Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 2014
DOI: 10.1145/2666310.2666476
|View full text |Cite
|
Sign up to set email alerts
|

Automated highway tag assessment of OpenStreetMap road networks

Abstract: OpenStreetMap (OSM) has been demonstrated to be a valuable source of spatial data in the context of many applications. However concerns still exist regarding the quality of such data and this has limited the proliferation of its use. Consequently much research has been invested in the development of methods for assessing and/or improving the quality of OSM data. However most of these methods require ground-truth data, which, in many cases, may not be available. In this paper we present a novel solution for OSM… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
30
0

Year Published

2015
2015
2021
2021

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 41 publications
(30 citation statements)
references
References 8 publications
0
30
0
Order By: Relevance
“…Corcoran and Mooney () have described a method to assess the topological properties of OSM data. Jilani, Corcoran, and Bertolotto () have presented a multi‐granular representation of street networks. They said that it can be used to assess data quality based on geometrical and morphological characteristics.…”
Section: Related Workmentioning
confidence: 99%
“…Corcoran and Mooney () have described a method to assess the topological properties of OSM data. Jilani, Corcoran, and Bertolotto () have presented a multi‐granular representation of street networks. They said that it can be used to assess data quality based on geometrical and morphological characteristics.…”
Section: Related Workmentioning
confidence: 99%
“…Ali and Schmid () designed a classifier that learns the correct class of existing entities (i.e., parks and gardens) on the basis of their characteristics (e.g., size) and used it to predict the correct class of a new entity. Similarly, Jilani and Corcoran () extracted geometrical and topological properties of OSM street network data that are representative of their semantic class, to infer the “road class” from the new data. Finally, Mohammadi and Malek () estimated the positional accuracy of OSM data without corresponding reference data by extracting patterns from OSM data that have corresponding reference data.…”
Section: Taxonomy Of Quality Assessment Methodsmentioning
confidence: 99%
“…This structure combines the primal (where nodes are road intersections) and dual representations (where nodes are fragments of roads) of road networks. This multigranular representation is used in [6] to extract features and train a Random Forest classifier that is able to classify streets to 21 different street categories in OSM. The method uses Bag of Words computed over geometrical and topological features of the analyzed streets and their neighbors.…”
Section: Extracting Roads From Aerial Imagesmentioning
confidence: 99%
“…In [72], the authors propose a CNN-based method to detect buildings in aerial imagery using an iterative process, in which new samples are selected for annotation by an active learning method and the model is retrained. In [73] the authors use multiple sources of crowdsourced geographical data (namely OSM, MapSwipe 6 , and OsmAnd 7 ) and an active learning strategy to train a CNN model that detects image patches with buildings. Furthermore, the authors perform an experiment in MapSwipe (smartphone-based application for humanitarian mapping) asking the volunteers to just verify the tiles that are selected by a trained classifier, saving considerably the user effort and obtaining an accurate classifier.…”
Section: B Building Detection and Segmentationmentioning
confidence: 99%