Discussion of Novel Filters and Models for Color Space Conversion

In the era of artificial intelligence perceptual algorithms used in state-of-the-art Advanced Driver Assistance Systems (ADAS), algorithm validation is not an easy task. To ensure the highest possible safety level of the solution, the performance of the algorithm must be evaluated under a variety of challenging conditions. To test the algorithms, simulators are used to emulate the virtual environment around the car taking into account road traffic, infrastructure and vehicles dynamics. Sensor models are necessary for virtual testing to provide required data to ADAS algorithms. This article introduces the issue of modeling the color filter spaces that are used in the automotive industry. The images generated by the simulator usually have RGB color. In contrast, the automotive industry uses filters such as RCCC and RYYCy. In this paper, the methods for transforming color space from RGB to RYYCy are discussed. Three novel approaches are introduced to solve this problem: analytical, polynomial, and based on a neural network. Moreover, comparative discussion of the presented solutions is shown and with the set of experiments the conversion accuracy and execution time of each algorithm are compared. In addition, introduced solution were compared with modified models that are presented in the literature.