Automatically maximize computer vision results by R-Car Series's ISP optimization in the cloud.

  • Optimize any camera to improve vision accuracy by up to 25 mAP
  • Accelerate schedules vs. manual ISP tuning from months to only days
  • Scalable secure metric-driven methodology for any camera or vision task
  • Automate Renesas R-Car ISP tuning to better leverage limited resources

Cameras are the sensor of choice for system developers of safety-critical applications. However, camera development currently relies on expert imaging teams to manually tune camera architectures.

This painstaking approach is expensive, can take many months, requires hard-to-find expertise, and depends on visual subjectivity. As such, this process does not ensure that the camera provides the optimal output for computer vision algorithms.

The Atlas Camera Optimization Suite is the industry’s first set of machine-learning tools and workflows that automatically optimizes camera architectures to improve computer vision results by up to 25 mAP points.

Atlas significantly improves computer vision results in days vs. traditional approaches that do not deliver optimal results even after many months of manual tuning. In turn, vision system teams can better scale their limited resources, reduce costs, and shrink development time – a game-changer for developers of vision systems.

The Atlas tools chain is available on the R-Car V series and has been optimized to take into account the specific features of Renesas tailored ISP for Human Vision and Machine Vision.


  • Multi-Objective Optimizer: Novel machine learning technology optimizes camera parameters to improve CV by 25 mAP
  • Automated Workflow: Leverage limited resources to optimize you vision system in days vs. manual ISP tuning approaches
  • Secure Infrastructure: Cloud server / client architecture ensures high performance and no exposure of proprietary data
  • Advanced Analysis: CV and IQ KPI analysis, pareto front evaluation, and customizable reporting
  • Optimized for R-Car V series for ADAS and AD Applications


Target Devices


Type Title Date
Product Brief Log in to Download PDF 812 KB
1 item