Renesas RZ/V2MA microprocessor embeds AI & OpenCV accelerators for image processing

Renesas has launched the RZ/V2MA dual-core Arm Cortex-A53 microprocessor with a low-power (1TOPS/W) DRP-AI accelerator and one OpenCV accelerator for rule-based image processing enabling vision AI applications.

The MPU also supports H.265 and H.264 video decoding and encoding, offers LPDDR4 memory and eMMC flash interfaces, as well as Gigabit Ethernet, a USB 3.1 interface, PCIe Gen 2, and more. The RZ/V2MA microprocessor targets applications ranging from AI-equipped gateways to video servers, security gates, POS terminals, and robotic arms.

Renesas RZ/V2MA specifications:

The Renesas RZ/V2MA EVK, designed in collaboration with SHIMAFUJI, is available for evaluation and early software development.

Renesas says the DRP-AI accelerator can achieve 52 fps when executing the TinyYoloV3 program, and they provide the DRP-AI Translator used on previous generation RZ/V microprocessors, plus a new DRP-AI TVM tool for converting ONNX and PyTorch AI models based on Apache TVM technology. TensorFlow models will also be supported in the future. The DRP (OpenCV) accelerator is supported through the RZ/V2MA OpenCV Accelerator Support Package Version.1.00.

The company has also developed the “Vision AI Gateway Solution” AI-based object detection and recognition platform based on the RZ/V2MA MPU. The solution uses multiple cameras to collect video data, process the data, and transmit it over Wi-Fi, Bluetooth LE 5.1, or LTE Cat M1 using modules from Renesas.

One example of an AI Edge gateway based on Renesas RZ/V2MA dual-core Cortex-A53 processor is the Amnimo Edge gateway running Ubuntu 18.04 Linux and equipped with four PoE interfaces, an LTE Cat4 & GNSS module, and other interfaces such as RS232 and USB.

The Renesas RZ/V2MA microprocessor and development tools are said to be available now, but there’s no public information with regard to pricing. You’ll find more details including plenty of documentation and software resources on the product page.

Thanks to TLS for the tip.

Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.

Support CNX Software! Donate via cryptocurrencies or become a Patron on Patreon

Related posts: