We address the automatic recognition of road safety attributes according to the iRAP methodology. We formulate the problem as a separate multi-class classification of each iRAP attribute in georeferenced video clips that correspond to particular road segments. We propose a solution based on an efficient multi-task model with shared features, which can recognize all attributes with a single forward pass and learn in an end-to-end fashion. We perform experiments on a novel real dataset acquired along 1850 km of public roads in Bosnia and Herzegovina, in which all iRAP attributes have been annotated by human experts. We express recognition accuracy as per-attribute macro-F1 scores due to a significant class imbalance present within most attributes. We thoroughly validate different variants of our model, analyze the contributions of several hyper-parameters, and report recognition accuracy on the independent test set.
Multi-Task Learning for iRAP Attribute Classification and Road Safety Assessment
20.09.2020
968413 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Dr. Saharjo Road Condition Audit Using IRAP Method to Achieve 3 Star Rating
Springer Verlag | 2022
|iRAP Road and Design Assessments and Outcomes: A Case Study From Moldova
DOAJ | 2017
|