Skip to main content
SpringerLink
Log in

A Grain Boundary Defects Detection Algorithm with Improved Localization Accuracy Based on EfficientDet

  • Published:
Automatic Control and Computer Sciences Aims and scope Submit manuscript

Abstract

Defects detection is one of the most important tasks in the materials industry. The existence of grain boundary defects causes the crystal structure to be susceptible to corrosion, which leads to a significant reduction in metal plasticity, hardness, and tensile strength. At present, some deep learning methods have been proposed to detect such problems based on HRTEM (high-resolution transmission electron microscope) images of crystal defects. However, they face the problem of low detection rate and low localization accuracy. In this paper, an improved detection algorithm has been proposed. Firstly, to balance the performance and complexity, the EfficientDet based network is adopted in the algorithm. Secondly, a weighted fusion module is introduced to the EfficientDet network to integrate the output of features from the backbone and BiFPN (bidirectional feature pyramid network) to achieve good detection accuracy. Finally, the location loss function of the network is substituted by \(CIoU\) (complete intersection over union) loss, which can improve the defects localization accuracy. The experimental results show that compared to the initial algorithms, the AP (average precision) value of grain boundary defect detection can be improved by about 5%.

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.

REFERENCES

  1. Ziatdinov, M., Dyck, O., Maksov, A., Li, X., Sang, X., Xiao, K., Unocic, R.R., Vasudevan, R., Jesse, S., and Kalinin, S.V., Deep learning of atomically resolved scanning transmission electron microscopy images: Chemical identification and tracking local transformations, ACS Nano, 2017, vol. 11, no. 12, pp. 12742–12752. https://doi.org/10.1021/acsnano.7b07504

    Article  Google Scholar 

  2. Madsen, J., Liu, P., Kling, J., Wagner, J.B., Hansen, T.W., Winther, O., and Schiøtz, J., A deep learning approach to identify local structures in atomic-resolution transmission electron microscopy images, Adv. Theory Simul., 2018, vol. 1, no. 8, p. 1800037. https://doi.org/10.1002/adts.201800037

    Article  Google Scholar 

  3. Lin, R., Zhang, R., Wang, Ch., Yang, X.-Q., and Xin, H.L., TEMImageNet training library and AtomSegNet deep-learning models for high-precision atom segmentation, localization, denoising, and deblurring of atomic-resolution images, Sci. Rep., 2021, vol. 11, p. 5386. https://doi.org/10.1038/s41598-021-84499-w

    Article  Google Scholar 

  4. Tan, M., Pang, R., and Le, Q.V., EfficientDet: Scalable and efficient object detection, 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Seattle, Wash., 2020, IEEE, 2020, pp. 10778–10787. https://doi.org/10.1109/CVPR42600.2020.01079

  5. Girshick, R., Donahue, J., Darrell, T., and Malik, J., Rich feature hierarchies for accurate object detection and semantic segmentation, 2014 IEEE Conf. Computer Vision and Pattern Recognition, Columbus, Ohio, 2014, IEEE, 2014, pp. 580–587. https://doi.org/10.1109/CVPR.2014.81

  6. Girshick, R., Fast R-CNN, 2015 IEEE Int. Conf. on Computer Vision (ICCV), Santiago, Chile, 2015, IEEE, 2015, pp. 1440–1448. https://doi.org/10.1109/ICCV.2015.169

  7. Ren, Sh., He, K., Girschik, R., and Sn, J., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Trans. Pattern Anal. Mach. Intell., 2017, vol. 39, no. 6, pp. 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031

    Article  Google Scholar 

  8. He, K., Gkioxari, G., Dollár, and Girschik, R., Mask R-CNN, 2017 IEEE Int. Conf. on Computer Vision (ICCV), Venice, 2017, IEEE, 2017, pp. 2980–2988. https://doi.org/10.1109/ICCV.2017.322

  9. He, K., Zhang, X., Ren, Sh., and Sun, J., Spatial pyramid pooling in deep convolutional networks for visual recognition, Computer Vision—ECCV 2014, Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T., Eds., Lecture Notes in Computer Science, vol. 8691, Cham: Springer, 2014, pp. 346–361. https://doi.org/10.1007/978-3-319-10578-9_23

    Book  Google Scholar 

  10. Dai, J., Li, Yi, He, K., and Sun, J., R-FCN: Object detection via region-based fully convolutional networks, Proc. 30th Int. Conf. on Neural Information Processing Systems, Barcelona, 2016, Lee, D.D., von Luxburg, U., Garnett, R., Sugiyama, M., and Guyon, I., Eds., Red Hook, N.Y.: Curran Associates, 2016, pp. 379–387.

