A deep residual network with transfer learning for pixel-level road crack detection

Seongdeok Bang, Somin Park, Hongjo Kim, Yeo san Yoon, Hyoungkwan Kim

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Image-based crack detection methods have been extensively studied due to their cost-effectiveness in terms of data acquisition and processing. However, automated crack detection still remain a challenging task due to complexity of image background and different patterns of cracks. To address these issues, this paper proposes a deep residual network with transfer learning for pixel-level crack detection on road surface images. The network was trained on 71 images of CrackForest dataset and tested on 47 images of it. Experimental results suggest that the deep residual network is superior to the existing algorithms with recall value and precision value of 84.90% and 93.57%, respectively.

Original languageEnglish
Publication statusPublished - 2018 Jan 1
Event35th International Symposium on Automation and Robotics in Construction and International AEC/FM Hackathon: The Future of Building Things, ISARC 2018 - Berlin, Germany
Duration: 2018 Jul 202018 Jul 25

Other

Other35th International Symposium on Automation and Robotics in Construction and International AEC/FM Hackathon: The Future of Building Things, ISARC 2018
CountryGermany
CityBerlin
Period18/7/2018/7/25

Fingerprint

Crack detection
Pixels
Cost effectiveness
Data acquisition
Cracks

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Building and Construction

Cite this

Bang, S., Park, S., Kim, H., Yoon, Y. S., & Kim, H. (2018). A deep residual network with transfer learning for pixel-level road crack detection. Paper presented at 35th International Symposium on Automation and Robotics in Construction and International AEC/FM Hackathon: The Future of Building Things, ISARC 2018, Berlin, Germany.
Bang, Seongdeok ; Park, Somin ; Kim, Hongjo ; Yoon, Yeo san ; Kim, Hyoungkwan. / A deep residual network with transfer learning for pixel-level road crack detection. Paper presented at 35th International Symposium on Automation and Robotics in Construction and International AEC/FM Hackathon: The Future of Building Things, ISARC 2018, Berlin, Germany.
@conference{cb70d6cffd7849018b3e20b95f172b46,
title = "A deep residual network with transfer learning for pixel-level road crack detection",
abstract = "Image-based crack detection methods have been extensively studied due to their cost-effectiveness in terms of data acquisition and processing. However, automated crack detection still remain a challenging task due to complexity of image background and different patterns of cracks. To address these issues, this paper proposes a deep residual network with transfer learning for pixel-level crack detection on road surface images. The network was trained on 71 images of CrackForest dataset and tested on 47 images of it. Experimental results suggest that the deep residual network is superior to the existing algorithms with recall value and precision value of 84.90{\%} and 93.57{\%}, respectively.",
author = "Seongdeok Bang and Somin Park and Hongjo Kim and Yoon, {Yeo san} and Hyoungkwan Kim",
year = "2018",
month = "1",
day = "1",
language = "English",
note = "35th International Symposium on Automation and Robotics in Construction and International AEC/FM Hackathon: The Future of Building Things, ISARC 2018 ; Conference date: 20-07-2018 Through 25-07-2018",

}

Bang, S, Park, S, Kim, H, Yoon, YS & Kim, H 2018, 'A deep residual network with transfer learning for pixel-level road crack detection' Paper presented at 35th International Symposium on Automation and Robotics in Construction and International AEC/FM Hackathon: The Future of Building Things, ISARC 2018, Berlin, Germany, 18/7/20 - 18/7/25, .

A deep residual network with transfer learning for pixel-level road crack detection. / Bang, Seongdeok; Park, Somin; Kim, Hongjo; Yoon, Yeo san; Kim, Hyoungkwan.

2018. Paper presented at 35th International Symposium on Automation and Robotics in Construction and International AEC/FM Hackathon: The Future of Building Things, ISARC 2018, Berlin, Germany.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A deep residual network with transfer learning for pixel-level road crack detection

AU - Bang, Seongdeok

AU - Park, Somin

AU - Kim, Hongjo

AU - Yoon, Yeo san

AU - Kim, Hyoungkwan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Image-based crack detection methods have been extensively studied due to their cost-effectiveness in terms of data acquisition and processing. However, automated crack detection still remain a challenging task due to complexity of image background and different patterns of cracks. To address these issues, this paper proposes a deep residual network with transfer learning for pixel-level crack detection on road surface images. The network was trained on 71 images of CrackForest dataset and tested on 47 images of it. Experimental results suggest that the deep residual network is superior to the existing algorithms with recall value and precision value of 84.90% and 93.57%, respectively.

AB - Image-based crack detection methods have been extensively studied due to their cost-effectiveness in terms of data acquisition and processing. However, automated crack detection still remain a challenging task due to complexity of image background and different patterns of cracks. To address these issues, this paper proposes a deep residual network with transfer learning for pixel-level crack detection on road surface images. The network was trained on 71 images of CrackForest dataset and tested on 47 images of it. Experimental results suggest that the deep residual network is superior to the existing algorithms with recall value and precision value of 84.90% and 93.57%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85053872134&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053872134&partnerID=8YFLogxK

M3 - Paper

ER -

Bang S, Park S, Kim H, Yoon YS, Kim H. A deep residual network with transfer learning for pixel-level road crack detection. 2018. Paper presented at 35th International Symposium on Automation and Robotics in Construction and International AEC/FM Hackathon: The Future of Building Things, ISARC 2018, Berlin, Germany.