Abstract
To address missed detections and limited efficiency in small fragment-impact recognition on target plates during warhead testing, this paper proposes small fragment detection YOLO (SFD-YOLO), a task-oriented detection framework built upon YOLOv11. An improved Spatial–Channel Reconstruction C3k2 (SCC3k2) module is integrated into the backbone to suppress redundant responses in both spatial and channel dimensions, enhancing the representation of weak micro-scale impact cues. To improve sensitivity to extremely small targets, we introduce an additional micro-object detection head and adopt an Asymptotic Feature Pyramid Network (AFPN) for progressive multi-level feature alignment and fusion, which strengthens feature consistency across pyramid levels. In addition, a Lightweight Adaptive Extraction (LAE) module is employed to replace standard convolutions, reducing model complexity while maintaining effective feature extraction. To comprehensively evaluate performance in realistic testing scenarios, we construct a multi-scene target-plate dataset from a series of static explosion experiments, covering both penetrative fragment holes and non-penetrative impact marks. Experimental results demonstrate that SFD-YOLO achieves 98.1% mAP@0.5 and 69.7% mAP@0.5:0.95, outperforming the YOLOv11 baseline by 2.7% in mAP@0.5 and 6.8% in mAP@0.5:0.95, at 135 FPS with only 2.15M parameters. Moreover, robustness evaluations under image degradations indicate that SFD-YOLO maintains more stable detection performance than the baseline. The proposed method provides a high-precision real-time solution for fragment lethality evaluation and shows potential for broader applications such as metal surface defect inspection.
Data availability
The relevant datasets and data used in this study can be obtained upon request to the corresponding author upon reasonable request, subject to applicable safety and confidentiality constraints.
References
Elveli, B. S. et al. Thin steel plates exposed to combined ballistic impact and partially confined airblast loading. Eng. Fail. Anal. 144, 106943. https://doi.org/10.1016/j.engfailanal.2022.106943 (2023).
Li, H., Zhang, X., Zhang, X. & Gao, J. Warhead fragments’ distribution measurement method by a multiscreen sensors’ intersection test mechanism and equivalent target damage probability calculation. IEEE Trans. Instrum. Meas. 70, 1–9. https://doi.org/10.1109/TIM.2021.3079557 (2021).
Gao, J. & Zhang, X. Fragment perforation spatial localization measurement method and calculation analysis by using photogrammetry technology. IEEE Access 11, 102092–102102. https://doi.org/10.1109/ACCESS.2023.3312014 (2023).
Guildenbecher, D. R. et al. 3d optical diagnostics for explosively driven deformation and fragmentation. Int. J. Impact Eng 162, 104142. https://doi.org/10.1016/j.ijimpeng.2021.104142 (2022).
Chen, C., Shi, Q., Feng You, Z., Yu Ge, H. & Zhang, F. A method to determine the shell layout scheme for equipment battlefield damage tests under artillery fire. Defence Technol. 17, 682–691. https://doi.org/10.1016/j.dt.2020.02.019 (2021).
Felix, D., Colwill, I. & Harris, P. Real-time simulation of a fragmenting explosion for cylindrical warheads. J. Defense Model. Simul. 19, 783–797. https://doi.org/10.1177/1548512921995560 (2022).
Zhang, G. et al. A novel detection method for warhead fragment targets in optical images under dynamic strong interference environments. Defence Technol. 43, 252–270. https://doi.org/10.1016/j.dt.2024.08.008 (2025).
Hussain, M. Yolo-v1 to yolo-v8, the rise of yolo and its complementary nature toward digital manufacturing and industrial defect detection. Machines https://doi.org/10.3390/machines11070677 (2023).
Dong, Y., Yang, L., Jin, Z. & Wu, L. Experimental and numerical analysis of ballistic impact response of fiber-reinforced composite/metal composite target. Compos. Struct. 294, 115776. https://doi.org/10.1016/j.compstruct.2022.115776 (2022).
Li, Y. Research and application of deep learning in image recognition. In 2022 IEEE 2nd International Conference on Power, Electronics and Computer Applications (ICPECA), 994–999. https://doi.org/10.1109/ICPECA53709.2022.9718847 (2022).
