Data-Driven Headlight Flare Model for Automotive Cameras

Automotive cameras are cost effective among perception sensors and have been widely deployed on cars, however the measurements generated by cameras can be affected by various noise factors. Flare, also known as straylight, is a common noise factor especially during night. Automotive headlights can be dazzling for human drivers and might be also challenging for Assisted and Automated Driving (AAD) functions. To enable higher levels of driving automation, investigating and testing this noise factor can be key to achieve AAD in challenging lighting conditions. Therefore, accurate automotive camera flare models need to be thoroughly investigated and developed. However, current camera datasets lack accuracy in representing state-of-the-art automotive cameras. This paper develops, describes, and validates an automotive specific parametrised method for modelling flare induced by automotive headlights. The presented model is validated with real-data and can be fine tuned to fit different types of automotive cameras and headlights. Additionally, this paper introduces a method to seamlessly integrate the modelling results into images generated by simulation platforms, such as CARLA and IPG CarMaker. Using the newly proposed model, automotive datasets with and without the realistic headlight flare can be generated. Overall, the integration of modelled flare provides a framework for accelerating the simulation and testing of assisted and automated driving functions.