Dynamic Adherent Raindrop Simulator for Automotive Vision Systems

Abstract

The automotive domain is highly regulated, with many safety-critical aspects to consider. This means that a great deal of testing is required to validate the performance of automotive systems, under all possible environmental conditions. For vision-based systems, camera images are among the most important input sources of information, and using high-quality images is integral to the system's performance. Rain, as a type of adverse weather condition, degrades the image quality which reflects negatively on the vision-based algorithms. Collecting representative sets of data under different rain conditions is required for system testing and performance evaluation. This usually is both costly and time-consuming. Augmenting the sets of real rained images in system testing is an attractive, feasible alternative. In this paper, we present an adherent rain simulator system, that adds simulated rain to clear image frames captured in real drive cycles. We test the quality of simulated rained images against real rained ones, using common image similarity metrics. We also compare the performance of deep learning-based object detectors, using our simulated rained images vs. real rained images. The results show that object detectors show similar performance using simulated and real rained images. A comparative analysis shows that our model produces more realistic raindrops, compared to a ray-tracing-based raindrop simulator.