Song, W. et al. Accurate extraction of fragmented field boundaries using classification-assisted and cnn-based semantic segmentation methods. In 2023 11th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), 1–4. https://doi.org/10.1109/Agro-Geoinformatics59224.2023.10233358 (2023).
Rusyn, B., Lutsyk, O., Kosarevych, R., Maksymyuk, T. & Gazda, J. Features extraction from multi-spectral remote sensing images based on multi-threshold binarization. Sci. Rep. 13, 19655. https://doi.org/10.1038/s41598-023-46785-7 (2023).
Zhang, Y., Zhao, H., Li, X., Li, H. & Jin, J. Mers-net: A lightweight and efficient remote sensing image object detector. IEEE Geosci. Remote Sens. Lett. https://doi.org/10.1109/LGRS.2025.3569672 (2025).
Ghorai, S., Mukherjee, A., Gangadaran, M. & Dutta, P. K. Automatic defect detection on hot-rolled flat steel products. IEEE Trans. Instrum. Meas. 62, 612–621. https://doi.org/10.1109/TIM.2012.2218677 (2013).
Li, R. & Shen, Y. Yolosr-ist: A deep learning method for small target detection in infrared remote sensing images based on super-resolution and yolo. SIGNAL PROCESSING 208, (2023) https://doi.org/10.1016/j.sigpro.2023.108962.
He, M., Qin, L., Deng, X. & Liu, K. Mfi-yolo: Multi-fault insulator detection based on an improved yolov8. IEEE Trans. Power Delivery 39, 168–179. https://doi.org/10.1109/TPWRD.2023.3328178 (2024).
Safaldin, M., Zaghden, N. & Mejdoub, M. An improved yolov8 to detect moving objects. IEEE ACCESS 12, 59782–59806. https://doi.org/10.1109/ACCESS.2024.3393835 (2024).
Zhao, L., Zhi, L., Zhao, C. & Zheng, W. Fire-yolo: A small target object detection method for fire inspection. Sustainability https://doi.org/10.3390/su14094930 (2022).
Zou, Z., Chen, K., Shi, Z., Guo, Y. & Ye, J. Object detection in 20 years: A survey. Proc. IEEE 111, 257–276. https://doi.org/10.1109/JPROC.2023.3238524 (2023).
Yao, Y. et al. On improving bounding box representations for oriented object detection. IEEE Trans. Geosci. Remote Sens. https://doi.org/10.1109/TGRS.2022.3231340 (2023).
Jiao, L. et al. A survey of deep learning-based object detection. IEEE Access 7, 128837–128868. https://doi.org/10.1109/ACCESS.2019.2939201 (2019).
Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, 580–587. https://doi.org/10.1109/CVPR.2014.81 (2014).
Girshick, R. Fast r-cnn. In 2015 IEEE International Conference on Computer Vision (ICCV), 1440–1448, (2015) https://doi.org/10.1109/ICCV.2015.169.
Ren, S., He, K., Girshick, R. & Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031 (2017).
Liu, W. et al. Ssd: Single shot multibox detector. In Computer Vision - ECCV 2016 (eds Leibe, B. et al.) 21–37 (Springer International Publishing, 2016).
Duan, K. et al. Centernet: Keypoint triplets for object detection. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 6568–6577. https://doi.org/10.1109/ICCV.2019.00667 (2019).
Carion, N. et al. End-to-end object detection with transformers. In Computer Vision - ECCV 2020 (eds Vedaldi, A. et al.) 213–229 (Springer International Publishing, 2020).
Zhang, J., Sun, H. & Li, C. Study on the detection method of broken piece perforation and crater based on hyperbolic threshold segmentation. In Second IYSF Academic Symposium on Artificial Intelligence and Computer Engineering, vol. 12079, 556–560 (SPIE, 2021).
Lei, J., Wang, Z. & Li, J. Research on target detection of fragment image based on faster r-cnn. Foreign Electr. Meas. Technol. 40, 70–74. https://doi.org/10.19652/j.cnki.femt.2002308 (2021).
