Advertisement

AI system-on-module simplifies embedded vision system design

Renesas’ scalable system-on-module SMARC board solution makes it easier to add AI IoT face/objection detection, imaging processing and 4K video playback.

Renesas Electronics Corp. has expanded its “Winning Combinations” portfolio with a new scalable artificial intelligence (AI) system-on-module (SoM) Smart Mobility ARChitecture (SMARC) board solution comprised of 10 Renesas ICs, including microprocessor (MPU), power, and analog ICs. This AI SMARC SoM Winning Combo board solution is designed to help engineers speed up the development of artificial intelligence (AI) IoT face/object detection, image processing, and 4K video playback applications in a range of applications. These include surveillance cameras, inspection equipment, and a range of industrial and building automation HMI and embedded vision systems.

The SoM winning combo board is based on the SMARC 2.0 industry standard, which specifies an 82 x 80-mm form factor. Communication interfaces such as USB, SATA, LVDS, HDMI, CSI, I2S, PCIe, and Gigabit Ethernet are accessible through the SMARC 2.0 connector. The board was designed by Renesas and developed through a collaboration with RelySys Technologies.

The SMARC SoM board offers designers a choice of three different versions of the Renesas 64-bit RZ/G2 MPU: a RZ/G2N dual core Arm Cortex-A57 MPU operating at 1.5 GHz for mid-range performance; the RZ/G2M MPU with dual-core Arm Cortex-A57 and quad-core Arm Cortex-A53 (1.2 GHz) for high performance, and the RZ/G2H MPU with quad-core Arm Cortex-A57 and quad-core Arm Cortex-A53 for ultra-high performance. All three MPUs (two cores up to eight cores) feature integrated 600 MHz PowerVR 3D graphics and a 4K UHD H.265 and H.264 codecs to meet the needs of different computer processing requirements.

Renesas system-on-module SMARC board

In addition, the SMARC 2.0 reference design offers several choices of on-board interfaces, large memory, and programmable clocks for different application needs. Designers can choose the RZ/G2 MPU with up to 35.6K DMIPS performance, plus 2 GB to 4 GB LPDDR4 RAM memory, and 32 GB eMMC.

Each RZ/G2 MPU is capable of running edge video analytics and AI frameworks, said Renesas. The MPUs feature an integrated AI software library, a comprehensive set of interfaces, error checking and correction (ECC) protection on both internal and external memories, Linux OS, and a Verified Linux Package (VLP) tested and maintained by Renesas.

The solutions also feature Civil Infrastructure Platform (CIP) Super Long-Term Support (SLTS) kernel, and a Linux kernel bundled with a software development environment. The SMARC SoM board also provides an optimized power and programmable timing tree to assist the RZ/G2 MPU with a wide variety of applications.

The Scalable AI SMARC SoM winning combo solution board and design files are available from Renesas’ worldwide sales and global distribution partners. It also can be purchased from RelySys Technologies.

Renesas also recently launched a 48-V Mobility winning combo solution reference design that helps developers speed up the design of electric mobility (e-mobility) applications, such as e-scooters, e-bikes, UPS, and energy storage systems.

Advertisement



Learn more about renesas

Leave a Reply