2021/09/06 by Alexander Maletzky, Maletzky, Alexander, Stefan Thumfart +3
Computer Science · Engineering · Health Professions · Mathematics · Psychology · #Archaeology #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #History #Machine Learning (cs.LG) #Mathematics #Occupational Health and Safety Research #Pictogram #Programming language #Readability #Safety Warnings and Signage #Sign (mathematics) #Traffic and Road Safety #Traffic sign #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2109.02362
published in arXiv (Cornell University) (Cornell University)
arxiv created 2021/09/06 · openalex publication_date 2021/09/06 · arxiv updated 2021/09/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We compare the machine readability of pictograms found on Austrian and German traffic signs. To that end, we train classification models on synthetic data sets and evaluate their classification accuracy in a controlled setting. In particular, we focus on differences between currently deployed pictograms in the two countries, and a set of new pictograms designed to increase human readability. Besides other results, we find that machine-learning models generalize poorly to data sets with pictogram designs they have not been trained on. We conclude that manufacturers of advanced driver-assistance systems (ADAS) must take special care to properly address small visual differences between current and newly designed traffic sign pictograms, as well as between pictograms from different countries.