Renesas and StradVision are developing a deep learning-based object recognition solution for smart cameras employed in next-generation advanced driver assistance system (ADAS) applications and cameras for ADAS Level 2 and above.
StradVision’s software detects vehicles, pedestrians, and lane marking and is enhanced for Renesas R-Car automotive system-on-chip (SoC) products R-Car V3H and R-Car V3M. These R-Car devices operate StradVision’s SVNet automotive deep learning network at an accelerated rate while consuming very little power.
The deep learning-based object recognition solution:
- Supports early evaluation to mass production
StradVision’s SVNet deep learning software for the R-Car V3H supports object recognition involving all the steps from training through the embedding of software for mass-produced vehicles.
- R-Car V3H and R-Car V3M SoCs enhance dependability for smart camera systems
The Renesas R-Car V3H and R-Car V3M include the IMP-X5 image recognition engine. Merging deep learning-based complex object recognition and image recognition processing enables designers to generate a sturdy system. The on-chip image signal processor (ISP) adapts sensor signals for image rendering and recognition processing.
Renesas R-Car SoCs will be available to developers in early 2020.
To learn more about the automotive industry, check out: