CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition

TL;DR

This paper introduces the CURE-TSR dataset, comprising over two million images from real and simulated environments, to evaluate and improve traffic sign recognition robustness under challenging conditions.

Contribution

The paper presents a large-scale, diverse dataset for traffic sign recognition, and benchmarks existing algorithms, highlighting the impact of challenging conditions and the benefits of data augmentation.

Findings

Challenging conditions significantly reduce recognition accuracy.

Simulator data combined with real data improves performance.

Loss of spatial information worsens recognition under challenging scenarios.

Abstract

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/.