CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition
This work addresses the need for more robust traffic sign recognition systems for autonomous driving by providing a comprehensive dataset, though it is incremental as it builds on existing methods with new data.
The authors tackled the problem of limited and insufficiently challenging datasets for traffic sign recognition by creating the CURE-TSR dataset, which includes over two million images from real-world and simulator sources, and showed that challenging conditions significantly reduce baseline performance while data augmentation with simulator data improves average recognition in real-world scenarios.
In this paper, we investigate the robustness of traffic sign recognition algorithms under challenging conditions. Existing datasets are limited in terms of their size and challenging condition coverage, which motivated us to generate the Challenging Unreal and Real Environments for Traffic Sign Recognition (CURE-TSR) dataset. It includes more than two million traffic sign images that are based on real-world and simulator data. We benchmark the performance of existing solutions in real-world scenarios and analyze the performance variation with respect to challenging conditions. We show that challenging conditions can decrease the performance of baseline methods significantly, especially if these challenging conditions result in loss or misplacement of spatial information. We also investigate the effect of data augmentation and show that utilization of simulator data along with real-world data enhance the average recognition performance in real-world scenarios. The dataset is publicly available at https://ghassanalregib.com/cure-tsr/.