How to Optimize a Camera ISP with Atlas to Automatically Improve Computer Vision Accuracy


Date:  Thursday, May 27

Start Time: 1:00 pm

End Time: 1:30 pm

Computer vision (CV) works on images pre-processed by a camera’s image signal processor (ISP). For the ISP to provide subjectively “good” image quality (IQ), its parameters must be manually tuned by imaging experts over many months for each specific lens / sensor configuration. However, “good” visual IQ isn’t necessarily what’s best for specific CV algorithms. In this session, we will show how to use the Atlas workflow to automatically optimize an ISP to maximize computer vision accuracy. Easy to access and deploy, the workflow can improve CV results by up to 25 mAP points while reducing time and effort by more than 10x versus today’s subjective manual IQ tuning approaches.

Track

Session Speakers

  • Marc Courtemanche is an accomplished engineer with over 25 years of experience in the IT industry, including computer vision and mobile video companies. Prior to Algolux, from 2007-2017 he served as Product Architect at Vantrix. Marc is currently responsible for the development of the Atlas Camera Optimization Suite, the industry’s first set of machine learning tools and workflows that automatically optimizes camera architectures for computer vision. Atlas significantly improves computer vision results in days vs. traditional approaches that do not deliver optimal results even after many months of manual tuning. Marc earned his Ph.D. from the University of Arizona and concluded his postdoc research at the University of California, San Diego.


Share

How to Optimize a Camera ISP with Atlas to Automatically Improve Computer Vision Accuracy