Renesas Electronics has unveiled a new R-Car V3H system-on-chip (SoC) for front cameras to be used in vehicles with Level 3 or 4 autonomy. The SoC is designed to offer high computer vision performance and AI processing, at low power levels.
The SoC is optimised for use in stereo front cameras and achieves five times the computer vision performance of its predecessor, the R-Car V3M SoC, targeting NCAP front cameras, announced in April 2017.
Part of the open Renesas autonomy platform, Renesas Electronics says the R-Car V3H enables design flexibility, so Tier 1s and OEMs can map their own road from assisted- to highly automated vehicles.
The R-Car V3H SoC focuses on architecture optimisation for computer vision processing, enabling all relevant ADAS functions from conditional to highly automated driving. Leveraging Renesas’s concept of heterogeneous computer vision cores based on the IMP-X5+ image recognition engine and dedicated hardware accelerators, the R-Car V3H is designed to achieve advanced sensing capabilities with algorithms including dense optical flow, dense stereo disparity and object classification.
The integrated IP for CNN accelerates deep learning at power levels of 0.3W, achieving more than twice the deep neural network performance of the R-Car V3M.
Relying on IPs already used in the R-Car V3M, the R-Car V3H includes a dual image signal processor (ISP) that converts camera sensor signals for image creation and recognition processing. The re-use ensures scalability from NCAP systems using R-Car V3M to Level 3 and 4 smart camera systems – using R-Car V3H – to reduce development time and costs by avoiding the need for ISPs in each camera. For further cost savings, the R-Car V3H requires only a single LPDDR4 memory.
Tier 1s and OEMs have the choice to develop a front camera solution by themselves or work with partners from the Renesas autonomy ecosystem, which is supported by front camera partners including Hella Aglaia.
Samples of the R-Car V3H SoC will be available from the fourth quarter of 2018, with mass production scheduled to begin in the third quarter of 2019.
March 6, 2018