Abstract
With the rapid development of urban traffic, accurate and up-to-date road maps are in crucial demand for daily human life and urban traffic control. Recently, with the emergence of crowdsourced mapping, a surge in academic attention has been paid to generating road networks from spatio-temporal trajectory data. However, most existing methods do not explore changing road patterns contained in multi-temporal trajectory data and it is still difficult to satisfy the precision and efficiency demands of road information extraction. Hence, in this paper, we propose a hybrid method to incrementally extract urban road networks from spatio-temporal trajectory data. First, raw trajectory data were partitioned into K time slices and were used to initialize K-temporal road networks by a mathematical morphology method. Then, the K-temporal road networks were adjusted according to a gravitation force model so as to amend their geometric inconsistencies. Finally, road networks were geometrically delineated using the k-segment fitting algorithm, and the associated road attributes (e.g., road width and driving rule) were inferred. Several case studies were examined to demonstrate that our method can effectively improve the efficiency and precision of road extraction and can make a significant attempt to mine the incremental change patterns in road networks from spatio-temporal trajectory data to help with road map renewal.
Highlights
With the ongoing rapid urbanization, road networks have become increasingly complicated and heavily dense
Since existing research has often ignored the potential road change patterns implied in different time-series trajectories, in this paper, we proposed a hybrid method to incrementally extract urban road networks from spatio-temporal trajectory data
The final geometry delineation and associated road attributes were constructed by k-segment fitting and statistical analysis, respectively
Summary
With the ongoing rapid urbanization, road networks have become increasingly complicated and heavily dense. Generating timely, detailed, and accurate road maps is the foundational demand of intelligent transportation systems and smart city management. Traditional road data acquisition methods, such as map digitization and field surveys, require expensive equipment and labor-intensive indoor processing. Some collaborative mapping programs (e.g., OpenStreetMap, Wikimapia) have made a significant contribution to commercial road maps, but they depend on the manual processing work of volunteers and are confronted with submissions of varying quality [1]. Used positioning devices (e.g., mobile phones) make it possible to create massive trajectory data for vehicles and people, which contain an abundance of information on road structures, traffic conditions, and driving behaviours. A surge in academic attention has, in recent years, been paid to automatically extracting road-related information from spatio-temporal trajectory data [2,3,4]
Sign-in/Register to view highlights & summary 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.
