Abstract
Automatically acquiring comprehensive, accurate, and real-time mapping information and translating this information into digital maps are challenging problems. Traditional methods are time consuming and costly because they require expensive field surveying and labor-intensive post-processing. Recently, the ubiquitous use of positioning technology in vehicles and other devices has produced massive amounts of trajectory data, which provide new opportunities for digital map production and updating. This paper presents an automatic method for producing road networks from raw vehicle global positioning system (GPS) trajectory data. First, raw GPS positioning data are processed to remove noise using a newly proposed algorithm employing flexible spatial, temporal, and logical constraint rules. Then, a new road network construction algorithm is used to incrementally merge trajectories into a directed graph representing a digital map. Furthermore, the average road traffic volume and speed are calculated and assigned to corresponding road segments. To evaluate the performance of the method, an experiment was conducted using 5.76 million trajectory data points from 200 taxis. The result was qualitatively compared with OpenStreetMap and quantitatively compared with two existing methods based on the F-score. The findings show that our method can automatically generate a road network representing a digital map.
Highlights
In the era of big data, people have increasing demands for comprehensive, accurate, and real-time navigational information, and the road network is the most important
The experimental global positioning system (GPS) trajectory data came from 200 taxis that had been equipped with GPS devices for approximately one month of daily travel in Beijing
Accurate digital road maps are of great importance for efficient travel
Summary
In the era of big data, people have increasing demands for comprehensive, accurate, and real-time navigational information, and the road network is the most important. Because the traditional acquiring and updating method of digital maps takes a great deal of human and material resources and the update cycle is long, changes are often not updated in a timely manner. For large cities such as Beijing and Shanghai, more than 40% of the map content should be updated every year; the traditional mapping method requires at least six months to update a map. We chose OpenStreetMap as our ground-truth map, which expresses freeways and arterial roads in detail and can be downloaded freely
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