  11. Redmon, J., Divvala, S., Girschik, R., and Farhadi, A., You only look once: Unified, real-time object detection, 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016, IEEE, 2016, pp. 779–788. https://doi.org/10.1109/CVPR.2016.91

  12. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, Ch.-Ya., and Berg, A.C., SSD: Single shot multibox detector, Computer Vision—ECCV 2016, Leibe, B., Matas, J., Sebe, N., and Welling, M., Eds., Lecture Notes in Computer Science, vol. 9905, Cham: Springer, 2016, pp. 21–37. https://doi.org/10.1007/978-3-319-46448-0_2

    Book  Google Scholar 

  13. Lin, Ts.-Yi, Goyal, P., Girschik, R., He, K., and Dollár, P., Focal loss for dense object detection, 2017 IEEE Int. Conf. on Computer Vision (ICCV), Venice, 2017, IEEE, 2017, pp. 2999–3007. https://doi.org/10.1109/ICCV.2017.324

  14. Cao, L., Zhang, X., Pu, J., Xu, S., Cai, X., and Li, Zh., The field wheat count based on the EfficientDet algorithm, IEEE 3rd Int. Conf. on Information Systems and Computer Aided Education (ICISCAE), Dalian, China, 2020, IEEE, 2020, pp. 557–561. https://doi.org/10.1109/ICISCAE51034.2020.9236918

  15. Chen, Q., Rigall, E., Wang, X., Fan, H., and Dong, J., Poker watcher: Playing card detection based on EfficientDet and sandglass block, 11th Int. Conf. on Awareness Science and Technology (iCAST), Qingdao, China, 2020, IEEE, 2020, pp. 1–6. https://doi.org/10.1109/iCAST51195.2020.9319468

  16. Ayachi, R., Afif, M., Said, Ya., and Abdelali, A.B., Drivers fatigue detection using EfficientDet in advanced driver assistance systems, 18th Int. Multi-Conf. on Systems, Signals & Devices (SSD), Monastir, Tunisia, 2021, IEEE, 2021, pp. 738–742. https://doi.org/10.1109/SSD52085.2021.9429294

  17. Tan, M. and Le, Q., EfficientNet: Rethinking model scaling for convolutional neural networks, Proc. Mach. Learn. Res., 2019, vol. 97, pp. 6105–6114.

    Google Scholar 

  18. Qiao, S., Chen, L.-Ch., and Yuille, A., DetectoRS: Detecting objects with recursive feature pyramid and switchable Atrous convolution, 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Nashville, Tenn., 2021, IEEE, 2021, pp. 10208–10219. https://doi.org/10.1109/CVPR46437.2021.01008

  19. Yu, J., Jiang, Yu., Wang, Zh., Cao, Zh., and Huang, T., Unitbox: An advanced object detection network, Proc. 24th ACM Int. Conf. on Multimedia, Amsterdam, 2016, New York: Association for Computing Machinery, 2016, pp. 516–520. https://doi.org/10.1145/2964284.2967274

  20. Rezatofighi, H., Tsoi, N., Gwak, J.Yo., Sadeghian, A., Reid, I., and Savarese, S., Generalized intersection over union: A metric and a loss for bounding box regression, 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Long Beach, Calif., 2019, IEEE, 2019, pp. 658–666. https://doi.org/10.1109/CVPR.2019.00075

  21. Zheng, Zh., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D., Distance-IoU loss: Faster and better learning for bounding box regression, Proc. AAAI Conf. Artif. Intell., 2020, vol. 34, no. 7, p. 12993–13000. https://doi.org/10.1609/aaai.v34i07.6999

  22. Kingma, D.P. and Ba, L.J., Adam: A method for stochastic optimization, Proc. Int. Conf. Learning Representation, San Diego, Calif., 2015. https://doi.org/10.48550/arXiv.1412.6980

Download references

Funding

This work is supported by MOE Planned Project of Humanities and Social Sciences (no. 20YJA870014).

Author information

Authors and Affiliations

  1. North China University of Technology, 100144, Beijing, China

    Fuqi Mao, Jing Li, Jian Yang, Zhi Liu & Mengmeng Zhang

  2. China University of Geosciences (Beijing), 100083, Beijing, China

    Fuqi Mao

Authors
  1. Fuqi Mao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jian Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mengmeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Zhi Liu or Mengmeng Zhang.

Ethics declarations

The authors declare that they have no conflicts of interest.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fuqi Mao, Li, J., Yang, J. et al. A Grain Boundary Defects Detection Algorithm with Improved Localization Accuracy Based on EfficientDet. Aut. Control Comp. Sci. 57, 81–92 (2023). https://doi.org/10.3103/S0146411623010078

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.3103/S0146411623010078

Keywords:

Search

Navigation