Automatic Extrapolation of Missing Road Network Data in OpenStreetMap
نویسندگان
چکیده
Road network data from OpenStreetMap (OSM) is the basis of various real-world applications such as fleet management or traffic flow estimation, and has become a standard dataset for research on route planning and related subjects. The quality of such applications and conclusiveness of research crucially relies on correctness and completeness of the underlying road network data. We introduce methods for automatic detection of gaps in the road network and extrapolation of missing street names by learning topological and semantic characteristics of road networks. Our experiments show that with the help of the learned data, the quality of the OSM road network data can indeed be improved.
منابع مشابه
An Automatic Road Network Construction Method Using Massive GPS Trajectory Data
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 massi...
متن کاملRoad Network Fusion for Incremental Map Updates
In the recent years a number of novel, automatic map-inference techniques have been proposed, which derive road-network from a cohort of GPS traces collected by a fleet of vehicles. In spite of considerable attention, these maps are imperfect in many ways: they create an abundance of spurious connections, have poor coverage, and are visually confusing. Hence, commercial and crowd-sourced mappin...
متن کاملRoad Network Fusion for Incremental Map Updates
In the recent years a number of novel, automatic map-inference techniques have been proposed, which derive road-network from a cohort of GPS traces collected by a fleet of vehicles. In spite of considerable attention, these maps are imperfect in many ways: they create an abundance of spurious connections, have poor coverage, and are visually confusing. Hence, commercial and crowd-sourced mappin...
متن کاملRoad Detection and Semantic Segmentation without Strong Human Supervision
Recently, convolutional neural networks (CNNs) trained with strong human supervision have shown to achieve state of the art performance for both road detection and semantic segmentation. However, collecting strongly labeled data for both require detailed per-pixel annotations from humans which renders data annotation highly costly and time consuming. Therefore, in this work we propose methods t...
متن کاملAutomatic Update of Road Attributes by Mining GPS Tracks
Despite advancements in cartography, mapping is still a costly process which involves a substantial amount ofmanual work. This paper presents amethod to automatically derive road attributes by analyzing and mining movement trajectories (e.g. GPS tracks). We have investigated the automatic extraction of eight road attributes: directionality, speed limit, number of lanes, access, average speed, c...
متن کامل