Multistage traffic sign recognition under harsh environment

This paper examines the impact of rain on traffic sign recognition system, addressing one of the challenges posed by harsh environmental conditions like low lighting, extreme weather (rain,fog, snow) and reduced sign visibility. A novel system is proposed in this work, which is capable of handling three different rain types (drizzle, torrential, and heavy). This work explores how different rain types affect training and testing of three customized convolutional neural networks for traffic sign recognition. Results show that the system’s performance is dependent on the rain type during training and testing. To address this variability, a multistage classifier is proposed: level 1 classifies rain type, and level 2 selects an appropriate traffic sign classifier based on output of level1. This work also analyzes the effect of augmenting three different types of rain for developing noise robust traffic sign recognition system. Experiments were conducted using publicly available German Traffic Sign Recognition Benchmark dataset. The proposed system attains overall classification accuracy of 95.10% measured through the accuracy score metric, which has not been claimed till now in any previous work in addressing the challenges of recognizing traffic signs in presence of different types of rain.