Hierarchical Segmentation Method for Generating Road Intersections from Crowdsourced Trajectory Data

Abstract

Maintaining the data freshness and completeness of road intersection information is the key task of urban road map production and updating. Compared to professional surveying methods, crowdsourced trajectory data provide a low-cost, wide-coverage and real-time data resource for road map construction. However, there may exist the problems of spatio-temporal heterogeneity and uneven density distribution in crowdsourced trajectory data. Hence, in light of road hierarchies, the paper proposes a hierarchical segmentation method to generate road intersections from crowdsourced trajectories. The proposed method firstly implements an adaptive density homogenization processing on raw trajectory data in order to decrease the uneven density discrepancy. Then, a hierarchical segmentation strategy is developed to extract multi-level road intersection elements from coarse scale to fine scale. Finally, the structural models of road intersections are delineated by an iterative piecewise fitting method. Experimental results show that the proposed method can accurately and completely extract road intersections of different shapes and scales, with an accuracy of about 87–90%. Particularly, the precision and recall of road intersection detection are obviously increased by about 7% and 20% by adaptive density homogenization, indicating the advantages of dealing with uneven trajectory data.