Road Network Extraction from Low-Frequency Trajectories Based on a Road Structure-Aware Filter

Abstract

Many studies have utilized global navigation satellite system (such as global positioning system (GPS)) trajectories in order to successfully infer road networks because such data can reveal the geometry and development of a road network, can be obtained in a timely manner, and updated on a low budget. Unfortunately, existing studies for inferring road networks from vehicle traces suffer from low accuracy, especially in dense urban regions and locations with complex structures, such as roundabouts, overpasses, and complex intersections. This study presents a novel two-stage approach for inferring road networks from trajectory points and capturing road geometry with better accuracy. First, a lane structure-aware filter is proposed to cluster vehicle trajectories influenced by high noise and outliers in order to reveal the continuous structure points of lane curves from massive trajectory points. Second, a road tracing operator is utilized to segment the road network geometry by inserting new vertices and segments to a vigorous vertex in the heading of the structure points that are extracted in the first step. Experimental results demonstrate the increased accuracy of the extracted roads and show that the proposed method exhibits strong robustness to noise and various sampling rates.

Driving Behavior Analysis of City Buses Based on Real-Time GNSS Traces and Road Information

“…Road networks can be generated by digitization maps, mobile survey vehicles, or aerial photographs and GNSS trajectories [44]. Lane-based road networks are essential for bus route planning, such as lane locations and lane changes.…”

A Hybrid Method to Incrementally Extract Road Networks Using Spatio-Temporal Trajectory Data

“…The incremental methods make a good attempt at continuously updating road networks, but it is fairly time consuming to process the whole long-term observed trajectories [35]. Hence, some researchers proposed combined methods to generate structural graph models of road networks, such as the divide-and-conquer method [36,37], the structure learning method [38], the topological Morse theory [39], and the structure-aware filtering method [40].…”

Estimating Road Segments Using Natural Point Correspondences of GPS Trajectories

“…It is not trivial to integrate the usage of the spatial information from trajectory points and their order within the trajectory. This fact leads to approaches that ignore the order of points in the trajectory [7], use available topology information [8,9], or apply regression [10]. The Medoid approach [11] focuses on the selection of one of the input trajectories without combining the information from several trajectories.…”