Smart cameras employ deep learning for precise object recognition and low power consumption

Renesas Electronics Corporation and StradVision, Inc., a vision processing technology solutions provider for autonomous vehicles with expertise in deep learning, today announced the joint development of a deep learning-based object recognition solution for smart cameras used in next-generation advanced driver assistance system (ADAS) applications and cameras for ADAS Level 2 and above.

To avoid hazards in urban areas, next-generation ADAS implementations require high-precision object recognition capable of detecting so-called vulnerable road users (VRUs) such as pedestrians and cyclists. At the same time, for mass-market mid-tier to entry-level vehicles, these systems must consume very low power. The new solution from Renesas and StradVision achieves both and is designed to accelerate the widespread adoption of ADAS.

StradVision’s deep learning–based object recognition software delivers high performance in recognizing vehicles, pedestrians, and lane marking. This high-precision recognition software has been optimized for Renesas R-Car automotive system-on-chip (SoC) products R-Car V3H and R-Car V3M, which have an established track record in mass-produced vehicles. These R-Car devices incorporate a dedicated engine for deep learning processing called CNN-IP (Convolution Neural Network Intellectual Property), enabling them to run StradVision’s SVNet automotive deep learning network at high speed with minimal power consumption. The object recognition solution resulting from this collaboration realizes deep learning–based object recognition while maintaining low power consumption, making its use suitable in mass-produced vehicles, encouraging ADAS adoption.