Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Gating attention convolutional networks with dense connection for pixel-level crack detection

  • Regular Paper
  • Published:
Multimedia Systems Aims and scope Submit manuscript

Abstract

Automatic detection of pavement cracks is an important task to ensure pavement safety. However, noise and uneven cracks in real pavement images present great challenges for crack detection. To address these issues, we propose a novel pavement crack detection network model with a densely connected architecture and a gating attention mechanism. Based on SegNet, the proposed network utilizes an atrous convolutional dense connection module (AD-block) to efficiently extract crack features with different structures in the encoding stage. In addition, for locating crack pixels in the decoding stage, a new gating attention unit (GAU) is designed that can suppress the background noise and accurately locate the crack pixels. Finally, by means of a new multiscale feature fusion (MFF) module, the side outputs are aggregated to obtain the final prediction results. Evaluations of the public DeepCrack, CFD, and Crack500 datasets show that our method achieves better performance than other recent approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Li, Q., Liu, X.: Novel approach to pavement image segmentation based on neighboring difference histogram method. IEE P-Vis. Image Sign. 8(2), 792–796 (2008)

    Google Scholar 

  2. Medina, R., Llamas, J., Bermejo, G.G., J., et al.: Crack detection in concrete tunnels using a gabor filter invariant to rotation. Sensors. 17(7), 1670–1680 (2017)

    Article  Google Scholar 

  3. Liu, Z., Shahrel, A., Ohashi, T., et al.: Tunnel crack detection and classification system based on image processing. In: Proceedings of Society of Photo-Optical Instrumentation Engineers (SPIE). San Jose, USA, 2002, pp. 145–152.

  4. Bang, S., Park, S., Kim, H.: Encoder-decoder network for pixel-level road crack detection in black-box images. Comput. Aided Civil Infrastruct. Eng. 34(8), 713–727 (2019)

    Article  Google Scholar 

  5. Choi, W., Cha, Y.J.: SDDNet: real-time crack segmentation. IEEE Trans. Ind. Electron. 67(9), 8016–8025 (2019)

    Article  Google Scholar 

  6. Qu, Z., Cao, C., Liu, L., Zhou, D.Y.: A deeply supervised convolutional neural network for pavement crack detection with multiscale feature fusion. IEEE Trans. Neural Netw. Learn. Syst. (2021). https://doi.org/10.1109/TNNLS.2021.3062070

    Article  Google Scholar 

  7. Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)

    Article  Google Scholar 

  8. Lee, C., Xie, S., Gallagher, P. and Tu, Z. 2015 Deeply-supervised nets. In: Proceedings of Artif. Intell. Statist. (AISTATS), pp. 562–570

  9. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 3431–3440 (2017)

    Google Scholar 

  10. Yang, X., Li, H., Yu, Y., Luo, X., Huang, T., Yang, X.: Automatic pixel-level crack detection and measurement using fully convolutional network. Comput. Aided Civil Infrastruct. Eng. 33(12), 1090–1109 (2018)

    Article  Google Scholar 

  11. Huang, H.W., Li, Q.T., Zhang, D.M.: Deep learning based image recognition for crack and leakage defects of metro shield tunnel. Tunnelling Underground Space Technol. 77, 166–176 (2018)

    Article  Google Scholar 

  12. Dung, C.V., Anh, L.D.: Autonomous concrete crack detection using deep fully convolutional neural network. Autom. Construct. 99, 52–58 (2019)

    Article  Google Scholar 

  13. Ren, Y., Huang, J., Hong, Z., et al.: Image-based concrete crack detection in tunnels using deep fully convolutional networks. Building Mater, Construct (2020). https://doi.org/10.1016/j.conbuildmat.2019.117367

    Book  Google Scholar 

  14. Chen, F.C., Mohammad, R.J.: NB-FCN: real-time accurate crack detection in inspection videos using deep fully convolutional network and parametric data fusion. IEEE Trans Instrum. 69(8), 5325–5334 (2019)

