概览

描述

The AI hardware IP, DRP-AI, configured with DRP and AI-MAC, combines both a high-speed AI inference and low power consumption and realizes 1TOPS/W class power performance. In addition, the image signal processor (ISP) is highly robust, producing a stable image independent of the environment, allowing for a high AI recognition accuracy. With these features, the RZ/V2M realizes low power consumption, which is a challenge for embedded devices, making heat dissipation measures easier. Since heat sinks and cooling fans are no longer needed, the equipment can be miniaturized and the BOM cost can be reduced. The result is that it is ideal for vision AI applications in a wide range of embedded markets, including surveillance security, retail, office automation (OA), industrial automation, robotics, and healthcare. In addition, the RZ/V2M also features abundant high-speed communication interfaces such as USB 3.1, PCI-Express, Gigabit Ethernet, and many CPU peripheral functions, so it can also be used in a variety of applications.

特性

  • CPU and DDR Memory Interfaces
    • 2x Cortex-A53 up to 1.0GHz
    • 32-bit LPDDR4-3200
  • Vision and Artificial Intelligence
    • AI Accelerator; DRP-AI at 1.0 TOPS/W class
    • Image Signal Processor (ISP) of multi-stream available
    • Camera Interface; 2x MIPI CSI
    • Face and Human Detection Engine
  • Video and Graphics, Display
    • H.265/H.264 Multi Codec
      Encoding; h.265 up to 2160p30, h.264 up to 1080p120
      Decoding; h.265 up to 2160p30, h.264 up to 1080p120
    • 2D Graphics Engine; 200MPixels/s
    • Display; MIPI-DSI (4-lane), HDMI 1.4a
  • High Speed Interfaces
    • 1x Gigabit Ethernet
    • 1x USB3.1 Gen1 Host/Peripheral
    • 1x PCIe Gen 2 (1-lane)
    • 2x SDIO 3.0
    • 1x NAND Flash Interface ONFI1.0
    • 1x eMMC 4.5.1
  • Hardware Security Engine provided
  • Package: FCBGA, 15x15mm 0.5mm pitch

应用

文档

文档标题 类型 日期
PDF16.00 MB
手册 - 硬件
PDF51 KB
指南
PDF642 KB
白皮书
PDF4.55 MB
应用文档
PDF172 KB
应用文档
PDF961 KB
应用文档
PDF287 KB
应用文档
PDF630 KB
应用文档
PDF177 KB
应用文档
PDF19.79 MB
手册
PDF10.10 MB
手册
PDF530 KB
传单
PDF14.70 MB
General Reliability Literature
PDF171 KB
指南
PDF1.28 MB
手册 - 开发工具
PDF746 KB
手册 - 开发工具
PDF105 KB
手册 - 开发工具
ZIP6.02 MB
手册 - 硬件
PDF23.00 MB
手册 - 硬件
PDF737 KB
手册 - 软件
PDF510 KB
手册 - 软件
PDF2.02 MB
其他
PDF1.04 MB
其他
PDF1.42 MB
其他
PDF1.28 MB
其他
PDF1.33 MB
其他
PDF940 KB
其他
PDF864 KB
其他
PDF939 KB
其他
PDF448 KB
其他
PDF470 KB
其他
PDF15.93 MB
其他
PDF1.22 MB
快速入门指南
PDF269 KB
Release Note
PDF331 KB
相关文件:
Release Note
PDF356 KB
相关文件:
Release Note
PDF294 KB
Release Note
PDF3.10 MB
Technical Update
PDF1.29 MBEnglish, 日本語
白皮书

设计和开发

软件与工具

软件与工具

DRP-AI TVM (GitHub)We provide an AI model conversion tool (DRP-AI TVM) for DRP-AI-equipped products. When using this product, please check the contents of the linked README.md first. Software Package 瑞萨电子
DRP-AI Translator [V1.81]This is an AI model conversion tool (DRP-AI Translator) for DRP-AI equipped products. Please check the Release Notes and User's Manual first before using this product. Software Package 瑞萨电子
RZ/V2M DRP-AI Support Package [V7.30]This product provides the software and documentation for DRP-AI embedded within RZ/V2M. Software Package 瑞萨电子
RZ/V2M ISP Support Package [V.1.3.1]This product provides ISP Support Package for RZ/V2M. Please read the Release Note included in this first when you use the package. Software Package 瑞萨电子
RZ/V2M Linux Package [5.10-CIP] V1.3.0This product provides Linux Package for RZ/V2M 64bit processors. Please read the Release Note included in this first when you use the package. Software Package 瑞萨电子

软件下载

文档标题 类型 日期
ZIP1.52 MB
PCB设计文档
ZIP210 KB
软件和工具 - 其他
ZIP1.62 MB
软件和工具 - 其他
ZIP270.19 MB
软件和工具 - 软件
ZIP2,551.92 MB
相关文件:
软件和工具 - 软件
ZIP5.50 MB
相关文件:
软件和工具 - 软件
ZIP41.07 MB
软件和工具 - 软件
7Z2,271.63 MB
软件和工具 - 软件

开发板与套件

开发板与套件

模块

图像
Lab on the Cloud

云上的瑞萨实验室

云上的瑞萨实验室是一个在线环境,其中的瑞萨解决方案托管在客户能在线访问和测试的远程实验室中,包括常用的评测板、成功的产品组合和软件。

RZ/V2M SMARC: Object Detection Solution

AI-only Accelerator (DRP-AI), 4K-compatible Image Signal Processor (ISP), Vision-AI ASSP for real-time human and object recognition.