Abstract
In order to solve the problem of small targets being prone to false detection and missed detection in aircraft skin defect detection under complex backgrounds, the model of aircraft skin defect detection based on improved YOLOv8n is proposed in this paper. Firstly, the Shuffle Attention + + module is incorporated into the network, combined with the residual connection idea, to more efficiently fuse feature map information; Secondly, SIOU and Focal Loss are used to replace CIOU as the regression loss functions to balance positive and negative samples in complex backgrounds and accelerate model convergence; Subsequently, the bidirectional feature pyramid network is used to modify the detection head and enhance multi-scale feature fusion. Furthermore, the depth-wise convolution module is used to replace the convolution module (Conv) in the neck part, which serves to reduce the parameters of the model and speed up the detection speed. Finally, an aircraft skin defect dataset is established, combined with Mosaic data enhancement to prevent the model from overfitting, and adopted the class balancing strategy to avoid class bias. The experimental results show that the detection accuracy of our improved YOLOv8n model is 97.9%, which is 7.3% higher than the baseline model. The model’s recall rate, the mean average precision, and F1 scores are improved by 13.9%, 6.6%, and 11.0%, respectively. The detection speed has achieved 139FPS, fulfilling the requirements of high accuracy and real-time performance in small target aircraft skin defect detection tasks.
Similar content being viewed by others
Data availability
Not applicable.
References
Patterson, J., Jr.: Foreign object debris (FOD) detection research. Int. Airpt. Rev. 11(2), 22–27 (2008)
AIRBUS, A.: Aircraft characteristics airport and maintenance planning. (2017)
Li, Z. C.: Research on the fusion positioning method of vision and inertial navigation during the inspection process of aircraft skin unmanned aerial vehicles. Master. (2021). https://doi.org/10.27627/d.cnki.gzmhy.2021.000095
Xie, Y., Hu, W., Xie, S., He, L.: Surface defect detection algorithm based on feature-enhanced YOLO. Cogn. Comput. 15(2), 565–579 (2023). https://doi.org/10.1007/s12559-022-10061-z
Niu, M., Song, K., Huang, L., Wang, Q., Yan, Y., Meng, Q.: Unsupervised saliency detection of rail surface defects using stereoscopic images. IEEE Trans. Ind. Inf. 17(3), 2271–2281 (2020)
Miao, R., Shan, Z., Zhou, Q., Wu, Y., Ge, L., Zhang, J., Hu, H.: Real-time defect identification of narrow overlap welds and application based on convolutional neural networks. J. Manuf. Syst. 62, 800–810 (2022). https://doi.org/10.1016/j.jmsy.2021.01.012
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580–587 (2014). https://doi.org/10.18127/j00338486-202109-11
Girshick, R.: Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, 1440–1448 (2015).
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp. 2961–2969 (2017)
He, D., Ren, R., Li, K., Zou, Z., Ma, R., Qin, Y., Yang, W.: Urban rail transit obstacle detection based on improved R-CNN. Measurement 196, 111277 (2022)
Zhang, H., Du, J., Xie, C., Zhang, J., Qian, S., Li, R.: AE-FPN: adaptive enhance feature learning for detecting wire defects. SIViP 17(5), 2145–2155 (2023). https://doi.org/10.1007/s11760-022-02429-3
Meng, D., Boer, W.U., Juan, X.U., Kasule, A.N., Hongfu, Z.U.O.: Visual inspection of aircraft skin: automated pixel-level defect detection by instance segmentation. Chin. J. Aeronaut. 35(10), 254–264 (2022). https://doi.org/10.1016/j.cja.2022.05.002
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., Berg, A. C.: Ssd: Single shot multibox detector. In: computer vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pp. 21–37. Springer International Publishing (2016).
Lin, T. Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: proceedings of the IEEE international conference on computer vision, pp. 2980–2988 (2017)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: 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)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. Preprint at arXiv:1804.02767 (2018)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263–7271 (2017)
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)
Xu, L., Cao, B., Xu, P., Zhao, F.: Infrared target detection using deep learning algorithms. Signal Image and Video Process. (2023). https://doi.org/10.1007/s11760-023-02629-5
Sun, S., Han, L., Wei, J., Hao, H., Huang, J., Xin, W., Kang, P.: ShuffleNetv2-YOLOv3: a real-time recognition method of static sign language based on a lightweight network. Signal Image Video Process. (2023). https://doi.org/10.1007/s11760-023-02489-z
Acikgoz, H.: An automatic detection model for cracks in photovoltaic cells based on electroluminescence imaging using improved YOLOv7. Signal Image Video Process. (2023). https://doi.org/10.1007/s11760-023-02724-7
Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L.: Microsoft coco: common objects in context. In: Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6–12, 2014, Proceedings, Part V 13 (pp. 740–755). Springer International Publishing (2014)
Zhang, Q. L., Yang, Y. B.: Sa-net: Shuffle attention for deep convolutional neural networks. In: ICASSP 2021–2021 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 2235–2239). IEEE (2021)
Tan, M., Pang, R., Le, Q. V.: Efficientdet: scalable and efficient object detection. In: proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp.10781–10790 (2020)
Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1251–1258 (2017)
Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. Computer Vision—ECCV 2018. ECCV 2018. Lecture notes in computer science, vol 11211 (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8759–8768 (2018)
Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N: Varifocalnet: an iou-aware dense object detector. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 8514–8523 (2021)
Gevorgyan, Z.: SIoU loss: more powerful learning for bounding box regression. Preprint at arXiv:2205.12740 (2022)
Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M.: Yolov4: optimal speed and accuracy of object detection. Preprint at arXiv:2004.10934 (2020)
Funding
This study was supported by the National Natural Science Foundation of China (grant no. U2133202), and Major Science and Technology Special Projects in Sichuan Province, China (grant no. 2021ZDZX0001).
Author information
Authors and Affiliations
Contributions
Lanxue Fu proposed this method and trained the model, as well as collected data to establish the dataset. Hao Wang directed the writing of the thesis and helped revise and polish it.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
Ethical approval
Not applicable.
Consent for publication
Author agreed with the content and that all gave explicit consent to submit.
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.
About this article
Cite this article
Wang, H., Fu, L. & Wang, L. Detection algorithm of aircraft skin defects based on improved YOLOv8n. SIViP 18, 3877–3891 (2024). https://doi.org/10.1007/s11760-024-03049-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-024-03049-9