    Article  Google Scholar 

  15. Zou, Q., Zhang, Z., Li, Q., Qi, X., Wang, Q., Wang, S.: Deepcrack: Learning hierarchical convolutional features for crack detection. IEEE Trans. Image Process. 28(3), 1498–1512 (2019)

    Article  MathSciNet  Google Scholar 

  16. Liu, Y., Yao, J., Lu, X., Xie, R., Li, L.: DeepCrack: a deep hierarchical feature learning architecture for crack segmentation. Neurocomputing 338, 139–153 (2019)

    Article  Google Scholar 

  17. Nguyen, N., Perrya, S., Bone, D., et al.: Two-stage convolutional neural network for road crack detection and segmentation. Exp. Syst. Appl (2021). https://doi.org/10.1016/j.eswa.2021.115718

    Article  Google Scholar 

  18. Hu, G.X., Hu, B.L., Yang, Z., Huang, L., Li, P.: Pavement crack detection method based on deep learning models. Wireless Commun. Mobile Comput. 2021, 1–13 (2021)

    Google Scholar 

  19. Fan, Z., Li, C., Chen, Y., et al.: Automatic crack detection on road pavements using encoder-decoder architecture. Materials (2021). https://doi.org/10.3390/ma13132960

    Article  Google Scholar 

  20. Hu, J., Shen, L., Albanie, S.G., Wu, E.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42(8), 2011–2023 (2020)

    Article  Google Scholar 

  21. Park, J., Woo, S., Lee, J. and Kweon, I.: BAM: Bottleneck attention module. In: Proceedings of Brit. Mach. Vis. Conf. 2018, pp. 1–14

  22. Woo, S., Park, Lee, J. J. Y. and Kweon, I. S.: CBAM: Convolutional block attention module. In: Proceedings of IEEE Eur. Conf. Comput. Vis. Munich, Germany, 2018, pp. 3–19

  23. Fu, J., Liu, J., Tian, H., et al.: Dual attention network for scene segmentation. In: Proceedings of IEEE Comput. Vis. Pattern Recognit. Long Beach, USA, pp. 3141–3149 (2019). https://doi.org/10.1109/CVPR.2019.00326

  24. Liu, H.J., Liu, F.Q., Fan, X.Y. and Huang, D.: Polarized self-attention: towards high-quality pixel-wise regression (2021). arXiv preprint arXiv:2107.00782

  25. Oktay O, Schlemper J, Folgoc LL., et al.: Attention U-Net: learning where to look for the pancreas (2018). arXiv preprint arXiv:1804.03999

  26. Yang, Z. X., Zhu, L., Wu, Y., et al.: Gated channel transformation for visual recognition. In: Proceedings of IEEE Conf. Comput. Vision and Pattern Recognit. (CVPR). Seattle, 2020, pp. 11791–800

  27. Qu, Z., Chen, W., Wang, S.Y., Yi, T.M., Liu, L.: A crack detection algorithm for concrete pavement based on attention mechanism and multi-features fusion. IEEE Trans. Intell. Transp. Syst. (2021). https://doi.org/10.1109/TITS.2021.3106647

    Article  Google Scholar 

  28. Zhou, Q., Qu, Z., Cao, C.: Mixed pooling and richer attention feature fusion for crack detection. Pattern Recogn. Lett. 145, 96–102 (2021)

    Article  Google Scholar 

  29. Sun, X.Z., Xie, Y.C., Cao, Y., et al.: DMA-Net: deepLab With Multi-Scale attention for pavement crack segmentation. IEEE Trans. Intell. Transp. Syst. (2022). https://doi.org/10.1109/TITS.2022.3158670

    Article  Google Scholar 

  30. Zhou, S.L., Song, W.: Robust image-based surface crack detection using range data. J. Comput Civil. Eng (2020). https://doi.org/10.1061/(ASCE)CP.1943-5487.0000873

    Article  Google Scholar 

  31. Sun, M.S., Zhao, H.W., Li, J.: Road crack detection network under noise based on feature pyramid structure with feature enhancement. IET Image Proc. 16(3), 809–822 (2022)

