Bridge Crack Segmentation and Measurement Method Based on Full Convolutional Neural Network

HU Wenkui; DENG Hui; FU Zhixu; AN Dongyang; DUAN Rui

doi:10.13204/j.gyjzG21053111

Volume 52 Issue 4

Jul. 2022

Turn off MathJax

Article Contents

Article Navigation > INDUSTRIAL CONSTRUCTION > 2022 > 52(4): 192-201,218

HU Wenkui, DENG Hui, FU Zhixu, AN Dongyang, DUAN Rui. Bridge Crack Segmentation and Measurement Method Based on Full Convolutional Neural Network[J]. INDUSTRIAL CONSTRUCTION, 2022, 52(4): 192-201,218. doi: 10.13204/j.gyjzG21053111

Citation:

HU Wenkui, DENG Hui, FU Zhixu, AN Dongyang, DUAN Rui. Bridge Crack Segmentation and Measurement Method Based on Full Convolutional Neural Network[J]. INDUSTRIAL CONSTRUCTION, 2022, 52(4): 192-201,218. doi: 10.13204/j.gyjzG21053111

Citation:

PDF( 5509 KB)

Bridge Crack Segmentation and Measurement Method Based on Full Convolutional Neural Network

doi: 10.13204/j.gyjzG21053111

School of Civil Engineering and Transportation, South China University of Technology, Guangzhou 510641, China

Received Date: 2021-05-31
Available Online: 2022-07-25

Abstract

Abstract

In order to improve the automation level of bridge disease detection, solve the current manual detection time-consuming and laborious, traditional image segmentation methods have problems such as non-obvious denoising effect and poor crack continuity after segmentation. A bridge crack automatic segmentation model of BCI-AS(Bridge Crack Image-Automatic Segmentation) based on full convolutional neural network and a crack width measurement algorithm of least square fitting center line based on projection technology were proposed.Based on the BCI-AS model, the image data set of bridge cracks was segmented at the pixel level accurately, and the segmentation accuracy reached 94.45%.The width of the segmented crack binary map was measured by the least square center line fitting algorithm based on the projection technology. The results showed that the relative error was less than 7%, which could prove the feasibility of the proposed algorithm for crack segmentation and crack width calculation.
- bridge cracks,
- image segmentation,
- full convolutional neural network,
- least squares fitting

FullText(HTML)

References(21)

References

[1]	HENDRICKSON C T.Applications of advanced technologies in transportation engineering[J].Journal of Transportation Engineering,2004,130(3):272-273.
[2]	张德津,李清泉,陈颖,等.基于空间聚集特征的沥青路面裂缝检测方法[J].自动化学报,2016,42(3):443-454.
[3]	KIRSCHKE K R,VELINSKY S A.Histogram-based approach for automated pavement-crack sensing[J].Journal of Transportation Engineering,1992,118(5):700-710.
[4]	孙波成.基于数字图像处理的沥青路面裂缝识别技术研究[D].成都:西南交通大学,2014.
[5]	TANG J,GU Y.Automatic crack detection and segmentation using a hybrid algorithm for road distress analysis[C]//IEEE International Conference on Systems,Man,and Cybernetics.Manchester,UK:IEEE,2013:3026-3030.
[6]	李楠.基于深度学习框架Caffe的路面裂缝识别研究[J].冶金丛刊,2017(3):20-28.
[7]	赵珊珊,何宁.基于卷积神经网络的路面裂缝检测[J].传感器与微系统,2017,36(11):135-138.
[8]	BADRINARAYANAN V,KENDALL A,CIPOLLA R.Segnet:a deep convolutional encoder-decoder architecture for scene segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[9]	中华人民共和国交通部.公路桥涵养护规范:JTG H11-2004[S].北京:人民交通出版社,2004.
[10]	陈龙,赵巍.一种改进的自适应分段线性变换算法[J].激光与红外,2020,50(8):1020-1024.
[11]	LIU F,LIU Z.A neighborhood-based value iteration algorithm for POMDP problems[C]//2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI).Volos Greece:IEEE,2018:808-812.
[12]	韩思奇,王蕾.图像分割的阈值法综述[J].系统工程与电子技术,2002,24(6):91-94.
[13]	吴昊.常用的数字图像边缘检测算法分析[J].淮海工学院学报(自然科学版),2013,22(3):31-33.
[14]	KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNet classification with deep convolutional neural networks[J].Advances in Neural Information Processing Systems,2012,25(2):84-90.
[15]	SZEGEDY C,LIU W,JIA Y,et al.Going Deeper with Convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA:IEEE,2015:1-9.
[16]	陈子杰.基于深度全卷积神经网络的头颈部CT中放疗危及器官分割方法研究[D].北京:中国科学院大学,2019.
[17]	LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(4):640-651.
[18]	程刚,楚汝峰,张伦.一种用于检测预定区域中特定标识图像的方法及装置:CN105303189A[P].2016-02-13.
[19]	王聪雅.基于图像识别处理的桥梁底面裂缝检测方法的研究[D].北京:北京交通大学,2016.
[20]	王鹏.基于无人机视频的桥梁裂缝识别方法研究[D].广州:华南理工大学,2018.
[21]	WANG W,WANG M,LI H,et al.Pavement crack image acquisition methods and crack extraction algorithms:a review[J].Journal of Traffic and Transportation Engineering (English Edition),2019,6(6):535-556.