EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLOv8m-CGSE: An Improved Lightweight YOLOv8m for Marine Oil Spill Detection

Qingyang Wang, Junjie Lu, Bin Yang, Chen Jiao, Tao Yue, Bo Song, Jianwu Jiang, Guoqing Zhou, Jingwen Li

Journal of Marine Science and Engineering · 29.05.2026 · 14 (11) · 1010

DOI: 10.3390/jmse14111010 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 29.05.2026. Verfasst von Qingyang Wang und 8 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Young and Middle-aged Teachers’ Basic Scientific Research Ability Improvement Project, Qingmiao Talent Research Project Funding, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unmanned Aerial Vehicle (UAV) remote sensing images provide high-resolution and flexible monitoring data for oil spill detection. To address the high computational cost and low accuracy of traditional models, this study proposes an improved model, YOLOv8m-CGSE. The model replaces standard convolution with Group Shuffle Convolution (GSConv), substitutes the C2f module with SENetV2, and introduces a light-weight Cross-scale Context Fusion Module (CCFM) to enhance multi-scale feature representation while maintaining a lightweight structure. Mosaic augmentation was applied to the marine oil spill dataset, improving mAP50 and mAP50–95 to 85.4% and 62.0%, respectively. Based on YOLOv8m, the proposed YOLOv8m-CGSE achieved mAP50 and mAP50–95 of 91.2% and 73.3%, respectively, improving accuracy while reducing parameters by 16.1% and computational cost by 12.6%. Furthermore, a supplementary vulnerability test on highly deceptive oil-free sea surfaces demonstrated that the proposed model actively suppresses complex background clutter (e.g., ship wakes and wave anomalies), effectively reducing false positive detections from 21 (baseline) to 15. The results demonstrate that the proposed model effectively balances high precision, robustness against visual lookalikes and computational efficiency for real-time marine oil spill monitoring.

Förderung

  • Guangxi Young and Middle-aged Teachers’ Basic Scientific Research Ability Improvement Project
  • Qingmiao Talent Research Project Funding
  • National Natural Science Foundation of China
  • Guangxi Key Laboratory of Spatial Information and Geomatics Program
  • Guilin University of Technology

Zitieren

APA

Wang, Q., Lu, J., Yang, B., Jiao, C., Yue, T., Song, B., Jiang, J., Zhou, G., & Li, J. (2026). YOLOv8m-CGSE: An Improved Lightweight YOLOv8m for Marine Oil Spill Detection. Journal of Marine Science and Engineering, 14(11), 1010. https://doi.org/10.3390/jmse14111010

Vancouver

Wang Q, Lu J, Yang B, Jiao C, Yue T, Song B, et al. YOLOv8m-CGSE: An Improved Lightweight YOLOv8m for Marine Oil Spill Detection. Journal of Marine Science and Engineering. 2026;14(11):1010. doi:10.3390/jmse14111010

BibTeX
@article{Wang2026,
  author = {Wang, Qingyang and Lu, Junjie and Yang, Bin and Jiao, Chen and Yue, Tao and Song, Bo and Jiang, Jianwu and Zhou, Guoqing and Li, Jingwen},
  title = {YOLOv8m-CGSE: An Improved Lightweight YOLOv8m for Marine Oil Spill Detection},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {11},
  pages = {1010},
  doi = {10.3390/jmse14111010}
}
Kostenlos starten →