Vehicle localization based on the detection of line segments from multi-camera images

Kosuke Hara, Hideo Saito

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

For realizing autonomous vehicle driving and advanced safety systems, it is necessary to achieve accurate vehicle localization in cities. This paper proposes a method of accurately estimating vehicle position by matching a map and line segment features detected from images captured by a camera. Features such as white road lines, yellow road lines, road signs, and curb stones, which could be used as clues for vehicle localization, were expressed as line segment features on a two-dimensional road plane in an integrated manner. The detected line segments were subjected to bird’s-eye view transformation to transform them to the vehicle coordinate system so that they could be used for vehicle localization regardless of the camera configuration. Moreover, an extended Kalman filter was applied after a detailed study of the line observation errors for realizing real-time estimation. Vehicle localization was tested under city driving conditions, and the vehicle position was identified with sub-meter accuracy.

Original languageEnglish
Pages (from-to)617-626
Number of pages10
JournalJournal of Robotics and Mechatronics
Volume27
Issue number6
Publication statusPublished - 2015

Fingerprint

Cameras
Curbs
Extended Kalman filters
Security systems

Keywords

  • Autonomous driving
  • Line segment detection
  • Localization
  • Multi camera system

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science(all)

Cite this

Vehicle localization based on the detection of line segments from multi-camera images. / Hara, Kosuke; Saito, Hideo.

In: Journal of Robotics and Mechatronics, Vol. 27, No. 6, 2015, p. 617-626.

Research output: Contribution to journalArticle

@article{26780d91fd8c4ba5979e0628542f0a4c,
title = "Vehicle localization based on the detection of line segments from multi-camera images",
abstract = "For realizing autonomous vehicle driving and advanced safety systems, it is necessary to achieve accurate vehicle localization in cities. This paper proposes a method of accurately estimating vehicle position by matching a map and line segment features detected from images captured by a camera. Features such as white road lines, yellow road lines, road signs, and curb stones, which could be used as clues for vehicle localization, were expressed as line segment features on a two-dimensional road plane in an integrated manner. The detected line segments were subjected to bird’s-eye view transformation to transform them to the vehicle coordinate system so that they could be used for vehicle localization regardless of the camera configuration. Moreover, an extended Kalman filter was applied after a detailed study of the line observation errors for realizing real-time estimation. Vehicle localization was tested under city driving conditions, and the vehicle position was identified with sub-meter accuracy.",
keywords = "Autonomous driving, Line segment detection, Localization, Multi camera system",
author = "Kosuke Hara and Hideo Saito",
year = "2015",
language = "English",
volume = "27",
pages = "617--626",
journal = "Journal of Robotics and Mechatronics",
issn = "0915-3942",
publisher = "Fuji Technology Press",
number = "6",

}

TY - JOUR

T1 - Vehicle localization based on the detection of line segments from multi-camera images

AU - Hara, Kosuke

AU - Saito, Hideo

PY - 2015

Y1 - 2015

N2 - For realizing autonomous vehicle driving and advanced safety systems, it is necessary to achieve accurate vehicle localization in cities. This paper proposes a method of accurately estimating vehicle position by matching a map and line segment features detected from images captured by a camera. Features such as white road lines, yellow road lines, road signs, and curb stones, which could be used as clues for vehicle localization, were expressed as line segment features on a two-dimensional road plane in an integrated manner. The detected line segments were subjected to bird’s-eye view transformation to transform them to the vehicle coordinate system so that they could be used for vehicle localization regardless of the camera configuration. Moreover, an extended Kalman filter was applied after a detailed study of the line observation errors for realizing real-time estimation. Vehicle localization was tested under city driving conditions, and the vehicle position was identified with sub-meter accuracy.

AB - For realizing autonomous vehicle driving and advanced safety systems, it is necessary to achieve accurate vehicle localization in cities. This paper proposes a method of accurately estimating vehicle position by matching a map and line segment features detected from images captured by a camera. Features such as white road lines, yellow road lines, road signs, and curb stones, which could be used as clues for vehicle localization, were expressed as line segment features on a two-dimensional road plane in an integrated manner. The detected line segments were subjected to bird’s-eye view transformation to transform them to the vehicle coordinate system so that they could be used for vehicle localization regardless of the camera configuration. Moreover, an extended Kalman filter was applied after a detailed study of the line observation errors for realizing real-time estimation. Vehicle localization was tested under city driving conditions, and the vehicle position was identified with sub-meter accuracy.

KW - Autonomous driving

KW - Line segment detection

KW - Localization

KW - Multi camera system

UR - http://www.scopus.com/inward/record.url?scp=84957588604&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957588604&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84957588604

VL - 27

SP - 617

EP - 626

JO - Journal of Robotics and Mechatronics

JF - Journal of Robotics and Mechatronics

SN - 0915-3942

IS - 6

ER -