Wenesday 1st of June : Presentation this morning by Gérard YAHIAOUI President & CEO of NEXYAD, France

« BUILDING A RELEVANT VALIDATION DATABASE FOR CAMERA-BASED ADAS »
Validation of camera-based artificial vision systems applied on open world is a very complex issue. An HD colour camera may generate more than 65 000 power 2 000 000 different images (information theory), so it is not possible to test every possible message. We propose a deterministic approach for building a validation database using the AGENDA methodology that was developed and published in the 1990s for neural network database (learn & test) design.

A large audience attended to this conference that questions the way for Autonomous Vehicle ADAS validation.

Gérard on the left, the conference’s audience on the top and the booth of Groupement ADAS from the mezzanine.