CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition
arXiv:1712.02463
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/.
31st Conference on Neural Information Processing Systems (NIPS), Machine Learning for Intelligent Transportation Systems Workshop, Long Beach, CA, USA, 2017
Cited by in corpus (5)
- Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics
- Traffic Signs in the Wild: Highlights from the IEEE Video and Image Processing Cup 2017 Student Competition [SP Competitions]
- Probing the Purview of Neural Networks via Gradient Analysis
- Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data
- Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts