Automated algorithm for removing clutter objects in mms point cloud for 3D road mapping

Jisang Lee; Suhong Yoo; Seunghwan Hong; Mohammad Gholami Farkoushi; Junsu Bae; Ilsuk Park; Hong Gyoo Sohn

doi:10.3390/s20154076

Automated algorithm for removing clutter objects in mms point cloud for 3D road mapping

Jisang Lee, Suhong Yoo, Seunghwan Hong, Mohammad Gholami Farkoushi, Junsu Bae, Ilsuk Park, Hong Gyoo Sohn

Department of Civil and Environmental Engineering

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

4 Citations (Scopus)

Abstract

Road information high definition maps (HD map) contain information about the facilities around the roads and are often constructed through a mobile mapping system (MMS). Although constructing an HD map is essential for road maintenance and the application of autonomous driving in the future, it is problematic to acquire the data of objects other than the facilities in an unstructured form while operating the MMS. In this study, the researchers define this object data as clutter objects and present a method of automatic removal using characteristics of the MMS and image segmentation techniques. By applying the method to 10 KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago) datasets, clutter objects were removed with an average overall accuracy of 91% with 0% (0.448%) error of commission for the complete point cloud map.

Original language	English
Article number	4076
Pages (from-to)	1-11
Number of pages	11
Journal	Sensors (Switzerland)
Volume	20
Issue number	15
DOIs	https://doi.org/10.3390/s20154076
Publication status	Published - 2020 Aug 1

Bibliographical note

Publisher Copyright:
© 2020 by the authors. Licensee MDPI, Basel, Switzerland.

All Science Journal Classification (ASJC) codes

Analytical Chemistry
Biochemistry
Atomic and Molecular Physics, and Optics
Instrumentation
Electrical and Electronic Engineering

Access to Document

10.3390/s20154076

Cite this

@article{3f7649579779435594f5e6d0609eb79d,

title = "Automated algorithm for removing clutter objects in mms point cloud for 3D road mapping",

abstract = "Road information high definition maps (HD map) contain information about the facilities around the roads and are often constructed through a mobile mapping system (MMS). Although constructing an HD map is essential for road maintenance and the application of autonomous driving in the future, it is problematic to acquire the data of objects other than the facilities in an unstructured form while operating the MMS. In this study, the researchers define this object data as clutter objects and present a method of automatic removal using characteristics of the MMS and image segmentation techniques. By applying the method to 10 KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago) datasets, clutter objects were removed with an average overall accuracy of 91% with 0% (0.448%) error of commission for the complete point cloud map.",

author = "Jisang Lee and Suhong Yoo and Seunghwan Hong and Farkoushi, {Mohammad Gholami} and Junsu Bae and Ilsuk Park and Sohn, {Hong Gyoo}",

note = "Publisher Copyright: {\textcopyright} 2020 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2020",

month = aug,

day = "1",

doi = "10.3390/s20154076",

language = "English",

volume = "20",

pages = "1--11",

journal = "Sensors (Switzerland)",

issn = "1424-8220",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "15",

}

TY - JOUR

T1 - Automated algorithm for removing clutter objects in mms point cloud for 3D road mapping

AU - Lee, Jisang

AU - Yoo, Suhong

AU - Hong, Seunghwan

AU - Farkoushi, Mohammad Gholami

AU - Bae, Junsu

AU - Park, Ilsuk

AU - Sohn, Hong Gyoo

PY - 2020/8/1

Y1 - 2020/8/1

N2 - Road information high definition maps (HD map) contain information about the facilities around the roads and are often constructed through a mobile mapping system (MMS). Although constructing an HD map is essential for road maintenance and the application of autonomous driving in the future, it is problematic to acquire the data of objects other than the facilities in an unstructured form while operating the MMS. In this study, the researchers define this object data as clutter objects and present a method of automatic removal using characteristics of the MMS and image segmentation techniques. By applying the method to 10 KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago) datasets, clutter objects were removed with an average overall accuracy of 91% with 0% (0.448%) error of commission for the complete point cloud map.

AB - Road information high definition maps (HD map) contain information about the facilities around the roads and are often constructed through a mobile mapping system (MMS). Although constructing an HD map is essential for road maintenance and the application of autonomous driving in the future, it is problematic to acquire the data of objects other than the facilities in an unstructured form while operating the MMS. In this study, the researchers define this object data as clutter objects and present a method of automatic removal using characteristics of the MMS and image segmentation techniques. By applying the method to 10 KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago) datasets, clutter objects were removed with an average overall accuracy of 91% with 0% (0.448%) error of commission for the complete point cloud map.

UR - http://www.scopus.com/inward/record.url?scp=85088236038&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85088236038&partnerID=8YFLogxK

U2 - 10.3390/s20154076

DO - 10.3390/s20154076

M3 - Article

C2 - 32707854

AN - SCOPUS:85088236038

SN - 1424-8220

VL - 20

SP - 1

EP - 11

JO - Sensors (Switzerland)

JF - Sensors (Switzerland)

IS - 15

M1 - 4076

ER -

Automated algorithm for removing clutter objects in mms point cloud for 3D road mapping

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this