Potentials of combined visible light and near infrared imaging for driving automation

Abstract

An extension of automotive imaging from the visible (VIS) to the near infrared (NIR) spectrum is promising for driving automation applications because the technology is readily available and offers potential benefits in low visibility conditions, in low light conditions with active illumination, and by collection of complementary data. We propose the evaluation of VIS-NIR imaging in simulation using an extended version of our camera simulation and optimization framework. Our extended framework generates realistic spectral irradiance data of synthetic scenes in the VIS and NIR spectral range and includes physically based camera models with characteristic increased NIR sensitivity of VIS-NIR CMOS imagers, modified automotive VIS-NIR color filter arrays and adapted image processing. We evaluate the reproduction of potential benefits of VIS-NIR imaging in our simulated camera images using exemplary night time and daylight traffic scenes, and discuss further extensions for creation of a well-balanced VIS-NIR dataset for quantitative evaluation.