Crack detection is important for evaluating pavement conditions. In this paper, we propose an automatic pavement crack detection method called as U2CrackNet. The architecture of U2CrackNet is a two-level nested U-structure which is an encoding and decoding architecture. Firstly, the crack features are extracted by the encoding layer so that the preliminary effective feature layer is obtained. Subsequently, the encoder and decoder are connected by an atrous spatial pyramid pooling (ASPP) model. The atrous convolution with different expansion rates can be used to capture the multi-scale crack information. Besides, in order to make the network pay more attention to the features of cracks, the crack feature map channels are given different weights through the effective channel attention mechanism after upsampling in the decoding layer. Finally, the crack saliency probability maps generated by each layer of the network are fused into the final crack saliency map through cascade operation. The proposed method has been evaluated on an expanded pavement crack dataset containing 8700 images. The experimental results demonstrate that the proposed U2CrackNet can obtain more clear and continuous cracks. Specifically, the precision, accuracy, F1-score, and Mean Intersection over Union (MIoU) are 89.51%, 98.95%, 81.45%, and 69.19%, respectively.
LiHWuZNieJ, et al. Automatic crack detection algorithm for airport pavement based on depth image. J Traffic Transp Eng2021; 20(6): 1–12.
2.
HoangND.Detection of surface crack in building structures using image processing technique with an improved Otsu method for image thresholding. Adv Civil Eng2018; 2018: 3924120.
3.
TianWShenHLiX, et al. Research on corridor surface crack detection technology based on image processing. Electronic Design Eng2020; 28(5): 48–156.
4.
DollárPZitnickCL. Structured forests for fast edge detection. In: Proceedings of the IEEE international conference on computer vision, Portland, USA, 1–8 December 2013, pp. 1841–1848. New York: IEEE.
5.
ShiYCuiLQiZ, et al. Automatic road crack detection using random structured forests. IEEE Trans Intell Transp Syst2016; 17(12): 3434–3445.
6.
ZouQCaoYLiQ, et al. Cracktree: automatic crack detection from pavement images. Pattern Recognit Lett2012; 33(3): 227–238.
7.
LiSCaoYCaiH.Automatic pavement-crack detection and segmentation based on steerable matched filtering and an active contour model. J Comput Civil Eng2017; 31(5): 04017045.
8.
AkagicABuzaEOmanovicS, et al. Pavement crack detection using Otsu thresholding for image segmentation. In: 2018 41st International convention on information and communication technology, electronics and microelectronics (MIPRO), Opatija, Croatia, 21–25 May 2018, pp. 1092–1097. New York: IEEE.
9.
QuanYSunJZhangY, et al. The method of the road surface crack detection by the improved Otsu threshold. In: 2019 IEEE international conference on mechatronics and automation (ICMA), Tianjin, China, 4–7 August 2019, pp. 1615–1620. New York: IEEE.
10.
LiPLiQMaW, et al. Pavement rack segmentation algorithm based on k-means clustering. Comput Eng Design2020; 41(11): 5.
11.
YangFZhangLYuS, et al. Feature pyramid and hierarchical boosting network for pavement crack detection. IEEE Trans Intell Transp Syst2019; 21(4): 1525–1535.
12.
DungCVAnhLD.Autonomous concrete crack detection using deep fully convolutional neural network. Autom Constr2019; 99: 52–58.
13.
LiuYYaoJLuX, et al. Deepcrack: a deep hierarchical feature learning architecture for crack segmentation. Neurocomputing2019; 338: 139–153.
14.
ZouQZhangZLiQ, et al. Deepcrack: learning hierarchical convolutional features for crack detection. IEEE Trans Image Proc2018; 28(3): 1498–1512.
15.
LiuZCaoYWangY, et al. Computer vision-based concrete crack detection using U-net fully convolutional networks. Autom Constr2019; 104: 129–139.
16.
WangLMaXYeY. Computer vision-based road crack detection using an improved I-UNet convolutional networks. In: 2020 Chinese control and decision conference (CCDC), Hefei, China, 22–24 August 2020, pp. 539–543. New York: IEEE.
17.
ZhangHPengBXuW. Road crack detection based on UNet++ and conditional generative adversarial network. J Comput Appl 2020; 40(S02): 4.
18.
GhoshSSinghSMaityA, et al. Crackweb: a modified U-Net based segmentation architecture for crack detection. In: IOP conference series: materials science and engineering, Shanghai, China, 2021, vol. 1080, p. 012002. IOP Publishing.
19.
ZhuYWangHLiK, et al. A high precision pavement crack detection network structure Crack U-NET. Comput Sci2022; 49(1): 204–211.
20.
KangDBenipalSSGopalDL, et al. Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning. Autom Constr2020; 118: 103291.
ChaYJChoiWSuhG, et al. Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput-Aided Civ Infrastruct Eng2018; 33(9): 731–747.
23.
QinXZhangZHuangC, et al. U2-Net: going deeper with nested U-structure for salient object detection. Pattern Recognit2020; 106: 107404.
24.
ChenLCPapandreouGSchroffF, et al. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:170605587 2017.
25.
ChoiWChaYJ. Sddnet: real-time crack segmentation. IEEE Trans Ind Electron2019; 67(9): 8016–8025.
26.
KangDHChaYJ. Efficient attention-based deep encoder and decoder for automatic crack segmentation. Struct Health Monit2022; 21(5): 2190–2205.
27.
WangQWuBZhuP, et al. ECA-Net: efficient channel attention for deep convolutional neural networks. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), Seattle, USA, 2020. New York: IEEE.
28.
ZhouZSiddiqueeMMRTajbakhshN, et al. Unet++: a nested u-net architecture for medical image segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support, Granada, Spain, 2018, pp. 3–11. Springer.
29.
XieSTuZ. Holistically-nested edge detection. In: Proceedings of the IEEE international conference on computer vision, Santiago, Chile, 7–13 December 2015, pp. 1395–1403. New York: IEEE.
30.
ZhangLYangFZhangYD, et al. Road crack detection using deep convolutional neural network. In: 2016 IEEE international conference on image processing (ICIP), Phoenix, AZ, USA, 25–28 September 2016, pp. 3708–3712. New York: IEEE.
31.
EisenbachMStrickerRSeichterD, et al. How to get pavement distress detection ready for deep learning? a systematic approach. In: 2017 International joint conference on neural networks (IJCNN), Anchorage, AK, USA, 14–19 May 2017, pp. 2039–2047. New York: IEEE.
