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.

In recent years, the rapid development of autonomous driving and intelligent driver assistance has brought about urgent demands on high-precision road maps. However, traditional road map production methods mainly rely on professional survey technologies, such as remote sensing and mobile mapping, which suffer from high costs, object occlusions, and long updating cycles. In the era of ubiquitous mapping, crowdsourced trajectory data offer a new and low-cost data resource for the production and updating of high-precision road maps. Meanwhile, as key nodes in the transportation network, maintaining the currency and integrity of road intersection data is the primary task in enhancing map updates. In this paper, we propose a novel approach for detecting road intersections based on crowdsourced trajectory data by introducing an attention mechanism and modifying the loss function in the YOLOv5 model. The proposed method encompasses two key steps of training data preparation and improved YOLOv5s model construction. Multi-scale training processing is first adopted to prepare a rich and diverse sample dataset, including various kinds and different sizes of road intersections. Particularly to enhance the model’s detection performance, we inserted convolutional attention mechanism modules into the original YOLOv5 and integrated other alternative confidence loss functions and localization loss functions. The experimental results demonstrate that the improved YOLOv5 model achieves detection accuracy, precision, and recall rates as high as 97.46%, 99.57%, and 97.87%, respectively, outperforming other object detection models.