Vision-based pavement marking detection : a case study

Shuyuan Xu; Jun Wang; Peng Wu; Wenchi Shou; Tingchen Fang; Xiangyu Wang

doi:10.1007/978-3-030-51295-8_81

Vision-based pavement marking detection : a case study

Shuyuan Xu
, Jun Wang
, Peng Wu
, Wenchi Shou
, Tingchen Fang
, Xiangyu Wang

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

4 Citations (Scopus)

Abstract

Pavement markings take responsibility to communicate with road users regarding travel regulations and guidance. Due to their irreplaceable role in ensuring the safety and order on road, it would be beneficial for road agencies to keep an as-is inventory record of the pavement markings on their roads for managerial operations. However, faced with the sheer volume of their responsible assets, manual inspection would be time-consuming and error prone. This study proposes a vision-based method to automatically detect and classify longitudinal markings using videos of road pavement. Not only line markings, audible markings, as a special category, were also identified in the images. The proposed method can achieve an average 0.89 detection accuracy for line markings and 0.82 for audible markings. Limitations and future work are also proposed. This study tests the possibility of utilising visual data to assist road agencies with an informative management of their civil assets.

Original language	English
Title of host publication	Proceedings of the 18th International Conference on Computing in Civil and Building Engineering (ICCCBE 2020), 18 - 20 August, 2020, SÃ£o Paulo, Brazil
Publisher	Springer
Pages	1162-1171
Number of pages	10
ISBN (Print)	9783030512941
DOIs	https://doi.org/10.1007/978-3-030-51295-8_81
Publication status	Published - 2021
Event	International Conference on Computing in Civil and Building Engineering - Duration: 18 Aug 2020 → …

Publication series

Name	Lecture Notes in Civil Engineering
Volume	98
ISSN (Print)	2366-2557
ISSN (Electronic)	2366-2565

Conference

Conference	International Conference on Computing in Civil and Building Engineering
Period	18/08/20 → …

Bibliographical note

Publisher Copyright:
© 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

computer vision
pavements
road markings
roads

Access to Document

10.1007/978-3-030-51295-8_81

Cite this

Xu, S., Wang, J., Wu, P., Shou, W., Fang, T., & Wang, X. (2021). Vision-based pavement marking detection : a case study. In Proceedings of the 18th International Conference on Computing in Civil and Building Engineering (ICCCBE 2020), 18 - 20 August, 2020, SÃ£o Paulo, Brazil (pp. 1162-1171). (Lecture Notes in Civil Engineering; Vol. 98). Springer. https://doi.org/10.1007/978-3-030-51295-8_81

@inproceedings{e04bbf3ebe754277a2228e8ddbe14810,

title = "Vision-based pavement marking detection : a case study",

abstract = "Pavement markings take responsibility to communicate with road users regarding travel regulations and guidance. Due to their irreplaceable role in ensuring the safety and order on road, it would be beneficial for road agencies to keep an as-is inventory record of the pavement markings on their roads for managerial operations. However, faced with the sheer volume of their responsible assets, manual inspection would be time-consuming and error prone. This study proposes a vision-based method to automatically detect and classify longitudinal markings using videos of road pavement. Not only line markings, audible markings, as a special category, were also identified in the images. The proposed method can achieve an average 0.89 detection accuracy for line markings and 0.82 for audible markings. Limitations and future work are also proposed. This study tests the possibility of utilising visual data to assist road agencies with an informative management of their civil assets.",

keywords = "computer vision, pavements, road markings, roads",

author = "Shuyuan Xu and Jun Wang and Peng Wu and Wenchi Shou and Tingchen Fang and Xiangyu Wang",

note = "Publisher Copyright: {\textcopyright} 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.; International Conference on Computing in Civil and Building Engineering ; Conference date: 18-08-2020",

year = "2021",

doi = "10.1007/978-3-030-51295-8\_81",

language = "English",

isbn = "9783030512941",

series = "Lecture Notes in Civil Engineering",

publisher = "Springer",

pages = "1162--1171",

booktitle = "Proceedings of the 18th International Conference on Computing in Civil and Building Engineering (ICCCBE 2020), 18 - 20 August, 2020, S{\~A}£o Paulo, Brazil",

}

Xu, S, Wang, J, Wu, P, Shou, W, Fang, T & Wang, X 2021, Vision-based pavement marking detection : a case study. in Proceedings of the 18th International Conference on Computing in Civil and Building Engineering (ICCCBE 2020), 18 - 20 August, 2020, SÃ£o Paulo, Brazil. Lecture Notes in Civil Engineering, vol. 98, Springer, pp. 1162-1171, International Conference on Computing in Civil and Building Engineering, 18/08/20. https://doi.org/10.1007/978-3-030-51295-8_81

Vision-based pavement marking detection : a case study. / Xu, Shuyuan; Wang, Jun; Wu, Peng et al.
Proceedings of the 18th International Conference on Computing in Civil and Building Engineering (ICCCBE 2020), 18 - 20 August, 2020, SÃ£o Paulo, Brazil. Springer, 2021. p. 1162-1171 (Lecture Notes in Civil Engineering; Vol. 98).

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Vision-based pavement marking detection : a case study

AU - Xu, Shuyuan

AU - Wang, Jun

AU - Wu, Peng

AU - Shou, Wenchi

AU - Fang, Tingchen

AU - Wang, Xiangyu

PY - 2021

Y1 - 2021

N2 - Pavement markings take responsibility to communicate with road users regarding travel regulations and guidance. Due to their irreplaceable role in ensuring the safety and order on road, it would be beneficial for road agencies to keep an as-is inventory record of the pavement markings on their roads for managerial operations. However, faced with the sheer volume of their responsible assets, manual inspection would be time-consuming and error prone. This study proposes a vision-based method to automatically detect and classify longitudinal markings using videos of road pavement. Not only line markings, audible markings, as a special category, were also identified in the images. The proposed method can achieve an average 0.89 detection accuracy for line markings and 0.82 for audible markings. Limitations and future work are also proposed. This study tests the possibility of utilising visual data to assist road agencies with an informative management of their civil assets.

AB - Pavement markings take responsibility to communicate with road users regarding travel regulations and guidance. Due to their irreplaceable role in ensuring the safety and order on road, it would be beneficial for road agencies to keep an as-is inventory record of the pavement markings on their roads for managerial operations. However, faced with the sheer volume of their responsible assets, manual inspection would be time-consuming and error prone. This study proposes a vision-based method to automatically detect and classify longitudinal markings using videos of road pavement. Not only line markings, audible markings, as a special category, were also identified in the images. The proposed method can achieve an average 0.89 detection accuracy for line markings and 0.82 for audible markings. Limitations and future work are also proposed. This study tests the possibility of utilising visual data to assist road agencies with an informative management of their civil assets.

KW - computer vision

KW - pavements

KW - road markings

KW - roads

UR - http://hdl.handle.net/1959.7/uws:56862

UR - https://www.scopus.com/pages/publications/85088454269

U2 - 10.1007/978-3-030-51295-8_81

DO - 10.1007/978-3-030-51295-8_81

M3 - Conference Paper

SN - 9783030512941

T3 - Lecture Notes in Civil Engineering

SP - 1162

EP - 1171

BT - Proceedings of the 18th International Conference on Computing in Civil and Building Engineering (ICCCBE 2020), 18 - 20 August, 2020, SÃ£o Paulo, Brazil

PB - Springer

T2 - International Conference on Computing in Civil and Building Engineering

Y2 - 18 August 2020

ER -

Vision-based pavement marking detection : a case study

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this