Renesas R-Car V3H drives automotive front cameras for level 3/4 autonomous vehicles

April 26, 2018 Brandon Lewis

TOKYO. Renesas Electronics Corporation has released the R-Car V3H system-on-chip (SoC), which targets computer vision (CV) and artificial intelligence (AI) processing applications in Level 3 and Level 4 autonomous vehicles. Based on the IMP-X5+ image recognition engine and optimized for use in stereo front cameras, the R-Car V3H delivers 5x the CV performance of its predecessor at only 0.3 W.

The R-Car VH3 SoC is equipped with a dual image signal processor (ISP), and includes image recognition algorithms such as Dense Optical Flow, Dense Stereo Disparity, and Object Classification. In addition, the SoC contains an integrated IP block for convolutional neural networks (CNNs) to accelerate deep learning workloads. By reusing IP also present in the R-Car V3M, automakers can scale NCAP-compliant systems with minimal effort.

Only a single LPDDR4 memory is required by the device.

"The R-Car V3H specification and design was done by cooperating closely with front camera market leaders to ensure we addressed the requirements of those leading innovations on autonomous driving systems,” says Jean-Francois Chouteau, Vice President, Renesas Electronics Corporation. “Besides featuring state-of-the-art computer vision performance at a very competitive system cost, what our customers like above all with R-Car-V3H is being able to keep the freedom to implement a front camera with their own differentiators and still benefit from scalable solutions between R-Car V3M and R-Car V3H.”

Samples of the R-Car V3H will be available in Q4 2018, with mass production scheduled for Q3 2019. More information can be found at

About the Author

Brandon Lewis

Brandon Lewis, Editor-in-Chief of Embedded Computing Design, is responsible for guiding the property's content strategy, editorial direction, and engineering community engagement, which includes IoT Design, Automotive Embedded Systems, the Power Page, Industrial AI & Machine Learning, and other publications. As an experienced technical journalist, editor, and reporter with an aptitude for identifying key technologies, products, and market trends in the embedded technology sector, he enjoys covering topics that range from development kits and tools to cyber security and technology business models. Brandon received a BA in English Literature from Arizona State University, where he graduated cum laude. He can be reached by email at

Follow on Twitter Follow on Linkedin Visit Website More Content by Brandon Lewis
Previous Article
Ampere LiDAR development board can deliver 5 ns pulses using eGaN technology

The development board is primarily intended to drive laser diodes and features an EPC2001C ground-reference...

Next Article
MVTec brings deep learning to NVIDIA Pascal architecture

The deep learning inference in the new version 17.12 of the HALCON machine vision software was tested on NV...