Comparing the Machine Readability of Traffic Sign Pictograms in Austria and Germany
This addresses a practical problem for manufacturers of advanced driver-assistance systems (ADAS) regarding visual differences in traffic signs, but it is incremental as it builds on existing classification methods.
The study compared machine readability of traffic sign pictograms in Austria and Germany, finding that machine-learning models generalize poorly to unseen pictogram designs, with classification accuracy dropping significantly in cross-country evaluations.
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.