Abstract
OpenStreetMap (OSM) is a valuable source of geographical data where any volunteer user can participate. The contributing users have different mapping experience and motives and also use different mapping gadgets to collect data. As a result many discrepancies may found in OSM data. Many efforts have been made by research community to evaluate the OSM data quality by comparing it with other proprietary datasets. These methods are not suitable in absence of reference datasets. So in this paper, a machine learning based solution is provided. It uses intrinsic parameters like road length, attributes of OSM objects to train machine learning model to improve the quality of OSM data. The trained model is applied over Patiala, India dataset to detect and rectify the errors like missing or incorrect attributes of nodes and ways. The results of the study shows that without using any external dataset for comparison, this proposed methodology shows a desirable results for enhancing OSM data quality.
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.
