Road Crack Detection Using U-Net

Naoki Wada; Kenji Kanai; Masaru Takeuchi; Jiro Katto

doi:10.1109/GCCE50665.2020.9292044

Road Crack Detection Using U-Net

Naoki Wada, Kenji Kanai, Masaru Takeuchi, Jiro Katto

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

Abstract

Recently, an efficient and automatic infrastructure maintenance service is mandatory. To address this demand, in this paper, we introduce a segmentation-based road damage detection method by using U-Net. To train the model, we collect 4K images by using a smartphone mounted on a bicycle and build our own road damage dataset. In addition, to improve detection accuracy, we apply focal loss and image patch for loss function and input image, respectively. From the evaluation, the result confirms that the method demonstrates to extract road damages with acceptable accuracy.

Original language	English
Title of host publication	2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	301-302
Number of pages	2
ISBN (Electronic)	9781728198026
DOIs	https://doi.org/10.1109/GCCE50665.2020.9292044
Publication status	Published - 2020 Oct 13
Event	9th IEEE Global Conference on Consumer Electronics, GCCE 2020 - Kobe, Japan Duration: 2020 Oct 13 → 2020 Oct 16

Publication series

Name	2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

Conference

Conference	9th IEEE Global Conference on Consumer Electronics, GCCE 2020
Country/Territory	Japan
City	Kobe
Period	20/10/13 → 20/10/16

Keywords

Deep learning
Mobile sensing
Road monitoring
Semantic segmentation

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering
Media Technology
Instrumentation
Computer Networks and Communications
Computer Vision and Pattern Recognition

Access to Document

10.1109/GCCE50665.2020.9292044

Cite this

Road Crack Detection Using U-Net. / Wada, Naoki; Kanai, Kenji; Takeuchi, Masaru et al.
2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 301-302 9292044 (2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020).

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

Wada, N, Kanai, K, Takeuchi, M & Katto, J 2020, Road Crack Detection Using U-Net. in 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020., 9292044, 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020, Institute of Electrical and Electronics Engineers Inc., pp. 301-302, 9th IEEE Global Conference on Consumer Electronics, GCCE 2020, Kobe, Japan, 20/10/13. https://doi.org/10.1109/GCCE50665.2020.9292044

@inproceedings{930fdf1a7e9a4d41a786ebf34bdcda20,

title = "Road Crack Detection Using U-Net",

abstract = "Recently, an efficient and automatic infrastructure maintenance service is mandatory. To address this demand, in this paper, we introduce a segmentation-based road damage detection method by using U-Net. To train the model, we collect 4K images by using a smartphone mounted on a bicycle and build our own road damage dataset. In addition, to improve detection accuracy, we apply focal loss and image patch for loss function and input image, respectively. From the evaluation, the result confirms that the method demonstrates to extract road damages with acceptable accuracy. ",

keywords = "Deep learning, Mobile sensing, Road monitoring, Semantic segmentation",

author = "Naoki Wada and Kenji Kanai and Masaru Takeuchi and Jiro Katto",

note = "Funding Information: This paper is supported by the verification-style R&D program for solving regional challenges using data cooperation and utilization by NICT, Japan. Publisher Copyright: {\textcopyright} 2020 IEEE.; 9th IEEE Global Conference on Consumer Electronics, GCCE 2020 ; Conference date: 13-10-2020 Through 16-10-2020",

year = "2020",

month = oct,

day = "13",

doi = "10.1109/GCCE50665.2020.9292044",

language = "English",

series = "2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "301--302",

booktitle = "2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020",

}

TY - GEN

T1 - Road Crack Detection Using U-Net

AU - Wada, Naoki

AU - Kanai, Kenji

AU - Takeuchi, Masaru

AU - Katto, Jiro

N1 - Funding Information: This paper is supported by the verification-style R&D program for solving regional challenges using data cooperation and utilization by NICT, Japan. Publisher Copyright: © 2020 IEEE.

PY - 2020/10/13

Y1 - 2020/10/13

N2 - Recently, an efficient and automatic infrastructure maintenance service is mandatory. To address this demand, in this paper, we introduce a segmentation-based road damage detection method by using U-Net. To train the model, we collect 4K images by using a smartphone mounted on a bicycle and build our own road damage dataset. In addition, to improve detection accuracy, we apply focal loss and image patch for loss function and input image, respectively. From the evaluation, the result confirms that the method demonstrates to extract road damages with acceptable accuracy.

AB - Recently, an efficient and automatic infrastructure maintenance service is mandatory. To address this demand, in this paper, we introduce a segmentation-based road damage detection method by using U-Net. To train the model, we collect 4K images by using a smartphone mounted on a bicycle and build our own road damage dataset. In addition, to improve detection accuracy, we apply focal loss and image patch for loss function and input image, respectively. From the evaluation, the result confirms that the method demonstrates to extract road damages with acceptable accuracy.

KW - Deep learning

KW - Mobile sensing

KW - Road monitoring

KW - Semantic segmentation

UR - http://www.scopus.com/inward/record.url?scp=85099335669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85099335669&partnerID=8YFLogxK

U2 - 10.1109/GCCE50665.2020.9292044

DO - 10.1109/GCCE50665.2020.9292044

M3 - Conference contribution

AN - SCOPUS:85099335669

T3 - 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

SP - 301

EP - 302

BT - 2020 IEEE 9th Global Conference on Consumer Electronics, GCCE 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th IEEE Global Conference on Consumer Electronics, GCCE 2020

Y2 - 13 October 2020 through 16 October 2020

ER -

Road Crack Detection Using U-Net

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this