Skip to main content
SpringerLink
Log in

A lightweight road crack detection algorithm based on improved YOLOv7 model

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Road crack detection plays a crucial role in protecting road safety. However, early manual detection is not only time-consuming and laborious but also highly inefficient. Although existing road inspection vehicles have powerful functions and precise detection, their high cost makes them not universally applicable. Besides, existing object detection algorithms have high computational costs, but the computing power of edge devices is often limited, making it difficult to deploy detection algorithms on edge devices. To this end, we propose a lightweight and efficient road crack detection algorithm, YOLOv7 BiFPN-G, based on YOLOv7. In response to the shortcomings of PANet in feature fusion in the original YOLOv7, we introduce the BiFPN structure to construct a better backbone feature extraction network. It achieves a higher level of feature fusion through different weights. To reduce the number of parameters, we introduce a lightweight Ghost convolution instead of the standard convolution, which continuously compresses the number of parameters through depthwise separable convolution. Then, we reduce the channel width and depth training parameters to further reduce the number of parameters and use knowledge distillation to improve the performance of the reduced model. Finally, we developed a road crack detection system based on the obtained model, which is mobile-friendly, inexpensive, and universal. We conduct visual experiments to compare the detection performance of multiple algorithms in various complex road environments. Compared with YOLOv7, YOLOv7 BiFPN-G is more lightweight, with only 7.4M parameters and a model size of only 14.MB, while there is no significant degradation in model accuracy. Compared with lightweight models YOLOv5-s and YOLOv7-tiny, YOLOv7-BiFPN-G shows leading performance in average accuracy, recall, and accuracy. The experimental results demonstrate that YOLOv7-BiFPN-G has good performance in normal road environments.

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

Access this article

Log in via an institution

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
Fig. 12
Fig. 13

Similar content being viewed by others

Data availability

https://github.com/sekilab/RoadDamageDetector

References

  1. Arya, D., et al.: RDD2020: an annotated image dataset for automatic road damage detection using deep learning. Data Brief 36(1), 107133 (2021)

    Article  Google Scholar 

  2. Arya, D. et al.: RDD2022: a multi-national image dataset for automatic road damage detection. arXiv preprint arXiv:2209.08538 (2022)

  3. Cho, J.H., Hariharan, B.: On the efficacy of knowledge distillation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4794–4802 (2019)

  4. Deng, B., Lv, H.: Survey of target detection based on neural network. J. Phys. Conf. Ser. 1952(2), 022055 (2021)

    Article  Google Scholar 

  5. Dharneeshkar, J. et al.: Deep learning based detection of potholes in Indian roads using YOLO. In: International Conference on Inventive Computation Technologies (ICICT). IEEE. 2020, pp. 381–385 (2020)

  6. Han, Kai., et al.: Ghostnet: more features from cheap operations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 1580–1589 (2020)

  7. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)

  8. Howard, A. et al.: Searching for mobilenetv3. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1314–1324 (2019)

  9. Howard, A.G. et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)

  10. Lin, T.-Y., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

  11. Liu, L., Zuo, H., Qiu, X.: Research on defect pattern recognition of light guide plate based on deep learning semantic segmentation. J. Phys. Conf. Ser. 1865(2), 022033 (2021)

    Article  Google Scholar 

  12. Liu, S. et al.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768 (2018)

  13. Liu, W. et al.: SSD: Single shot multibox detector. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer, pp. 21–37 (2016)

  14. Liu, Y., Shao, Z., Hoffmann, N.: Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv:2112.05561 (2021)

  15. Ma, N. et al.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116–131 (2018)

  16. Mandal, Vishal, Mussah, Abdul Rashid, Adu-Gyamfi, Yaw, “Deep learning frameworks for pavement distress classification: A comparative analysis”. In,: IEEE international conference on big data (big data). IEEE. 2020, 5577–5583 (2020)

  17. Mandal, V., Mussah, A.R., Adu-Gyamfi, Y.: Deep learning frameworks for pavement distress classification: a comparative analysis. In: IEEE International Conference on Big Data (Big Data). IEEE. 2020, 5577–5583 (2020)

  18. Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)

  19. Redmon, J., et al.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)

  20. Ren, S., et al.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)

  21. Sandler, M. et al.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)

  22. Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning. PMLR. pp. 6105–6114 (2019)

  23. Tripathi, M.: Analysis of convolutional neural network based image classification techniques. J. Innov. Image Process. 2 (2021)

  24. Wan, F., et al.: YOLO-LRDD: a lightweight method for road damage detection based on improved YOLOv5s. EURASIP J. Adv. Signal Process. 2022(1), 98 (2022)

    Article  Google Scholar 

  25. Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464–7475 (2023)

  26. Wang, L., Yoon, K.-J.: Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3048–3068 (2021)

    Article  Google Scholar 

  27. Xiao, Q., et al.: Transparent component defect detection method based on improved YOLOv7 algorithm’’. Int. J. Pattern Recognit. Artif. Intell. 37(14), 2350030 (2023)

    Article  Google Scholar 

  28. Xie, J., et al.: Gesture Recognition Controls Image Style Transfer Based on Improved YOLOV5s Algorithm. Springer, Cham (2022)

    Book  Google Scholar 

  29. Zhang, X., et al.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)

  30. Zoph, B. et al.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)

Download references

Acknowledgements

This work is supported in part by the Natural Science Foundation of Zhejiang Province under Grant No. LQ23F020010 and No. LZ22F020010, in part by the National Natural Science Foundation of China under Grant No. 62272419, and in part by Jinhua Science and Technology Plan Project under Grant No. 2023-4-016.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Zhejiang Normal University, Jinhua, 321004, China

    Junjie He, Yanchao Wang, Yiting Wang, Run Li, Dawei Zhang & Zhonglong Zheng

  2. Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province, Jinhua, 321004, China

    Dawei Zhang & Zhonglong Zheng

Authors
  1. Junjie He
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yanchao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yiting Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Run Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Dawei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhonglong Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

JH was involved in conceptualization, methodology, software, and writing-original draft. YW contributed to data curation, analysis, and writing—reviewing and editing. YW and RL contributed to data curation and writing—reviewing and editing. DZ was responsible for conceptualization, methodology, writing-reviewing and editing, supervision, and funding acquisition. ZZ took part in writing—reviewing and editing, supervision, and funding acquisition.

Corresponding author

Correspondence to Dawei Zhang.

Ethics declarations

Conflict of interest

The authors declare no Conflict of interest.

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 (e.g. a society or other partner) 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

He, J., Wang, Y., Wang, Y. et al. A lightweight road crack detection algorithm based on improved YOLOv7 model. SIViP (2024). https://doi.org/10.1007/s11760-024-03197-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11760-024-03197-y

Keywords

Search

Navigation