Recognition Method of Road Cracks with Lane Lines Based on Deep Learning

Renyi Chen; Guosheng Xu; Yan Lin; Guoai Xu; Miao Zhang

doi:10.1145/3383972.3384056

Recognition Method of Road Cracks with Lane Lines Based on Deep Learning

Renyi Chen
, Guosheng Xu
, Yan Lin
, Guoai Xu
, Miao Zhang

Beijing University of Posts and Telecommunications

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Due to the vehicle wheeling and abrasion, the paint on the lane lines usually appears cracked. In the process of automatic detection of the pavement cracks, the paint cracks can be easily misidentified as the road cracks, reducing the recognition accuracy of the pavement cracks. We propose a lane line detection method based on deep learning method, extracting multi-angle and multidimensional features of lane lines automatically. A complete dataset has been constructed to solve the problems of uneven illumination, pollution and abrasion. Our method achieves a result of 91.84% precision, 86.67% recall and 87.34% Dice coefficient, which are all about 30% better than the traditional digital image processing techniques. The crack model and the lane line model are superimposed to improve the recognition effect of pavement cracks, which is better than the single crack model.

Original language	English
Title of host publication	Proceedings of the 2020 12th International Conference on Machine Learning and Computing, ICMLC 2020
Publisher	Association for Computing Machinery
Pages	379-383
Number of pages	5
ISBN (Electronic)	9781450376426
DOIs	https://doi.org/10.1145/3383972.3384056
State	Published - 15 Feb 2020
Externally published	Yes
Event	12th International Conference on Machine Learning and Computing, ICMLC 2020 - Shenzhen, China Duration: 15 Feb 2020 → 17 Feb 2020

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	12th International Conference on Machine Learning and Computing, ICMLC 2020
Country/Territory	China
City	Shenzhen
Period	15/02/20 → 17/02/20

Keywords

Pavement cracks
deep learning
lane lines
model superimpose

Access to Document

10.1145/3383972.3384056

Cite this

Chen, R., Xu, G., Lin, Y., Xu, G., & Zhang, M. (2020). Recognition Method of Road Cracks with Lane Lines Based on Deep Learning. In Proceedings of the 2020 12th International Conference on Machine Learning and Computing, ICMLC 2020 (pp. 379-383). (ACM International Conference Proceeding Series). Association for Computing Machinery . https://doi.org/10.1145/3383972.3384056

@inproceedings{07e0934cefe74b2fac36997e5b3d6002,

title = "Recognition Method of Road Cracks with Lane Lines Based on Deep Learning",

abstract = "Due to the vehicle wheeling and abrasion, the paint on the lane lines usually appears cracked. In the process of automatic detection of the pavement cracks, the paint cracks can be easily misidentified as the road cracks, reducing the recognition accuracy of the pavement cracks. We propose a lane line detection method based on deep learning method, extracting multi-angle and multidimensional features of lane lines automatically. A complete dataset has been constructed to solve the problems of uneven illumination, pollution and abrasion. Our method achieves a result of 91.84\% precision, 86.67\% recall and 87.34\% Dice coefficient, which are all about 30\% better than the traditional digital image processing techniques. The crack model and the lane line model are superimposed to improve the recognition effect of pavement cracks, which is better than the single crack model.",

keywords = "Pavement cracks, deep learning, lane lines, model superimpose",

author = "Renyi Chen and Guosheng Xu and Yan Lin and Guoai Xu and Miao Zhang",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.; 12th International Conference on Machine Learning and Computing, ICMLC 2020 ; Conference date: 15-02-2020 Through 17-02-2020",

year = "2020",

month = feb,

day = "15",

doi = "10.1145/3383972.3384056",

language = "英语",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery ",

pages = "379--383",

booktitle = "Proceedings of the 2020 12th International Conference on Machine Learning and Computing, ICMLC 2020",

address = "美国",

}

Chen, R, Xu, G, Lin, Y, Xu, G & Zhang, M 2020, Recognition Method of Road Cracks with Lane Lines Based on Deep Learning. in Proceedings of the 2020 12th International Conference on Machine Learning and Computing, ICMLC 2020. ACM International Conference Proceeding Series, Association for Computing Machinery , pp. 379-383, 12th International Conference on Machine Learning and Computing, ICMLC 2020, Shenzhen, China, 15/02/20. https://doi.org/10.1145/3383972.3384056

Recognition Method of Road Cracks with Lane Lines Based on Deep Learning. / Chen, Renyi; Xu, Guosheng; Lin, Yan et al.
Proceedings of the 2020 12th International Conference on Machine Learning and Computing, ICMLC 2020. Association for Computing Machinery , 2020. p. 379-383 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Recognition Method of Road Cracks with Lane Lines Based on Deep Learning

AU - Chen, Renyi

AU - Xu, Guosheng

AU - Lin, Yan

AU - Xu, Guoai

AU - Zhang, Miao

PY - 2020/2/15

Y1 - 2020/2/15

N2 - Due to the vehicle wheeling and abrasion, the paint on the lane lines usually appears cracked. In the process of automatic detection of the pavement cracks, the paint cracks can be easily misidentified as the road cracks, reducing the recognition accuracy of the pavement cracks. We propose a lane line detection method based on deep learning method, extracting multi-angle and multidimensional features of lane lines automatically. A complete dataset has been constructed to solve the problems of uneven illumination, pollution and abrasion. Our method achieves a result of 91.84% precision, 86.67% recall and 87.34% Dice coefficient, which are all about 30% better than the traditional digital image processing techniques. The crack model and the lane line model are superimposed to improve the recognition effect of pavement cracks, which is better than the single crack model.

AB - Due to the vehicle wheeling and abrasion, the paint on the lane lines usually appears cracked. In the process of automatic detection of the pavement cracks, the paint cracks can be easily misidentified as the road cracks, reducing the recognition accuracy of the pavement cracks. We propose a lane line detection method based on deep learning method, extracting multi-angle and multidimensional features of lane lines automatically. A complete dataset has been constructed to solve the problems of uneven illumination, pollution and abrasion. Our method achieves a result of 91.84% precision, 86.67% recall and 87.34% Dice coefficient, which are all about 30% better than the traditional digital image processing techniques. The crack model and the lane line model are superimposed to improve the recognition effect of pavement cracks, which is better than the single crack model.

KW - Pavement cracks

KW - deep learning

KW - lane lines

KW - model superimpose

UR - https://www.scopus.com/pages/publications/85085913215

U2 - 10.1145/3383972.3384056

DO - 10.1145/3383972.3384056

M3 - 会议稿件

AN - SCOPUS:85085913215

T3 - ACM International Conference Proceeding Series

SP - 379

EP - 383

BT - Proceedings of the 2020 12th International Conference on Machine Learning and Computing, ICMLC 2020

PB - Association for Computing Machinery

T2 - 12th International Conference on Machine Learning and Computing, ICMLC 2020

Y2 - 15 February 2020 through 17 February 2020

ER -

Recognition Method of Road Cracks with Lane Lines Based on Deep Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this