StradVision has been working closely with Renesas on deep learning-based object recognition solutions for smart cameras used In ADAS since 2019
StradVision, whose AI-based camera perception software is a leading innovator in Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicles (AV), has been selected as a member of Renesas’ R-Car Consortium Proactive Partner Program for the second consecutive year. Satisfying the consortium’s criteria of “open”, “innovative”, and “trusted”, StradVision was verified as a high-performance company with a good track record in the automotive market, consequently enabling quick engagement with customers.
“Being selected as a member of the R-Car Consortium Proactive Partner Program is a fantastic opportunity to work even more closely with compatible vendors in the automotive industry, and it’s a very exciting prospect to be part of this platform to speed up the advancement of ADAS technology,” says StradVision CEO Junhwan Kim.
The R-Car Consortium is an open platform environment organized by Renesas, that enables customers to quickly identify and engage with ecosystem partners, whose solutions will help accelerate their innovation for the future mobility market, strengthening research and development for the connected car and ADAS.
StradVision has been working closely with Renesas since the announcement of their collaboration on developing a deep learning-based object recognition solution for smart cameras used in ADAS in September 2019.
“We regard StradVision’s SVNet software as one of the best deep learning and camera based ADAS perception solutions for Front Facing Camera (FFC) and Surround View Monitoring (SVM). It was only natural to turn to StradVision to be the first deep learning-based algorithm to be run on Renesas’ R-Car H3, R-Car V2H, R-Car V3M, and R-Car V3H SoCs,” says Naoki Yoshida, Vice President of Automotive Digital Products Marketing Division at Renesas. “Discussions are underway to supply Renesas SoCs powered by SVNet algorithms to customers around the world, and we look forward to our continuous partnership with StradVision.”
StradVision’s pioneering SVNet software allows for ADAS and autonomous vehicles to detect and identify objects accurately, such as other vehicles, lanes, pedestrians, animals, free space, traffic signs, and lights, even in harsh weather conditions or poor lighting.
To achieve surround vision, SVNet’s camera and deep learning-based capabilities work seamlessly with other sensors such as LiDAR and RADAR to process collected road data with high speed and accuracy.
SVNet’s software algorithm is customized for R-Car V3H and R-Car V3M, Renesas’ automotive SoCs optimized for stereo front cameras and surround view systems. These SoCs have an established track record in low power consumption and a high level of functional safety, and its Starter Kits are ready-to-use.
To tackle the high-power consumption constraints in entry- to mid-level vehicles, the combination of StradVision’s SVNet and Renesas SoCs enables both high performance and low power consumption.
Compared with competitors, SVNet is compact, requires dramatically less memory capacity to run, and consumes less electricity. It can also be customized for any hardware system thanks to StradVision’s patented and cutting-edge Deep Neural Network-enabled software.