New Product Introduction

Renesas RZ/V2M MPU Group

RZ/V2M - AI-only Accelerator (DRP-AI), 4K-compatible Image Signal Processor (ISP), Vision-AI ASSP for Real-time Human and Object Recognition

RZ/V2M - front and back side of the chip

The AI dedicated 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.

 

Features

  • 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
  • Hardware Security Engine provided

 

Applications

  • Object detection (surveillance & traffic monitoring camera)
  • Classification (product scanner, POS terminal)
  • Face recognition (security door, door phone)
  • Visual Inspection (Factory Line)
  • Motion capture (sports analysis)
  • Detection support (medical camera)
  • Appliance with AI

 

Related Documents



Have a question? Contact us

Email:
For general questions:
yourmessage@avnet.eu

Local Avnet Silica offices:
Click here to find contact information for your local Avnet Silica team.