Road network fusion for incremental map updates

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

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 mapping services heavily use human annotation to minimize the mapping errors. Consequently, their response to changes in the road network is inevitably slow. In this paper we describe MapFuse, a system which fuses a human-annotated map (e.g., OpenStreetMap) with any automatically inferred map, thus effectively enabling quick map updates. In addition to new road creation, we study in depth road closure, which have not been examined in the past. By leveraging solid, human-annotated maps with minor corrections, we derive maps which minimize the trajectory matching errors due to both road network change and imperfect map inference of fully-automatic approaches.

Original languageEnglish
Pages (from-to)91-109
Number of pages19
JournalLecture Notes in Geoinformation and Cartography
Issue number208669
DOIs
Publication statusPublished - 1 Jan 2018

Fingerprint

road network
Fusion reactions
road
coverage
Electric fuses
Global positioning system
GPS
trajectory
Trajectories

Keywords

  • Map fusion
  • Map inference
  • Road closures

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Geography, Planning and Development
  • Earth-Surface Processes
  • Computers in Earth Sciences

Cite this

Road network fusion for incremental map updates. / Stanojevic, Rade; Abbar, Sofiane; Thirumuruganathan, Saravanan; Morales, Gianmarco; Chawla, Sanjay; Filali, Fethi; Aleimat, Ahid.

In: Lecture Notes in Geoinformation and Cartography, No. 208669, 01.01.2018, p. 91-109.

Research output: Contribution to journalConference article

@article{33032becbdde4edaa547b95013aca535,
title = "Road network fusion for incremental map updates",
abstract = "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 mapping services heavily use human annotation to minimize the mapping errors. Consequently, their response to changes in the road network is inevitably slow. In this paper we describe MapFuse, a system which fuses a human-annotated map (e.g., OpenStreetMap) with any automatically inferred map, thus effectively enabling quick map updates. In addition to new road creation, we study in depth road closure, which have not been examined in the past. By leveraging solid, human-annotated maps with minor corrections, we derive maps which minimize the trajectory matching errors due to both road network change and imperfect map inference of fully-automatic approaches.",
keywords = "Map fusion, Map inference, Road closures",
author = "Rade Stanojevic and Sofiane Abbar and Saravanan Thirumuruganathan and Gianmarco Morales and Sanjay Chawla and Fethi Filali and Ahid Aleimat",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-319-71470-7_5",
language = "English",
pages = "91--109",
journal = "Lecture Notes in Geoinformation and Cartography",
issn = "1863-2351",
publisher = "Springer International Publishing AG",
number = "208669",

}

TY - JOUR

T1 - Road network fusion for incremental map updates

AU - Stanojevic, Rade

AU - Abbar, Sofiane

AU - Thirumuruganathan, Saravanan

AU - Morales, Gianmarco

AU - Chawla, Sanjay

AU - Filali, Fethi

AU - Aleimat, Ahid

PY - 2018/1/1

Y1 - 2018/1/1

N2 - 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 mapping services heavily use human annotation to minimize the mapping errors. Consequently, their response to changes in the road network is inevitably slow. In this paper we describe MapFuse, a system which fuses a human-annotated map (e.g., OpenStreetMap) with any automatically inferred map, thus effectively enabling quick map updates. In addition to new road creation, we study in depth road closure, which have not been examined in the past. By leveraging solid, human-annotated maps with minor corrections, we derive maps which minimize the trajectory matching errors due to both road network change and imperfect map inference of fully-automatic approaches.

AB - 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 mapping services heavily use human annotation to minimize the mapping errors. Consequently, their response to changes in the road network is inevitably slow. In this paper we describe MapFuse, a system which fuses a human-annotated map (e.g., OpenStreetMap) with any automatically inferred map, thus effectively enabling quick map updates. In addition to new road creation, we study in depth road closure, which have not been examined in the past. By leveraging solid, human-annotated maps with minor corrections, we derive maps which minimize the trajectory matching errors due to both road network change and imperfect map inference of fully-automatic approaches.

KW - Map fusion

KW - Map inference

KW - Road closures

UR - http://www.scopus.com/inward/record.url?scp=85041331109&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041331109&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-71470-7_5

DO - 10.1007/978-3-319-71470-7_5

M3 - Conference article

SP - 91

EP - 109

JO - Lecture Notes in Geoinformation and Cartography

JF - Lecture Notes in Geoinformation and Cartography

SN - 1863-2351

IS - 208669

ER -