Abstract
Ship detection plays an increasing role in security surveillance of inland water transport. However, it is often disturbed by environment noises such as water ripples, stronger scattering, and fluctuating weather. Due to the influence of these sophisticated factors, the current target detection algorithms cannot balance speed, accuracy, and model size in the changeable and complex inland river environment well. To solve this problem, this paper proposes a lightweight dual dynamic ship detection network based on YOLOv5s, which has few parameters and achieves high accuracy. Specifically, mixup data augmentation is introduced in training to balance the uneven distribution of different ship types while enhancing ship characteristics. Then a light pyramid split attention (LPSA) module is also designed to extract features with different perceptual fields, which enriches the ship feature information and suppresses the interference factors in the images. Finally, a dynamic cross stage partial (D-CSP) module is designed with dynamic convolution to extract ship features more efficiently by weighting the input computation with multiple convolution kernels before performing the convolution computation. Experimental results demonstrate that our proposed algorithm enhances the F1 value from 79.2% to 85.7%, and increases mAP@0.5 value from 82.4% to 89.0% when compared to original YOLOv5s. These results also clearly indicate the effectiveness of our model in achieving superior detection capabilities through the integration of the D-CSP and LPSA modules while keeping a satisfactory speed and model size.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03607-1/MediaObjects/11760_2024_3607_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03607-1/MediaObjects/11760_2024_3607_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03607-1/MediaObjects/11760_2024_3607_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03607-1/MediaObjects/11760_2024_3607_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03607-1/MediaObjects/11760_2024_3607_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03607-1/MediaObjects/11760_2024_3607_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03607-1/MediaObjects/11760_2024_3607_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11760-024-03607-1/MediaObjects/11760_2024_3607_Fig8_HTML.png)
Similar content being viewed by others
References
Zhang, L., Shah, S.K., Kakadiaris, I.A.: Hierarchical multi-label classification using fully associative ensemble learning. Pattern Recogn. 70, 89–103 (2017). https://doi.org/10.1016/j.patcog.2017.05.007
Yang, F., Xu, Q., Li, B., Ji, Y.: Ship detection from thermal remote sensing imagery through region-based deep forest. IEEE Geosci. Remote Sens. Lett. 15(3), 449–453 (2018)
Girshick, R.: Fast R-CNN. In: Proc of IEEE International Conference of Computer Vision, pp. 1440–1448 (2015)
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(6), 1137–1149 (2017)
Dai, J., Li, Y., He, K., Sun, J.: R-fcn: Object detection via region-based fully convolutional networks. Adv. Neural Inf. Process. Syst. 379–387 (2016)
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 (2016)
Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE Internationa L 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.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Wong, G.J., King, A.: YOLOv5: You only look once v5. https://github.com/ultralytics/yolov5. Accessed: 2023-05-30 (2020)
Peng, X., Zhong, R., Li, Z., Li, Q.: Optical remote sensing image change detection based on attention mechanism and image difference. IEEE Trans. Geosci. Remote Sens. 59, 7296–7307 (2021)
Zou, Y., Zhao, L., Qin, S., Pan, M., Li, Z.: Ship target detection and identification based on ssd_mobilenetv2. In: 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), pp. 1676–1680. IEEE (2020)
Huang, H., Sun, D., Wang, R., Zhu, C., Liu, B.: Ship target detection based on improved yolo network. Math. Probl. Eng. 2020, 6402149 (2020)
Zhou, W., Liu, L.: Multilayer attention receptive fusion network for multiscale ship detection with complex background. J. Electron. Imaging 31(4), 043029 (2022)
Han, X., Zhao, L., Ning, Y., Hu, J.: Shipyolo: an enhanced model for ship detection. J. Adv. Transp. 2021, 1–11 (2021)
Ting, L., Baijun, Z., Yongsheng, Z., Shun, Y.: Ship detection algorithm based on improved yolo v5. In: 2021 6th International Conference on Automation, Control and Robotics Engineering (CACRE), pp. 483–487. IEEE (2021)
Zhou, W., Peng, Y.: Ship detection based on multi-scale weighted fusion. Displays 78, 102448 (2023)
Wang, Y., Li, J., Chen, Z., Wang, C.: Ships’ small target detection based on the cbam-yolox algorithm. J. Marine Sci. Eng. 10, 2013 (2022)
Chen, Z., Liu, C., Filaretov, V., Yukhimets, D.: Multi-scale ship detection algorithm based on yolov7 for complex scene sar images. Remote. Sens. 15, 2071 (2023)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)
Zhang, H., Zu, K., Lu, J., Zou, Y., Meng, D.: Epsanet: An efficient pyramid split attention block on convolutional neural network. arxiv 2021. arXiv preprint arXiv:2105.14447 (2021)
Li, Y., Chen, Y., Dai, X., Liu, M., Chen, D., Yu, Y., Yuan, L., Liu, Z., Chen, M., Vasconcelos, N.: Revisiting dynamic convolution via matrix decomposition. arXiv preprint arXiv:2103.08756 (2021)
Shao, Z., Wu, W., Wang, Z., Du, W., Li, C.: Seaships: a large-scale precisely annotated dataset for ship detection. IEEE Trans. Multimed. 20(10), 2593–2604 (2018)
Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)
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)
Funding
This research was funded in part by the State Key Laboratory of ASIC & System (2021KF010) and National Natural Science Foundation of China (Grant No. 61404083).
Author information
Authors and Affiliations
Contributions
Weina Zhou: Conceptualization, Methodology, Resources, Supervision, Writing -review and editing, Project administration. Chengsong Gu:Methodology, Software, Validation, Formal analysis, Investigation,Data curation, Writing original draft, Visualization.
Corresponding author
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.
About this article
Cite this article
Zhou, W., Gu, C. A lightweight dual dynamic ship detection network with complex background of inland river. SIViP 19, 94 (2025). https://doi.org/10.1007/s11760-024-03607-1
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11760-024-03607-1