    Article  Google Scholar 

  32. Yu, J.W., Chen, Z.P., Xiong, Z.M.: A novel path voting algorithm for surface crack detection. Electronics (2022). https://doi.org/10.3390/electronics11030501

    Article  Google Scholar 

  33. Safaei, N., Smadi, O., Masoud, A., Safaei, B.: An automatic image processing algorithm based on crack pixel density for pavement crack detection and classification. Int. J. Pavement. Res. Technol. 15(1), 159–172 (2022)

    Article  Google Scholar 

  34. Ronneberger, O., Fischer, P., Brox, T. 2015 U-net: convolutional networks for biomedical image segmentation. In: Proceedings of Conf. MICCAI. Cham, , pp. 234–241

  35. Zhou, Z., Siddiquee, M., Tajbkhsh, N., et al.: Unet++: Redesigning skip connections to exploit muti-scale features in image segmentation. IEEE Transactions. Medical Imaging. 39(6), 1856–1867 (2019)

    Article  Google Scholar 

  36. Huang, G., Liu, Z., Weinberger, K. Q., et al. 2017 Densely connected convolutional networks. In: Proceedings of Conference on Computer Vision and Pattern Recognition. (CVPR). Munich, Germany, , pp. 4700–4708

  37. Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F. and Adam, H. 2017 Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR), Munich, Germany, pp. 833–851

  38. Chen, H.S., Lin, H.P.: An effective hybrid atrous convolutional network for pixel-level crack detection. IEEE Trans. Instrum. 70, 388–393 (2021)

    Google Scholar 

  39. Lin, F. Z., Yang, J., Shu, J. P., et al. (2021) Crack semantic segmentation using the U-Net with full attention strategy. In: Proceedings of IEEE Conf. Comput. Vision and Pattern Recognit. arXiv preprint arXiv: 2104. 14586

  40. Petar, V., Cucurull, G., Casanova, A., et al.: Graph attention networks (2017). arXiv preprint. arXiv:1710.10903. https://doi.org/10.48550/arXiv.1710.10903

  41. Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, F., Tang, X. and Wang, X.: Residual attention network for image classification. In: Proceedings of IEEE Conf. Comput. Vision and Pattern Recognit. (CVPR). Honolulu, HI, pp. 6450–6458 (2017). https://doi.org/10.1109/CVPR.2017.683

  42. Hdanau, B., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). arXiv preprint arXiv:1409.0473

  43. Lin, T. Y., Goyal, P., Girshick, R., He, K., Dollár, P. 2017 Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision. Venice pp. 2980–2988

  44. Shi, Y., Cui, L., Qi, Z., Meng, F., Chen, Z.: Automatic road crack detection using random structured forests. IEEE Trans. Intell. Transp. Syst. 17(12), 3434–3445 (2016)

    Article  Google Scholar 

  45. Yang, F., Zhang, L., Yu, S., et al.: Feature pyramid and hierarchical boosting network for pavement crack detection. IEEE Trans. Intell. Transp. Syst. 21(4), 1525–1535 (2020)

    Article  Google Scholar 

Download references

Acknowledgements

The authors wish to thank the associate editors and anonymous reviewers for their valuable comments and suggestions on this paper. This work was supported by the National Natural Science Foundation of China (No. 62176034, 61905033).

Author information

Authors and Affiliations

  1. Chongqing University of Posts and Telecommunications, Chongqing, China

    Zhong Qu & Lili Wang

Authors
  1. Zhong Qu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lili Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

ZQ and LiW wrote the main manuscript text and prepared figures 1-10 and tables 1-4. All authors reviewed the manuscript.

Corresponding author

Correspondence to Zhong Qu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Qu, Z., Wang, L. Gating attention convolutional networks with dense connection for pixel-level crack detection. Multimedia Systems 29, 641–652 (2023). https://doi.org/10.1007/s00530-022-01008-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00530-022-01008-3

Keywords

Search

Navigation