Impact of reduced visibility from fog on traffic sign detection

Abstract

In camera-based Advance Driver Assistance System (ADAS) such as traffic sign recognition, some failure may be inferred by adverse meteorological conditions, in particular under foggy weather. This paper investigates the effects of reduced visibility from fog in an ADAS operating range, more specifically a traffic sign detection algorithm. For this purpose, we produced a database of synthetic images containing road signs with and without fog, that is intended to be shared with the scientific community. The database enables a study of the effects of reduced visibility from fog on a gradient-based geometrical model of traffic signs. After analysing the tolerance of the algorithm to additive noise and blurring, its performance is measured under increasing level of fog. Its operating range is measured with regard to the fog density: we discuss the way the distance required to detect a sign increases with the meteorological visibility distance and its impact on safety.