Improving Navigation: Automated Name Extraction for Separately Mapped Pedestrian and Cycle Links

Anita Graser; Markus Straub

doi:10.1553/giscience2015s546

Improving Navigation: Automated Name Extraction for Separately Mapped Pedestrian and Cycle Links

Anita Graser (Speaker)
, Markus Straub

Digital Resilient Cities

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

Abstract

Navigation instructions in pre- and on-trip routing services are usually based on street names and types, distances, and turn directions. However, in digital street graphs it is common that street names for separately mapped pedestrian and cycle links are missing. This leads to unsatisfactory instructions containing "unknown road" records. Often, these unnamed links run parallel to a named road, and it would be beneficial to use this Information to generate instructions similar to "follow the sidewalk along Street A", whereby "Street A" has to be determined by an algorithm. This paper introduces the Unnamed Link Naming Problem (ULNP) and presents a new approach to automatically extract suitable names to describe separately mapped pedestrian and cycle links. The approach has been tested using OpenStreetMap data and manually generated ground truth data for the second district of the city of Vienna, Austria. Results show that our best method achieves 90.7% correct matches in this challenging setting.

Original language	English
Title of host publication	GI_Forum ‒ Journal for Geographic Information Science.
Pages	546-556
Number of pages	11
DOIs	https://doi.org/10.1553/giscience2015s546
Publication status	Published - 2015
Event	GI_Forum 2015 - Duration: 7 Jul 2015 → 10 Jul 2015

Conference

Conference	GI_Forum 2015
Period	7/07/15 → 10/07/15

Research Field

Former Research Field - Mobility Systems

Access to Document

10.1553/giscience2015s546Licence: Unspecified

Cite this

@inproceedings{3912354c91ec4e578fcc656c52cad1ad,

title = "Improving Navigation: Automated Name Extraction for Separately Mapped Pedestrian and Cycle Links",

abstract = "Navigation instructions in pre- and on-trip routing services are usually based on street names and types, distances, and turn directions. However, in digital street graphs it is common that street names for separately mapped pedestrian and cycle links are missing. This leads to unsatisfactory instructions containing {"}unknown road{"} records. Often, these unnamed links run parallel to a named road, and it would be beneficial to use this Information to generate instructions similar to {"}follow the sidewalk along Street A{"}, whereby {"}Street A{"} has to be determined by an algorithm. This paper introduces the Unnamed Link Naming Problem (ULNP) and presents a new approach to automatically extract suitable names to describe separately mapped pedestrian and cycle links. The approach has been tested using OpenStreetMap data and manually generated ground truth data for the second district of the city of Vienna, Austria. Results show that our best method achieves 90.7\% correct matches in this challenging setting.",

author = "Anita Graser and Markus Straub",

year = "2015",

doi = "10.1553/giscience2015s546",

language = "English",

isbn = "978-3-87907-558-4",

pages = "546--556",

booktitle = "GI\_Forum ‒ Journal for Geographic Information Science.",

note = "GI\_Forum 2015 ; Conference date: 07-07-2015 Through 10-07-2015",

}

TY - GEN

T1 - Improving Navigation: Automated Name Extraction for Separately Mapped Pedestrian and Cycle Links

AU - Straub, Markus

A2 - Graser, Anita

PY - 2015

Y1 - 2015

N2 - Navigation instructions in pre- and on-trip routing services are usually based on street names and types, distances, and turn directions. However, in digital street graphs it is common that street names for separately mapped pedestrian and cycle links are missing. This leads to unsatisfactory instructions containing "unknown road" records. Often, these unnamed links run parallel to a named road, and it would be beneficial to use this Information to generate instructions similar to "follow the sidewalk along Street A", whereby "Street A" has to be determined by an algorithm. This paper introduces the Unnamed Link Naming Problem (ULNP) and presents a new approach to automatically extract suitable names to describe separately mapped pedestrian and cycle links. The approach has been tested using OpenStreetMap data and manually generated ground truth data for the second district of the city of Vienna, Austria. Results show that our best method achieves 90.7% correct matches in this challenging setting.

AB - Navigation instructions in pre- and on-trip routing services are usually based on street names and types, distances, and turn directions. However, in digital street graphs it is common that street names for separately mapped pedestrian and cycle links are missing. This leads to unsatisfactory instructions containing "unknown road" records. Often, these unnamed links run parallel to a named road, and it would be beneficial to use this Information to generate instructions similar to "follow the sidewalk along Street A", whereby "Street A" has to be determined by an algorithm. This paper introduces the Unnamed Link Naming Problem (ULNP) and presents a new approach to automatically extract suitable names to describe separately mapped pedestrian and cycle links. The approach has been tested using OpenStreetMap data and manually generated ground truth data for the second district of the city of Vienna, Austria. Results show that our best method achieves 90.7% correct matches in this challenging setting.

U2 - 10.1553/giscience2015s546

DO - 10.1553/giscience2015s546

M3 - Conference Proceedings with Oral Presentation

SN - 978-3-87907-558-4

SP - 546

EP - 556

BT - GI_Forum ‒ Journal for Geographic Information Science.

T2 - GI_Forum 2015

Y2 - 7 July 2015 through 10 July 2015

ER -

Improving Navigation: Automated Name Extraction for Separately Mapped Pedestrian and Cycle Links

Abstract

Conference

Research Field

Access to Document

Fingerprint

Cite this