The new starter kit is based on the R-Car V3M on-chip image recognition system (SoC), which offers a combination of low power consumption and high performance for the growing NCAP front camera market. By combining the R-Car V3M starter kit with supporting software and tools, system developers can easily develop front camera applications, helping to reduce development effort and accelerate time to market.
 
Renesas has also announced an improvement to the R-Car V3M by integrating a new high-efficiency hardware accelerator for high-performance convolutional neural networks (CNN, Note 2This enables functions such as path detection and object classification, which are increasingly used in automotive applications. The R-Car V3M's innovative hardware accelerator allows the CNNs to operate at ultra-low power consumption levels that are unattainable when the CNNs run on a CPU or GPU.
 
The new R-Car V3M Starter Kit, the R-Car V3M SoC and supporting software and tools, including Renesas' e² open source IDE (e² studio) integrated development environment, are part of Renesas' open, innovative and reliable Renesas autonomy™ platform for ADAS and automated driving, offering total end-to-end solutions from the cloud to vehicle sensing and control.
 
The main features of the R-Car V3M Starter Kit
• The flexible board can be used for a wide range of computer applications
The new starter kit is a ready-to-use kit. In addition to the necessary interface and tools, the kit provides essential components for ADAS and automated driving development, including 2 GB of RAM, 4 GB of eMMC (embedded multimedia controller, Note 3), built-in memory, Ethernet, display outputs, and debugging interfaces. The integrated 440-pin expansion port gives system builders complete freedom to develop custom expansion boards for a wide range of computing applications, from a simple computer vision development environment to prototyping multi-camera systems for applications such as surround vision. This board flexibility reduces hardware development time while maintaining a high degree of software portability and reuse.
 
• Linux BSP quickstart solution and various tools
The R-Car V3M Starter Kit is compatible with the Linux Board Support Package (BSP), which is available through elinux.org.
Codeplay will enable OpenCL™ and SYCL™ in the starter kit in Q1 2018. More tools, sample code, and application notes for machine vision and image processing will be provided throughout 2018.
Renesas enables several tools in the R-Car V3M Starter Kit, including the Renesas e2 studio toolchain and debugging tools, which ease the development burden and allow for faster time to market.
The partners, including Cogent Embedded, which developed a 3D surround-view parking assistance system, are making their field-proven software solutions and development systems available using the R-Car V3M Starter Kit to accelerate development.
 
In addition to the R-Car V3M Starter Kit, Renesas has enabled ultra-low power consumption for CNNs, which perform image recognition and classification, in the R-Car V3M SoC. The R-Car V3M allows for the implementation of high-performance, low-power CNNs in NCAP cameras, something not possible with traditional, power-hungry CPU or GPU architectures. Renesas complements the IMP-X5, a computer vision processing subsystem consisting of an image processor and a programmable CV engine, with a new, innovative, in-house developed hardware CNN accelerator, enabling the implementation of high-performance CNNs at very low power. With this new IP, Renesas allows system developers to choose between the IMP-X5 or the new hardware accelerator for their CNN implementation. This heterogeneous approach allows system developers to select the most efficient architecture based on their required programming flexibility, performance, and power consumption.
 
 
Availability
The Renesas R-Car V3M is now available. The R-Car V3M Starter Kit with Linux BSP will be available in Q1 2018, initially in limited quantities. A full offering with an extended software solution is planned for Q3 2018.
 
Note 1)
New Car Assessment Program (NCAP): A developer car safety program to evaluate the performance of new car designs against various safety threats.
 
Note 2)
Convolutional neural networks (CNNs) are advanced artificial neural networks that have been successfully applied to analyze visual images and are increasingly used in the automotive sector for applications such as road detection or object classification.
 
Note 3)
The embedded memory of a multimedia controller (eMMC) allows the operating system to boot from the boot kit. This is much faster than booting over the network.

More information or a quote