Road network inference through multiple track alignment. (November 2016)

• Record Type: Journal Article
• Authors: Xie, Xingzhe; Wong, Kevin Bing-Yung; Aghajan, Hamid; Veelaert, Peter; Philips, Wilfried
• Is Part Of: Transportation research. Volume 72(2016)
• Page Start: 93
• Page End: 108
• Publication Date: 2016-11
• Subjects: Road map -- Trajectory alignment -- Trajectory similarity -- Trajectory clustering -- GPS traces; Transportation -- Periodicals; Transportation -- Technological innovations -- Periodicals; 388.011
• DOI: 10.1016/j.trc.2016.09.010
• Languages: English
• ISSNs: 0968-090X

Abstract

Highlights: Generated the road network through intersection detection and track alignment. Proposed a new method to align multiple tracks. Reduced computational cost by an iterative procedure of successor classification. Calculated each road segment using multiple track alignment. Analyzed the velocity variation along each road segment. Abstract: Road networks are a critical aspect of both path optimization and route planning. This paper proposes to generate the road network automatically from GPS traces through jointly aligning tracks for each road segment. First, intersections are clustered from turning points where the road users' moving directions change. GPS traces are partitioned into small tracks for individual road segments by directly-connected intersections. The tracks for each road segment are aligned using a greedy method based on successor classification. A "forward-track" procedure is proposed to locate a warp path through jointly traversing all tracks in a way which keeps the points associated by the path element spatially close to each other. This involves an iterative procedure to cluster successor points on the tracks. The warp path produced during the alignment is used to average the tracks as the geometric representation of the road segment, and to analyze the velocity variation along the road segment. Experimental results show our method outperforms other existing methods in producing no spurious road edges and more accurate geometric road representation.