This paper presents the use of genetic algorithms (GAs) for optimising different global positioning system-based procedures for horizontal roadway alignment extraction. Two algorithms are proposed – one uses design information to guide the GA, aiming to evaluate the segmentation procedures' precision, while the other uses curve-similarity measures. The linear matching model, the discrete Fréchet distance and the modified Hausdorff distance were tested for guiding the optimisation algorithm in cases when there is no design information available. This paper also presents an extension to a segmentation method available in the literature for increasing the optimisation performance. The proposed algorithms were evaluated on a synthetic data set with 2100 curves. In the experiments, both algorithms correctly identified all the curves, with the best segmentation precision achieved by the algorithm with design information, closely followed by the curve-similarity metrics. Compared with manual segmentation, all showed good results.

No abstract

Road geometric design data are a vital input for diverse transportation studies. This information is usually obtained from the road design project. However, these are not always available and the as-built course of the road may diverge considerably from its projected one, rendering subsequent studies inaccurate or impossible. Moreover, the systematic acquisition of this data for the entire road network of a country or even a state represents a very challenging and laborious task. This study's goal was the extraction of geometric design data for the paved segments of the Brazilian federal highway network, containing more than 47,000 km of highways. It presents the details of the method's adoption process, the particularities of its application to the dataset and the obtained geometric design information. Additionally, it provides a first overview of the Brazilian federal highway network composition (curves and tangents) and geometry.

No abstract