Enrichment of OpenStreetMap Data Completeness with Sidewalk Geometries Using Data Mining Techniques

Nowadays, several research projects show interest in employing volunteered geographic information (VGI) to improve their systems through using up-to-date and detailed data. The European project CAP4Access is one of the successful examples of such international-wide research projects that aims to improve the accessibility of people with restricted mobility using crowdsourced data. In this project, OpenStreetMap (OSM) is used to extend OpenRouteService, a well-known routing platform. However, a basic challenge that this project tackled was the incompleteness of OSM data with regards to certain information that is required for wheelchair accessibility (e.g. sidewalk information, kerb data, etc.). In this article, we present the results of initial assessment of sidewalk data in OSM at the beginning of the project as well as our approach in awareness raising and using tools for tagging accessibility data into OSM database for enriching the sidewalk data completeness. Several experiments have been carried out in different European cities, and discussion on the results of the experiments as well as the lessons learned are provided. The lessons learned provide recommendations that help in organizing better mapping party events in the future. We conclude by reporting on how and to what extent the OSM sidewalk data completeness in these study areas have benefited from the mapping parties by the end of the project. ARTICLE HISTORY

show abstract

“…and data mining techniques(Mobasheri et al 2018) for The proposed system architecture for data completeness checking.…”

mentioning

confidence: 99%

OpenStreetMap data quality enrichment through awareness raising and collective action tools—experiences from a European project

Mobasheri

Zipf

Francis³

2018

Geo-spatial Information Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In these situations, GIS and terrain data are not sufficient to build high-fidelity models. As a result, other data including the LIDAR data, GPS data and crowdsourcing data should be integrated for accurate modeling [32][33][34][35][36]. The modeling effects and efficiency can be further improved.…”

Section: Discussionmentioning

confidence: 99%

Template-Based 3D Road Modeling for Generating Large-Scale Virtual Road Network Environment

Zhang

Zhong

Liu

et al. 2019

IJGI

View full text Add to dashboard Cite

The 3D road network scene helps to simulate the distribution of road infrastructure and the corresponding traffic conditions. However, the existing road modeling methods have limitations such as inflexibility in different types of road construction, inferior quality in visual effects and poor efficiency for large-scale model rendering. To tackle these challenges, a template-based 3D road modeling method is proposed in this paper. In this method, the road GIS data is first pre-processed before modeling. The road centerlines are analyzed to extract topology information and resampled to improve path accuracy and match the terrain. Meanwhile, the road network is segmented and organized using a hierarchical block data structure. Road elements, including roadbeds, road facilities and moving vehicles are then designed based on templates. These templates define the geometric and semantic information of elements along both the cross-section and road centerline. Finally, the road network scene is built by the construction algorithms, where roads, at-grade intersections, grade separated areas and moving vehicles are modeled and simulated separately. The proposed method is tested by generating large-scale virtual road network scenes in the World Wind, an open source software package. The experimental results demonstrate that the method is flexible and can be used to develop different types of road models and efficiently simulate large-scale road network environments.

show abstract

“…OSM is a crowdsourced data and data quality is a major concern [30]. However, lots of research is in progress in this area and should be considered for future work [31,32].…”

Section: Discussionmentioning

confidence: 99%

Distributed Context Tree Weighting (CTW) for route prediction

Tiwari

Arya

2018

Open geospatial data, softw. stand.

View full text Add to dashboard Cite

Route prediction play a vital role in many important location-based applications like resource prediction in grid computing, traffic congestion estimation, vehicular ad-hoc networks, travel recommendation etc. The goal of this work is to design scalable route prediction application based on Context Tree Weighting (CTW) modeling of user travel data. CTW is one of the widely used technique for text compression as well string sequence indexing and for prediction. CTW tree construction from the huge volume of data by sequential processing is time-consuming in practical implementation. Existing techniques are designed for single machine and their implementation on the distributed environment is still a challenge. This work focuses on achieving horizontal scalability of CTW and addresses various challenges in distributed construction like reducing I/O, parallel computation of sequences and coming up with final CTW tree in a distributed environment efficiently. Map Reduce framework running over Hadoop file system is used for processing in distributed mode. Large GPS data set is map-matched to digitized road network obtained from Open Street Map and CTW model is built. A two-step construction of CTW tree is proposed which is implemented in the map-reduce framework. Horizontally scalable CTW model is built and evaluated for route prediction from a huge corpus of historical GPS traces.

show abstract

Enrichment of OpenStreetMap Data Completeness with Sidewalk Geometries Using Data Mining Techniques

Cited by 41 publications

References 45 publications

OpenStreetMap data quality enrichment through awareness raising and collective action tools—experiences from a European project

OpenStreetMap data quality enrichment through awareness raising and collective action tools—experiences from a European project

Template-Based 3D Road Modeling for Generating Large-Scale Virtual Road Network Environment

Distributed Context Tree Weighting (CTW) for route prediction

Contact Info

Product

Resources

About