A Lightweight Ship Target Detection Method based on Improved YOLOv8

Authors

  • Shiquan Yuan
  • Jianming Zheng

DOI:

https://doi.org/10.6919/ICJE.202412_10(12).0009

Keywords:

YOLOv8; Object Detection and Recognition; Attention Mechanism; Ships.

Abstract

In the realm of modern maritime and inland shipping management, the demands for sophisticated oversight are continually escalating. With the seamless fusion of deep learning and computer vision, ship target detection has emerged as a pivotal detection method within shipping management. To address the challenges posed by varying ship sizes and high quantities in complex scenarios, where traditional computer vision methods suffer from inadequate detection accuracy and sluggish recognition speeds, this paper introduces a lightweight ship target detection approach, CL-YOLO, based on an improved YOLOv8 model. Initially, we integrate the Coordinate Attention mechanism with the C2f module, decoupling and optimizing the channel attention mechanism. By individually fusing features across two distinct spatial dimensions, we devise an efficient one-dimensional feature encoding strategy that alleviates the model's computational burden. Furthermore, to enhance the model's detection efficiency, we incorporate the Large Kernel Attention (LKA) mechanism into the Backbone, significantly boosting detection accuracy without altering the parameter count. Upon experimenting with the optimized model on the SeaShips dataset, we observed an 1.1% increase in mean Average Precision (mAP) compared to the unoptimized YOLOv8, achieving a remarkable 97.5%. This underscores CL-YOLO's superior accuracy in detecting inland ships.

Downloads

Download data is not yet available.

References

[1] Girshick R. Fast r-cnn[C].Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.

[2] Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 91-99.

[3] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.

[4] Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C].Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016: 21-37.

[5] Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[C].Proceedings of the IEEE international conference on computer vision. 2017: 2980-2988.

[6] ZHANG S M, SUN Y W, FAN W, et al. Research progress in the application of deep learning methods for marine fishery production: a review[J]. Journal of Dalian Ocean University, 2022, 37(4): 683-695.

[7] WANG S X, ZHANG S M, ZHU W B, et al. Application of an electronic monitoring system for video target detection in tuna longline fishing based on YOLOR5 deep learning model [J]. Journal of Dalian Ocean University, 2021, 36(5): 842-850.

[8] TU W, YU H, ZHANG P, et al. Farmed fish detection by improved Yolov8 based on channel non-degradation attention with weighted spatial pyramid pooling attention network attention [J]. Journal of Dalian Ocean University, 2023, 38(4): 717-725.

[9] YUAN H C, TAO L. Detection and identification of fish in electronic monitoring data of commercial fishing vessels based on improved Yolov8 [J]. Journal of Dalian Ocean University, 2023, 38(3): 533-542.

[10] MEI H B, HUANG A Z, YAO A H C. A lightweight and efficient object detection method based on improved yolov7 model [J]. Journal of Dalian Ocean University, 2023, 38(6): 1032-1043.

[11] WU Z G, CHEN M. Lightweight detection method based on improved yolov7 model [J]. Journal of Dalian Ocean University, 2023, 38(1): 129-139.

[12] GAO Y,WU Z,REN M,et al. Improved YOLOv4 based on attention mechanism for ship detection in SAR images[J].IEEE Access,2022,10:23785-23797.

[13] Huang. Research on Fall Detection Algorithm Based on Improved YOLOv7 [D]. Wuhan: Jianghan University, 2023.

[14] YIN Y,LEI L,LIANG M,et al. Research on fall detection algorithm for the elderly living alone based on YOLO[C] / / 2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT). Chongqing:IEEE,2021:403-408.

[15] Woo S, Debnath S, Hu R, et al. Convnext v2: Codesigning and scaling convnets with masked autoencoders[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 16133-16142.

[16] WANG Wenliang, LI Yanxiang, ZHANG Yifan,et al.MPANet-YOLOv5:Complex sea target detection by multipath aggregation network[J]. Journal of Hunan University(Natural Science Edition),2022, 49(10):69-76.

[17] ZHANG X P, XU Z Y, QU S, et al. Recognition algorithm of marine ship based on improved YOLOv5 deep learning [J]. Journal of Dalian Ocean University, 2022, 37(5): 866-872.

[18] ZHANG D C, LI H T, LI X, et al. Optimization of Yolov5 fish vessel target detection based on CBAM and BiFPN [J]. Fishery Modernization, 2022, 49(3): 71-80.

Downloads

Published

2024-11-19

Issue

Section

Articles

How to Cite

Yuan, Shiquan, and Jianming Zheng. 2024. “A Lightweight Ship Target Detection Method Based on Improved YOLOv8”. International Core Journal of Engineering 10 (12): 71-79. https://doi.org/10.6919/ICJE.202412_10(12).0009.