Efficient vehicle localization based on road-boundary maps

Dawei Zhao; Tao Wu; Yuqiang Fang; Ruili Wang; Jing Dai; Bin Dai

doi:10.1007/978-3-319-13560-1

Efficient vehicle localization based on road-boundary maps

Dawei Zhao, Tao Wu, Yuqiang Fang, Ruili Wang, Jing Dai, Bin Dai

Research output: Journal Publication › Article › peer-review

1 Citation (Scopus)

Abstract

Localization is a critical task of autonomous vehicles, and can provide a foundation for the planning and perception modules. In this paper, we propose a novel vehicle localization method based on roadboundary maps. Firstly, a fast road boundary detection method based on random forests is presented. Secondly, two road-boundary maps, global and local maps, are built based on the boundary detection results respectively. Finally, an efficient localization algorithm via the road-boundary maps in Bayes framework is implemented. Our method is evaluated with data collected from an urban environment and the results show that the proposed method can be used for efficient road boundary detection and accurate vehicle localization.

Original language	English
Pages (from-to)	536-547
Number of pages	12
Journal	Lecture Notes in Computer Science
Volume	8862
DOIs	https://doi.org/10.1007/978-3-319-13560-1
Publication status	Published - 2014
Externally published	Yes

Keywords

Random forests
Road boundary detection
Vehicle localization

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-319-13560-1

Cite this

@article{8cfbe0d35e5c424da64bb7f14f397abc,

title = "Efficient vehicle localization based on road-boundary maps",

abstract = "Localization is a critical task of autonomous vehicles, and can provide a foundation for the planning and perception modules. In this paper, we propose a novel vehicle localization method based on roadboundary maps. Firstly, a fast road boundary detection method based on random forests is presented. Secondly, two road-boundary maps, global and local maps, are built based on the boundary detection results respectively. Finally, an efficient localization algorithm via the road-boundary maps in Bayes framework is implemented. Our method is evaluated with data collected from an urban environment and the results show that the proposed method can be used for efficient road boundary detection and accurate vehicle localization.",

keywords = "Random forests, Road boundary detection, Vehicle localization",

author = "Dawei Zhao and Tao Wu and Yuqiang Fang and Ruili Wang and Jing Dai and Bin Dai",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2014.",

year = "2014",

doi = "10.1007/978-3-319-13560-1",

language = "English",

volume = "8862",

pages = "536--547",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Verlag",

}

TY - JOUR

T1 - Efficient vehicle localization based on road-boundary maps

AU - Zhao, Dawei

AU - Wu, Tao

AU - Fang, Yuqiang

AU - Wang, Ruili

AU - Dai, Jing

AU - Dai, Bin

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2014.

PY - 2014

Y1 - 2014

N2 - Localization is a critical task of autonomous vehicles, and can provide a foundation for the planning and perception modules. In this paper, we propose a novel vehicle localization method based on roadboundary maps. Firstly, a fast road boundary detection method based on random forests is presented. Secondly, two road-boundary maps, global and local maps, are built based on the boundary detection results respectively. Finally, an efficient localization algorithm via the road-boundary maps in Bayes framework is implemented. Our method is evaluated with data collected from an urban environment and the results show that the proposed method can be used for efficient road boundary detection and accurate vehicle localization.

AB - Localization is a critical task of autonomous vehicles, and can provide a foundation for the planning and perception modules. In this paper, we propose a novel vehicle localization method based on roadboundary maps. Firstly, a fast road boundary detection method based on random forests is presented. Secondly, two road-boundary maps, global and local maps, are built based on the boundary detection results respectively. Finally, an efficient localization algorithm via the road-boundary maps in Bayes framework is implemented. Our method is evaluated with data collected from an urban environment and the results show that the proposed method can be used for efficient road boundary detection and accurate vehicle localization.

KW - Random forests

KW - Road boundary detection

KW - Vehicle localization

UR - http://www.scopus.com/inward/record.url?scp=84911924423&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-13560-1

DO - 10.1007/978-3-319-13560-1

M3 - Article

AN - SCOPUS:84911924423

SN - 0302-9743

VL - 8862

SP - 536

EP - 547

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

ER -

Efficient vehicle localization based on road-boundary maps

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this