/V series is ideal for embedded devices since it does not need fans or heat sinks, due to its extremely low power consumption and low heat capability when running AI,” said Chiharu Nakabayashi, President of Amnimo Inc., a provider of IoT and AI-based services and a wholly owned subsidiary of Yokogawa Electric Corporation.
For more information on the Renesas RZ/V2MA microprocessors, head to the official product page.