Abstract
This paper proposes a method to infer road networks from GPS traces. These networks include intersections between roads, the connectivity between the intersections and the possible traffic directions between directly-connected intersections. These intersections are localized by detecting and clustering turning points, which are locations where the moving direction changes on GPS traces. We infer the structure of road networks by segmenting all of the GPS traces to identify these intersections. We can then form both a connectivity matrix of the intersections and a small representative GPS track for each road segment. The road segment between each pair of directly-connected intersections is represented using a series of geographical locations, which are averaged from all of the tracks on this road segment by aligning them using the dynamic time warping (DTW) algorithm. Our contribution is two-fold. First, we detect potential intersections by clustering the turning points on the GPS traces. Second, we infer the geometry of the road segments between intersections by aligning GPS tracks point by point using a “stretch and then compress” strategy based on the DTW algorithm. This approach not only allows road estimation by averaging the aligned tracks, but also a deeper statistical analysis based on the individual track’s time alignment, for example the variance of speed along a road segment.
Highlights
Automatic road map inference is an important tool in the field of intelligent transportation systems (ITS): it allows unexplored geographic regions to be mapped quickly [1,2,3,4]; it can update the existing maps [5,6]; and it provides information on the density of traffic [7], which can be used in navigation [8] and for urban planning [9,10]
Edges from each raw Global Positioning System (GPS) trace are added to the graph, unless an edge with a similar location and bearing already exists in the graph under construction
We have presented a novel approach to infer a road network by extracting intersections, inferring their topology and segmenting road segments between intersections using GPS traces
Summary
Road maps were previously constructed through labor-intensive geographic surveying using telescopes, sextants and other devices. Today, these methods have been replaced by mobile mapping vehicles, which can map whole cities with high accuracy [11]. As the hand-held GPS devices have become increasingly popular in the last decade, geographical data are more obtainable from cars, taxis and trucks, and from cyclists and pedestrians. This abundance of GPS-derived geospatial data has stimulated the development of both crowd-sourced mapping projects [14,15], as well as commercial products. The research on GPS tracking analysis has focused on building road maps [16]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call