Wei, Q., He, Z., Wang, Y. & Wang, J. Research on fragment identification of a static explosion field based on densenet and attention mechanism. J. Ordnance Equip. Eng. 44, 259–265 (2023).
He, M., Wu, J., Liang, C., Hu, P. & Ren, Y. Few-shot warhead fragment group object detection based on feature reassembly and attention. Opt. Precis. Eng. 32, 1929–1940 (2024).
Gao, J., Han, H. & Li, H. A semantic segmentation and distortion correction of fragment perforation small target. IEEE Access 12, 82769–82781. https://doi.org/10.1109/ACCESS.2024.3412796 (2024).
Zhang, C. et al. Aggregation connection network for tiny face detection. In 2019 International Joint Conference on Neural Networks (IJCNN), 1–8, (2019) https://doi.org/10.1109/IJCNN.2019.8852083.
Tang, X., Du, D. K., He, Z. & Liu, J. Pyramidbox: A context-assisted single shot face detector. In Computer Vision - ECCV 2018 (eds Ferrari, V. et al.) 812–828 (Springer International Publishing, 2018).
Guo, C., Fan, B., Zhang, Q., Xiang, S. & Pan, C. Augfpn: Improving multi-scale feature learning for object detection. In: Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020).
Zhang, Y. et al. Ffca-yolo for small object detection in remote sensing images. IEEE Trans. Geosci. Remote Sens. 62, 1–15. https://doi.org/10.1109/TGRS.2024.3363057 (2024).
Chen, Y. et al. Dynamic scale training for object detection 2004, 12432 (2021).
Yu, X., Gong, Y., Jiang, N., Ye, Q. & Han, Z. Scale match for tiny person detection. In 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 1246–1254, (2020) https://doi.org/10.1109/WACV45572.2020.9093394.
Yu, Z. et al. Lsm-yolo: A compact and effective roi detector for medical detection. arXiv preprint arXiv:2408.14087 (2024).
Yang, G., Lei, J., Tian, H., Feng, Z. & Liang, R. Asymptotic feature pyramid network for labeling pixels and regions. IEEE Trans. Circuits Syst. Video Technol. 34, 7820–7829. https://doi.org/10.1109/TCSVT.2024.3376773 (2024).
Maruschak, P. et al. Surface defects of rolled metal products recognised by a deep neural network under different illuminance levels and low-amplitude vibration. Int. J. Adv. Manuf. Technol. 139, 449–464. https://doi.org/10.1007/s00170-025-15942-9 (2025).
Krishna, H. & Jawahar, C. Improving small object detection. In 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR), 340–345. https://doi.org/10.1109/ACPR.2017.149 (2017).
Cao, Z., Chen, K., Chen, J., Chen, Z. & Zhang, M. Cacs-yolo: A lightweight model for insulator defect detection based on improved yolov8m. IEEE Trans. Instrum. Meas. 73, 1–10. https://doi.org/10.1109/TIM.2024.3453332 (2024).
Acknowledgements
The authors would like to thank all colleagues who provided helpful discussions and technical support.
Funding
This research was supported by the National Natural Science Foundation of China grant number 61701445, the Open Research Foundation of the Key Laboratory of North University of China grant number DXMBJJ202007, and the “Fundamental Research Program” of Shanxi Province grant number 20210302124200.
Author information
Authors and Affiliations
Contributions
H.L. conceived the study, developed the SFD-YOLO method, implemented the algorithms, and performed model training and data analysis. Y.D. contributed to dataset construction, experiment coordination, and validation of detection results. W.Y. supervised the research, provided methodological guidance, and oversaw project progress. Y.L. assisted with investigation, data curation, and performance evaluation. H.L. drafted the manuscript, and all authors revised and approved the final version.
Corresponding author
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
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Liu, H., Ding, Y., You, W. et al. SFD-YOLO for small-object fragment impact detection in warhead target-plate testing. Sci Rep (2026). https://doi.org/10.1038/s41598-026-40457-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-40457-y
