Method to improve localization and mapping accuracy on the urban road using GPS, monocular camera and HD map

Young Hun Kim; Jae Myeong Kim; Gi Chang Kim; Yun Soo Choi

doi:10.7780/kjrs.2021.37.5.1.21

Method to improve localization and mapping accuracy on the urban road using GPS, monocular camera and HD map

Young Hun Kim, Jae Myeong Kim, Gi Chang Kim, Yun Soo Choi

Department of Geoinformatics

Research output: Contribution to journal › Article › peer-review

Abstract

The technology used to recognize the location and surroundings of autonomous vehicles is called SLAM. SLAM stands for Simultaneously Localization and Mapping and has recently been actively utilized in research on autonomous vehicles, starting with robotic research. Expensive GPS, INS, LiDAR, RADAR, and Wheel Odometry allow precise magnetic positioning and mapping in centimeters. However, if it can secure similar accuracy as using cheaper Cameras and GPS data, it will contribute to advancing the era of autonomous driving. In this paper, we present a method for converging monocular camera with RTK-enabled GPS data to perform RMSE 33.7 cm localization and mapping on the urban road.

Original language	English
Pages (from-to)	1095-1109
Number of pages	15
Journal	Korean Journal of Remote Sensing
Volume	37
Issue number	5-1
DOIs	https://doi.org/10.7780/kjrs.2021.37.5.1.21
State	Published - 2021

Keywords

Bias error
Bundle adjustment
GPS(RTK)
Graph optimization
Monocular visual SLAM

Access to Document

10.7780/kjrs.2021.37.5.1.21

Cite this

@article{a2ed126122f449da9b479d3f4797a097,

title = "Method to improve localization and mapping accuracy on the urban road using GPS, monocular camera and HD map",

abstract = "The technology used to recognize the location and surroundings of autonomous vehicles is called SLAM. SLAM stands for Simultaneously Localization and Mapping and has recently been actively utilized in research on autonomous vehicles, starting with robotic research. Expensive GPS, INS, LiDAR, RADAR, and Wheel Odometry allow precise magnetic positioning and mapping in centimeters. However, if it can secure similar accuracy as using cheaper Cameras and GPS data, it will contribute to advancing the era of autonomous driving. In this paper, we present a method for converging monocular camera with RTK-enabled GPS data to perform RMSE 33.7 cm localization and mapping on the urban road.",

keywords = "Bias error, Bundle adjustment, GPS(RTK), Graph optimization, Monocular visual SLAM",

author = "Kim, {Young Hun} and Kim, {Jae Myeong} and Kim, {Gi Chang} and Choi, {Yun Soo}",

note = "Publisher Copyright: {\textcopyright} This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.",

year = "2021",

doi = "10.7780/kjrs.2021.37.5.1.21",

language = "English",

volume = "37",

pages = "1095--1109",

journal = "Korean Journal of Remote Sensing",

issn = "1225-6161",

publisher = "Korean Society of Remote Sensing",

number = "5-1",

}

TY - JOUR

T1 - Method to improve localization and mapping accuracy on the urban road using GPS, monocular camera and HD map

AU - Kim, Young Hun

AU - Kim, Jae Myeong

AU - Kim, Gi Chang

AU - Choi, Yun Soo

N1 - Publisher Copyright: © This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

PY - 2021

Y1 - 2021

N2 - The technology used to recognize the location and surroundings of autonomous vehicles is called SLAM. SLAM stands for Simultaneously Localization and Mapping and has recently been actively utilized in research on autonomous vehicles, starting with robotic research. Expensive GPS, INS, LiDAR, RADAR, and Wheel Odometry allow precise magnetic positioning and mapping in centimeters. However, if it can secure similar accuracy as using cheaper Cameras and GPS data, it will contribute to advancing the era of autonomous driving. In this paper, we present a method for converging monocular camera with RTK-enabled GPS data to perform RMSE 33.7 cm localization and mapping on the urban road.

AB - The technology used to recognize the location and surroundings of autonomous vehicles is called SLAM. SLAM stands for Simultaneously Localization and Mapping and has recently been actively utilized in research on autonomous vehicles, starting with robotic research. Expensive GPS, INS, LiDAR, RADAR, and Wheel Odometry allow precise magnetic positioning and mapping in centimeters. However, if it can secure similar accuracy as using cheaper Cameras and GPS data, it will contribute to advancing the era of autonomous driving. In this paper, we present a method for converging monocular camera with RTK-enabled GPS data to perform RMSE 33.7 cm localization and mapping on the urban road.

KW - Bias error

KW - Bundle adjustment

KW - GPS(RTK)

KW - Graph optimization

KW - Monocular visual SLAM

UR - http://www.scopus.com/inward/record.url?scp=85119368067&partnerID=8YFLogxK

U2 - 10.7780/kjrs.2021.37.5.1.21

DO - 10.7780/kjrs.2021.37.5.1.21

M3 - Article

AN - SCOPUS:85119368067

SN - 1225-6161

VL - 37

SP - 1095

EP - 1109

JO - Korean Journal of Remote Sensing

JF - Korean Journal of Remote Sensing

IS - 5-1

ER -

Method to improve localization and mapping accuracy on the urban road using GPS, monocular camera and HD map

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this